Search results for: parsing

Authors: Jamil Ahmed

Abstract:

Left to Right-Right Most (LR) parsing algorithm is a widely used algorithm of syntax analysis. It is contingent on a parsing table, whereas the parsing tables are extracted from the grammar. The parsing table specifies the actions to be taken during parsing. It requires that the parsing table should have no action conflicts for the same input symbol. This requirement imposes a condition on the class of grammars over which the LR algorithms work. However, there are grammars for which the parsing tables hold action conflicts. In such cases, the algorithm needs a capability of scanning (looking-ahead) next input symbols ahead of the current input symbol. In this paper, a ‘Left to Right’-‘Right Most’ parsing algorithm with lookahead capability is introduced. The 'look-ahead' capability in the LR parsing algorithm is the major contribution of this paper. The practicality of the proposed algorithm is substantiated by the parser implementation of the Context Free Grammar (CFG) of an already proposed programming language 'State Controlled Object Oriented Programming' (SCOOP). SCOOP’s Context Free Grammar has 125 productions and 192 item sets. This algorithm parses SCOOP while the grammar requires to ‘look ahead’ the input symbols due to action conflicts in its parsing table. Proposed LR parsing algorithm with lookahead capability can be viewed as an optimization of ‘Simple Left to Right’-‘Right Most’ (SLR) parsing algorithm.

Keywords: left to right-right most parsing, syntax analysis, bottom-up parsing algorithm

Procedia PDF Downloads 126

Authors: Yukiko Sasaki Alam, Shahid Alam

Abstract:

Syntactic parsing is vital for semantic treatment by many applications related to natural language processing (NLP), because form and content coincide in many cases. However, it has not yet reached the levels of reliable performance. By manually examining and analyzing individual machine translation output errors that involve syntax as well as semantics, this study attempts to discover what is required for improving syntactic and semantic parsing.

Keywords: syntactic parsing, error analysis, machine translation, deep parsing

Procedia PDF Downloads 560

Authors: Weitao Lin

Abstract:

To quickly extract adequate information from large-scale unstructured text data, this paper studies the representation of events in Chinese scenarios and performs the regularized abstraction. It proposes a Chinese event detection technique based on dependency parsing and rule matching. The method first performs dependency parsing on the original utterance, then performs pattern matching at the word or phrase granularity based on the results of dependent syntactic analysis, filters out the utterances with prominent non-event characteristics, and obtains the final results. The experimental results show the effectiveness of the method.

Keywords: natural language processing, Chinese event detection, rules matching, dependency parsing

Procedia PDF Downloads 141

Authors: Liu Lin Xin

Abstract:

With the increasing complexity of systems, log parsing and anomaly detection have become crucial for maintaining system stability. However, traditional methods often struggle with adaptability and accuracy, especially when dealing with rapidly evolving log content and unfamiliar domains. To address these challenges, this paper proposes approach that integrates Retrieval Augmented Generation (RAG) technology with Prompt Engineering for Large Language Models, applied specifically in LogPrompt. This approach enables dynamic log parsing and intelligent anomaly detection by combining real-time information retrieval with prompt optimization. The proposed method significantly enhances the adaptability of log analysis and improves the interpretability of results. Experimental results on several public datasets demonstrate the method's superior performance, particularly in scenarios lacking training data, where it significantly outperforms traditional methods. This paper introduces a novel technical pathway for log parsing and anomaly detection, showcasing the substantial theoretical value and practical potential.

Keywords: log parsing, anomaly detection, RAG, prompt engineering, LLMs

Procedia PDF Downloads 33

Authors: Liu Linxin

Abstract:

As system complexity increases, log parsing and anomaly detection become more and more important in ensuring system stability. However, traditional methods often face the problems of insufficient adaptability and decreasing accuracy when dealing with rapidly changing log contents and unknown domains. To this end, this paper proposes an approach LogRAG, which combines RAG (Retrieval Augmented Generation) technology with Prompt Engineering for Large Language Models, applied to log analysis tasks to achieve dynamic parsing of logs and intelligent anomaly detection. By combining real-time information retrieval and prompt optimisation, this study significantly improves the adaptive capability of log analysis and the interpretability of results. Experimental results show that the method performs well on several public datasets, especially in the absence of training data, and significantly outperforms traditional methods. This paper provides a technical path for log parsing and anomaly detection, demonstrating significant theoretical value and application potential.

Keywords: log parsing, anomaly detection, retrieval-augmented generation, prompt engineering, LLMs

Procedia PDF Downloads 29

Authors: Parthiban Srinivasan

Abstract:

PubMed provides online access to the National Library of Medicine database (MEDLINE) and other publications, which contain close to 25 million scientific citations from 1865 to the present. There are close to 80 million author name instances in those close to 25 million citations. For any work of literature, a fundamental issue is to identify the individual(s) who wrote it, and conversely, to identify all of the works that belong to a given individual. Due to the lack of universal standards for name information, there are two aspects of name ambiguity: name synonymy (a single author with multiple name representations), and name homonymy (multiple authors sharing the same name representation). In this talk, we present some results from our extensive work in author name disambiguation for PubMed citations. Information will be presented on the effectiveness and shortcomings of different aspects of successful name disambiguation such as parsing, validation, standardization and normalization.

Keywords: disambiguation, normalization, parsing, PubMed

Procedia PDF Downloads 300

Authors: R. Kumaravelu, S. Poornima, Sunil Kumar Kashyap

Abstract:

The optimized and digitalized restoration of the information from the old and used manual jacquard punched card in textile industry is referred to as Jacquard Punch Card (JPC) reader. In this paper, we present a novel design and development of photo electronics based system for reading old and used punched cards and storing its binary information for transforming them into an effective image file format. In our textile industry the jacquard punched cards holes diameters having the sizes of 3mm, 5mm and 5.5mm pitch. Before the adaptation of computing systems in the field of textile industry those punched cards were prepared manually without digital design source, but those punched cards are having rich woven designs. Now, the idea is to retrieve binary information from the jacquard punched cards and store them in digital (Non-Graphics) format before processing it. After processing the digital format (Non-Graphics) it is converted into an effective image file format through either by Row major or Column major parsing technique.To accomplish these activities, an embedded system based device and software integration is developed. As part of the test and trial activity the device was tested and installed for industrial service at Weavers Service Centre, Kanchipuram, Tamilnadu in India.

Keywords: file system, SPI. UART, ARM controller, jacquard, punched card, photo LED, photo diode

Procedia PDF Downloads 167

Authors: Duong Thuy Nguyen, Giulia Bencini

Abstract:

The present study examined structural and prosodic factors on the computation of antecedent-reflexive relationships and sentence comprehension in native English (L1) and Vietnamese-English bilinguals (L2). Participants read sentences presented on the computer screen in one of three presentation formats aimed at manipulating prosodic parsing: word-by-word (RSVP), phrase-segment (self-paced), or whole-sentence (self-paced), then completed a grammaticality rating and a comprehension task (following Pratt & Fernandez, 2016). The design crossed three factors: syntactic structure (simple; complex), grammaticality (target-match; target-mismatch) and presentation format. An example item is provided in (1): (1) The actress that (Mary/John) interviewed at the awards ceremony (about two years ago/organized outside the theater) described (herself/himself) as an extreme workaholic). Results showed that overall, both L1 and L2 speakers made use of a good-enough processing strategy at the expense of more detailed syntactic analyses. L1 and L2 speakers’ comprehension and grammaticality judgements were negatively affected by the most prosodically disrupting condition (word-by-word). However, the two groups demonstrated differences in their performance in the other two reading conditions. For L1 speakers, the whole-sentence and the phrase-segment formats were both facilitative in the grammaticality rating and comprehension tasks; for L2, compared with the whole-sentence condition, the phrase-segment paradigm did not significantly improve accuracy or comprehension. These findings are consistent with the findings of Pratt & Fernandez (2016), who found a similar pattern of results in the processing of subject-verb agreement relations using the same experimental paradigm and prosodic manipulation with English L1 and L2 English-Spanish speakers. The results provide further support for a Good-Enough cue model of sentence processing that integrates cue-based retrieval and implicit prosodic parsing (Pratt & Fernandez, 2016) and highlights similarities and differences between L1 and L2 sentence processing and comprehension.

Keywords: anaphora resolution, bilingualism, implicit prosody, sentence processing

Procedia PDF Downloads 152

Authors: Hermann Dornhackl, Konstantin Kadletz, Robert Luh, Paul Tavolato

Abstract:

In this paper we describe the use of formal methods to model malware behaviour. The modelling of harmful behaviour rests upon syntactic structures that represent malicious procedures inside malware. The malicious activities are modelled by a formal grammar, where API calls’ components are the terminals and the set of API calls used in combination to achieve a goal are designated non-terminals. The combination of different non-terminals in various ways and tiers make up the attack vectors that are used by harmful software. Based on these syntactic structures a parser can be generated which takes execution traces as input for pattern recognition.

Keywords: malware behaviour, modelling, parsing, search, pattern matching

Procedia PDF Downloads 332

Authors: Reza Morad Sahraei, Roghayeh Kazeminahad

Abstract:

Surveying the structure of NP in Persian, this article tries to show that most of NP constituents are either independent of each other or they are dependent to Determiner Phrase (=DP). The writer follows a uniform minimal analysis to illustrate the structural position of relevant constituents of DP, including Possessive Phrase, Ezafat Phrase and Quantifier Phrase, under the tree diagram. The most important point of this article is the claim that NP is mostly one of the dependents of DP. Hence, the final section of the article deals with and analyzes the structure of DP in Persian. The DP analysis undertaken in this article has some advantages. It can explain the internal relevance of all DP constituents and provides them all a uniform analysis. Also, the semantic importance of Persian genitive marker and its role in parsing is borne out.

Keywords: determiner phrase (DP), ezafat phrase (Ezaf P), noun phrase(NP), possessive phrase (PossP), quantifier phrase (QP)

Procedia PDF Downloads 584

Authors: Ian O'Loughlin

Abstract:

Memory networks aim to integrate some of the recent successes in machine learning with a dynamic memory base that can be updated and deployed in artificial reasoning tasks. These models involve training networks to identify, update, and operate over stored elements in a large memory array in order, for example, to ably perform question and answer tasks parsing real-world and simulated discourses. This family of approaches still faces numerous challenges: the performance of these network models in simulated domains remains considerably better than in open, real-world domains, wide-context cues remain elusive in parsing words and sentences, and even moderately complex sentence structures remain problematic. This innovation, employing an array of stored and updatable ‘memory’ elements over which the system operates as it parses text input and develops responses to questions, is a compelling one for at least two reasons: first, it addresses one of the difficulties that standard machine learning techniques face, by providing a way to store a large bank of facts, offering a way forward for the kinds of long-term reasoning that, for example, recurrent neural networks trained on a corpus have difficulty performing. Second, the addition of a stored long-term memory component in artificial reasoning seems psychologically plausible; human reasoning appears replete with invocations of long-term memory, and the stored but dynamic elements in the arrays of memory networks are deeply reminiscent of the way that human memory is readily and often characterized. However, this apparent psychological plausibility is belied by a recent turn in the study of human memory in cognitive science. In recent years, the very notion that there is a stored element which enables remembering, however dynamic or reconstructive it may be, has come under deep suspicion. In the wake of constructive memory studies, amnesia and impairment studies, and studies of implicit memory—as well as following considerations from the cognitive neuroscience of memory and conceptual analyses from the philosophy of mind and cognitive science—researchers are now rejecting storage and retrieval, even in principle, and instead seeking and developing models of human memory wherein plasticity and dynamics are the rule rather than the exception. In these models, storage is entirely avoided by modeling memory using a recurrent neural network designed to fit a preconceived energy function that attains zero values only for desired memory patterns, so that these patterns are the sole stable equilibrium points in the attractor network. So although the array of long-term memory elements in memory networks seem psychologically appropriate for reasoning systems, they may actually be incurring difficulties that are theoretically analogous to those that older, storage-based models of human memory have demonstrated. The kind of emergent stability found in the attractor network models more closely fits our best understanding of human long-term memory than do the memory network arrays, despite appearances to the contrary.

Keywords: artificial reasoning, human memory, machine learning, neural networks

Procedia PDF Downloads 271

Authors: Raninder Kaur Dhillon, Mayur Jethwa, Hardeep Singh Rai

Abstract:

Information technology has made a pivotal progress across disparate disciplines, one of which is AEC (Architecture, Engineering and Construction) industry. CAD is a form of computer-aided building modulation that architects, engineers and contractors use to create and view two- and three-dimensional models. The AEC industry also uses building information modeling (BIM), a newer computerized modeling system that can create four-dimensional models; this software can greatly increase productivity in the AEC industry. BIM models generate open source IFC (Industry Foundation Classes) files which aim for interoperability for exchanging information throughout the project lifecycle among various disciplines. The methods developed in previous studies require either an IFC schema or MVD and software applications, such as an IFC model server or a Building Information Modeling (BIM) authoring tool, to extract a partial or complete IFC instance model. This paper proposes an efficient algorithm for extracting a partial and total model from an Industry Foundation Classes (IFC) instance model without an IFC schema or a complete IFC model view definition (MVD).

Keywords: BIM, CAD, IFC, MVD

Procedia PDF Downloads 300

Authors: Y. Bablu Singh, B. S. Purkayashtha, Chungkham Yashawanta Singh

Abstract:

Morphological analysis forms the basic foundation in NLP applications including syntax parsing Machine Translation (MT), Information Retrieval (IR) and automatic indexing in all languages. It is the field of the linguistics; it can provide valuable information for computer based linguistics task such as lemmatization and studies of internal structure of the words. Computational Morphology is the application of morphological rules in the field of computational linguistics, and it is the emerging area in AI, which studies the structure of words, which are formed by combining smaller units of linguistics information, called morphemes: the building blocks of words. Morphological analysis provides about semantic and syntactic role in a sentence. It analyzes the Manipuri word forms and produces several grammatical information associated with the words. The Morphological Analyzer for Manipuri has been tested on 3500 Manipuri words in Shakti Standard format (SSF) using Meitei Mayek as source; thereby an accuracy of 80% has been obtained on a manual check.

Keywords: morphological analysis, machine translation, computational morphology, information retrieval, SSF

Procedia PDF Downloads 326

Authors: Bolin Hua

Abstract:

In city governance, various data are involved, including city component data, demographic data, housing data and all kinds of business data. These data reflects different aspects of people, events and activities. Data generated from various systems are different in form and data source are different because they may come from different sectors. In order to reflect one or several facets of an event or rule, data from multiple sources need fusion together. Data from different sources using different ways of collection raised several issues which need to be resolved. Problem of data fusion include data update and synchronization, data exchange and sharing, file parsing and entry, duplicate data and its comparison, resource catalogue construction. Governments adopt statistical analysis, time series analysis, extrapolation, monitoring analysis, value mining, scenario prediction in order to achieve pattern discovery, law verification, root cause analysis and public opinion monitoring. The result of Multi-source data fusion is to form a uniform central database, which includes people data, location data, object data, and institution data, business data and space data. We need to use meta data to be referred to and read when application needs to access, manipulate and display the data. A uniform meta data management ensures effectiveness and consistency of data in the process of data exchange, data modeling, data cleansing, data loading, data storing, data analysis, data search and data delivery.

Keywords: multi-source data fusion, urban comprehensive management, information fusion, government data

Procedia PDF Downloads 393

Authors: Yahya Toyin Muritala, Nonglaksana Kama, Ahmad Yani

Abstract:

The aim of the paper is to investigate various linguistic techniques in enhancing and facilitating the acquisition of the practical knowledge of Arabic grammatical structuring among non-Arab learners of the standard classical Arabic language in non-Arabic speaking academic settings in the course of the current growth of the internationalism and cultural integration in some higher institutions. As the nature of the project requires standard investigations into the unique principal features of Arabic structurings and implications, the findings of the research work suggest some principles to follow in solving the problems faced by learners while acquiring grammatical aspects of Arabic language. The work also concentrates on the the structural features of the language in terms of inflection/parsing, structural arrangement order, functional particles, morphological formation and conformity etc. Therefore, grammatical aspect of Arabic which has gone through major stages in its early evolution of the classical stages up to the era of stagnation, development and modern stage of revitalization is a main subject matter of the paper as it is globally connected with communication and religion of Islam practiced by millions of Arabs and non-Arabs nowadays. The conclusion of the work shows new findings, through the descriptive and analytical methods, in terms of teaching language for the purpose of effective global communication with focus on methods of second language acquisitions by application.

Keywords: language structure, Arabic grammar, classical Arabic, intercultural communication, non-Arabic speaking environment and prospects

Procedia PDF Downloads 399

Authors: Delphine Vendryes, Dushyanth Sekhar, Baojia Tong, Matthew Theisen, Chester Curme

Abstract:

Much of the data that inform the decisions of governments, corporations and individuals are harvested from unstructured documents. Data extraction is defined here as a process that turns non-machine-readable information into a machine-readable format that can be stored, for instance, in a database. In financial services, introducing more automation in data extraction pipelines is a major challenge. Information sought by financial data consumers is often buried within vast bodies of unstructured documents, which have historically required thorough manual extraction. Automated solutions provide faster access to non-machine-readable datasets, in a context where untimely information quickly becomes irrelevant. Data quality standards cannot be compromised, so automation requires high data integrity. This multifaceted task is broken down into smaller steps: ingestion, table parsing (detection and structure recognition), text analysis (entity detection and disambiguation), schema-based record extraction, user feedback incorporation. Selected intermediary steps are phrased as machine learning problems. Solutions leveraging cutting-edge approaches from the fields of computer vision (e.g. table detection) and natural language processing (e.g. entity detection and disambiguation) are proposed.

Keywords: computer vision, entity recognition, finance, information retrieval, machine learning, natural language processing

Procedia PDF Downloads 111

Authors: Yan Huang

Abstract:

Event-related potentials (ERPs) technique helps researchers to make continuous measures on the whole process of language comprehension, with an excellent temporal resolution at the level of milliseconds. The research on sentence processing has developed from the behavioral level to the neuropsychological level, which brings about a variety of sentence processing theories and models. However, the applicability of these models to L2 learners is still under debate. Therefore, the present study aims to investigate the neural mechanisms underlying English subjunctive mood processing by Chinese ESL learners. To this end, English subject clauses with subjunctive moods are used as the stimuli, all of which follow the same syntactic structure, “It is + adjective + that … + (should) do + …” Besides, in order to examine the role that language proficiency plays on L2 processing, this research deals with two groups of Chinese ESL learners (18 males and 22 females, mean age=21.68), namely, high proficiency group (Group H) and low proficiency group (Group L). Finally, the behavioral and neurophysiological data analysis reveals the following findings: 1) Syntax and semantics interact with each other on the SECOND phase (300-500ms) of sentence processing, which is partially in line with the Three-phase Sentence Model; 2) Language proficiency does affect L2 processing. Specifically, for Group H, it is the syntactic processing that plays the dominant role in sentence processing while for Group L, semantic processing also affects the syntactic parsing during the THIRD phase of sentence processing (500-700ms). Besides, Group H, compared to Group L, demonstrates a richer native-like ERPs pattern, which further demonstrates the role of language proficiency in L2 processing. Based on the research findings, this paper also provides some enlightenment for the L2 pedagogy as well as the L2 proficiency assessment.

Keywords: Chinese ESL learners, English subjunctive mood, ERPs, L2 processing

Procedia PDF Downloads 131

Authors: Maria Lina Garrido

Abstract:

This paper aims to reflect upon instruction in English classes with the specific purpose of reading comprehension development, having as its paradigm the considerations presented by William Grabe, in his book Reading in a Second Language: Moving from theory to practice. His concerns regarding the connection between research findings and instructional practices have stimulated the present author to re-evaluate both her long practice as an English reading teacher and as the author of two reading textbooks for graduate students. Elements of the reading process such as linguistic issues, prior knowledge, reading strategies, critical evaluation, and motivation are the main foci of this analysis as far as the activities developed in the classroom are concerned. The experience with university candidates on postgraduate courses with different levels of English knowledge in Bahia, Brazil, has definitely demanded certain adjustments to this author`s classroom setting. Word recognition based on cognates, for example, has been emphasized given the fact that academic texts use many Latin words which have the same roots as the Brazilian Portuguese lexicon. Concerning syntactic parsing, the tenses/verbal aspects, modality and linking words are included in the curriculum, but not with the same depth as the general English curricula. Reading strategies, another essential predictor for developing reading skills, have been largely stimulated in L2 classes in order to compensate for a lack of the appropriate knowledge of the foreign language. This paper presents results that demonstrate that this author`s teaching practice is compatible with the implications and instruction concerning the reading process outlined by Grabe, however, it admits that each class demands specific instructions to meet the needs of that particular group.

Keywords: classroom practice, instructional activities, reading comprehension, reading skills

Procedia PDF Downloads 462

Authors: Barbara Pittau, Piergiorgio Palla, Antonio Mastino

Abstract:

Communication is fundamental to health education. The proper use of medicinal products is a crucial aspect of the health of citizens that affects both safety and health care spending. Therefore, encouraging/promoting communication, concerning the importance of proper use of pharmaceuticals, has substantial implications in terms of individual health, health care, and health care system sustainability. In view of these considerations, in the context of two projects, one of which is still in progress, a relational database-backed web application named COLLABORAFARMACISOLA has been designed and developed as a tool to analyze and visualize how people approach the use of medicinal products, with the aim of improving and enhancing communication efficacy. The software application is being used to collect information (anonymously and voluntarily) from the citizens of Sardinia, an Italian region, regarding their knowledge, experiences, and opinions towards pharmaceuticals. This study that was conducted to date on thousand of interviewed people, has focused on different aspects such as: the treatment interruption and the "self-prescription” without medical consultation, the attention paid to reading the leaflets, the awareness of the economic value of the pharmaceuticals, the importance of avoiding the waste of medicinal products and the attitudes towards the use of generics. To this purpose, our software application provides a set of ad hoc parsing routines, to store information into the structure of a relational database and to process and visualize it through a set of interactive tools aimed to emphasize the findings and the insights obtained. The results of our preliminary analysis show the efficacy of the awareness plan and, at the same time, the criticality and the needs of the territory under examination. The ultimate goal of our study is to provide a contribution to the community by improving communication that can result in a benefit for public health in a context strictly connected to the reality of the territory.

Keywords: communication, pharmaceuticals, public health, relational database, tool, web application

Procedia PDF Downloads 137

Authors: David A. Harness

Abstract:

Natural evolution of ATP cognitive systems is to meet AI peer review standards. ATP process of axiom selection from Mizar to prove a conjecture would be further refined, as in all human and machine learning, by solving the real world problem of the proposed AI peer review challenge: Determine which conjecture forms the higher confidence level constructive proof between Standard Model of Physics SU(n) lattice gauge group operation vs. present non-standard 4D GEM EOS SU(n) lattice gauge group spatially extended operation in which the photon and electron are the first two trace angular momentum invariants of a gravitoelectromagnetic (GEM) energy momentum density tensor wavetrain integration spin-stress pressure-volume equation of state (EOS), initiated via 32 lines of Mathematica code. Resulting gravitoelectromagnetic spectrum ranges from compressive through rarefactive of the central cosmological constant vacuum energy density in units of pascals. Said self-adjoint group operation exclusively operates on the stress energy momentum tensor of the Einstein field equations, introducing quantization directly on the 4D spacetime level, essentially reformulating the Yang-Mills virtual superpositioned particle compounded lattice gauge groups quantization of the vacuum—into a single hyper-complex multi-valued GEM U(1) × SU(1,3) lattice gauge group Planck spacetime mesh quantization of the vacuum. Thus the Mizar corpus already contains all of the axioms required for relevant DeepMath premise selection and unambiguous formal natural language parsing in context deep learning.

Keywords: automated theorem proving, constructive quantum field theory, information theory, neural networks

Procedia PDF Downloads 179

Authors: Aliaksandr Huminski

Abstract:

Semantic Role Labeling (SRL) as shallow semantic parsing approach includes recognition and labeling arguments of a verb in a sentence. Verb participants are linked with specific semantic roles (Agent, Patient, Instrument, Location, etc.). Thus, SRL can answer on key questions such as ‘Who’, ‘When’, ‘What’, ‘Where’ in a text and it is widely applied in dialog systems, question-answering, named entity recognition, information retrieval, and other fields of NLP. However, SRL has the following flaw: Two sentences with identical (or almost identical) meaning can have different semantic role structures. Let consider 2 sentences: (1) John put butter on the bread. (2) John buttered the bread. SRL for (1) and (2) will be significantly different. For the verb put in (1) it is [Agent + Patient + Goal], but for the verb butter in (2) it is [Agent + Goal]. It happens because of one of the most interesting and intriguing features of a verb: Its ability to capture participants as in the case of the verb butter, or their features as, say, in the case of the verb drink where the participant’s feature being liquid is shared with the verb. This capture looks like a total fusion of meaning and cannot be decomposed in direct way (in comparison with compound verbs like babysit or breastfeed). From this perspective, SRL looks really shallow to represent semantic structure. If the key point in semantic representation is an opportunity to use it for making inferences and finding hidden reasons, it assumes by default that two different but semantically identical sentences must have the same semantic structure. Otherwise we will have different inferences from the same meaning. To overcome the above-mentioned flaw, the following approach is suggested. Assume that: P is a participant of relation; F is a feature of a participant; Vcp is a verb that captures a participant; Vcf is a verb that captures a feature of a participant; Vpr is a primitive verb or a verb that does not capture any participant and represents only a relation. In another word, a primitive verb is a verb whose meaning does not include meanings from its surroundings. Then Vcp and Vcf can be decomposed as: Vcp = Vpr +P; Vcf = Vpr +F. If all Vcp and Vcf will be represented this way, then primitive verbs Vpr can be considered as a canonical form for SRL. As a result of that, there will be no hidden participants caught by a verb since all participants will be explicitly unfolded. An obvious example of Vpr is the verb go, which represents pure movement. In this case the verb drink can be represented as man-made movement of liquid into specific direction. Extraction and using primitive verbs for SRL create a canonical representation unique for semantically identical sentences. It leads to the unification of semantic representation. In this case, the critical flaw related to SRL will be resolved.

Keywords: decomposition, labeling, primitive verbs, semantic roles

Procedia PDF Downloads 366

Authors: Jelena Radmanovic

Abstract:

On 5 March 2020, the International Criminal Court has decided to authorize the investigation into the crimes allegedly committed on the territory of Afghanistan after 1 May 2003. The said determination has raised several controversies, including the recently imposed sanctions by the United States, furthering the United States' long-standing rejection of the authority of the International Criminal Court. The purpose of this research is to address the said investigation in light of its importance for the prevention of impunity in the cases where the perpetrators are nationals of Non-Party States to the Rome Statute. Difficulties that the International Criminal Court has been facing, concerning the establishment of its jurisdiction in those instances where an involved state is not a Party to the Rome Statute, have become the most significant stumbling block undermining the importance, integrity, and influence of the Court. The Situation in Afghanistan raises even further concern, bearing in mind that the Prosecutor’s Request for authorization of an investigation pursuant to article 15 from 20 November 2017 has initially been rejected with the ‘interests of justice’ as an applied rationale. The first method used for the present research is the description of the actual events regarding the aforementioned decisions and the following reactions in the international community, while with the second method – the method of conceptual analysis, the research will address the decisions pertaining to the International Criminal Court’s jurisdiction and will attempt to address the mentioned Decision of 5 March 2020 as an example of good practice and a precedent that should be followed in all similar situations. The research will attempt parsing the reasons used by the International Criminal Court, giving rather greater attention to the latter decision that has authorized the investigation and the points raised by the officials of the United States. It is a find of this research that the International Criminal Court, together with other similar judicial instances (Nuremberg and Tokyo Tribunals, The International Criminal Tribunal for the former Yugoslavia, The International Criminal Tribunal for Rwanda), has presented the world with the possibility of non-impunity, attempting to prosecute those responsible for the gravest of crimes known to the humanity and has shown that such persons should not enjoy the benefits of their immunities, with its focus primarily on the victims of such crimes. Whilst it is an issue that will most certainly be addressed further in the future, with the situations that will be brought before the International Criminal Court, the present research will make an attempt at pointing to the significance of the situation in Afghanistan, the International Criminal Court as such and the international criminal justice as a whole, for the purpose of putting an end to impunity.

Keywords: Afghanistan, impunity, international criminal court, sanctions, United States

Procedia PDF Downloads 127

Authors: Burak Oksuzoglu, Savas Yildirim, Ferhat Kutlu

Abstract:

Opinion mining (OM) is one of the natural language processing (NLP) problems to determine the polarity of opinions, mostly represented on a positive-neutral-negative axis. The data for OM is usually collected from various social media platforms. In an era where social media has considerable control over companies’ futures, it’s worth understanding social media and taking actions accordingly. OM comes to the fore here as the scale of the discussion about companies increases, and it becomes unfeasible to gauge opinion on individual levels. Thus, the companies opt to automize this process by applying machine learning (ML) approaches to their data. For the last two decades, OM or sentiment analysis (SA) has been mainly performed by applying ML classification algorithms such as support vector machines (SVM) and Naïve Bayes to a bag of n-gram representations of textual data. With the advent of deep learning and its apparent success in NLP, traditional methods have become obsolete. Transfer learning paradigm that has been commonly used in computer vision (CV) problems started to shape NLP approaches and language models (LM) lately. This gave a sudden rise to the usage of the pretrained language model (PTM), which contains language representations that are obtained by training it on the large datasets using self-supervised learning objectives. The PTMs are further fine-tuned by a specialized downstream task dataset to produce efficient models for various NLP tasks such as OM, NER (Named-Entity Recognition), Question Answering (QA), and so forth. In this study, the traditional and modern NLP approaches have been evaluated for OM by using a sizable corpus belonging to a large private company containing about 76,000 comments in Turkish: SVM with a bag of n-grams, and two chosen pre-trained models, multilingual universal sentence encoder (MUSE) and bidirectional encoder representations from transformers (BERT). The MUSE model is a multilingual model that supports 16 languages, including Turkish, and it is based on convolutional neural networks. The BERT is a monolingual model in our case and transformers-based neural networks. It uses a masked language model and next sentence prediction tasks that allow the bidirectional training of the transformers. During the training phase of the architecture, pre-processing operations such as morphological parsing, stemming, and spelling correction was not used since the experiments showed that their contribution to the model performance was found insignificant even though Turkish is a highly agglutinative and inflective language. The results show that usage of deep learning methods with pre-trained models and fine-tuning achieve about 11% improvement over SVM for OM. The BERT model achieved around 94% prediction accuracy while the MUSE model achieved around 88% and SVM did around 83%. The MUSE multilingual model shows better results than SVM, but it still performs worse than the monolingual BERT model.

Keywords: BERT, MUSE, opinion mining, pretrained language model, SVM, Turkish

Procedia PDF Downloads 146

Authors: Zhao Gao, Eran Edirisinghe

Abstract:

The production of an accurate sketch of a suspect based on a verbal description obtained from a witness is an essential task for most criminal investigations. The criminal investigation system employs specifically trained professional artists to manually draw a facial image of the suspect according to the descriptions of an eyewitness for subsequent identification. Within the advancement of Deep Learning, Recurrent Neural Networks (RNN) have shown great promise in Natural Language Processing (NLP) tasks. Additionally, Generative Adversarial Networks (GAN) have also proven to be very effective in image generation. In this study, a trained GAN conditioned on textual features such as keywords automatically encoded from a verbal description of a human face using an RNN is used to generate photo-realistic facial images for criminal investigations. The intention of the proposed system is to map corresponding features into text generated from verbal descriptions. With this, it becomes possible to generate many reasonably accurate alternatives to which the witness can use to hopefully identify a suspect from. This reduces subjectivity in decision making both by the eyewitness and the artist while giving an opportunity for the witness to evaluate and reconsider decisions. Furthermore, the proposed approach benefits law enforcement agencies by reducing the time taken to physically draw each potential sketch, thus increasing response times and mitigating potentially malicious human intervention. With publically available 'CelebFaces Attributes Dataset' (CelebA) and additionally providing verbal description as training data, the proposed architecture is able to effectively produce facial structures from given text. Word Embeddings are learnt by applying the RNN architecture in order to perform semantic parsing, the output of which is fed into the GAN for synthesizing photo-realistic images. Rather than the grid search method, a metaheuristic search based on genetic algorithms is applied to evolve the network with the intent of achieving optimal hyperparameters in a fraction the time of a typical brute force approach. With the exception of the ‘CelebA’ training database, further novel test cases are supplied to the network for evaluation. Witness reports detailing criminals from Interpol or other law enforcement agencies are sampled on the network. Using the descriptions provided, samples are generated and compared with the ground truth images of a criminal in order to calculate the similarities. Two factors are used for performance evaluation: The Structural Similarity Index (SSIM) and the Peak Signal-to-Noise Ratio (PSNR). A high percentile output from this performance matrix should attribute to demonstrating the accuracy, in hope of proving that the proposed approach can be an effective tool for law enforcement agencies. The proposed approach to criminal facial image generation has potential to increase the ratio of criminal cases that can be ultimately resolved using eyewitness information gathering.

Keywords: RNN, GAN, NLP, facial composition, criminal investigation

Procedia PDF Downloads 160

Authors: Gertraud Koch, Teresa Stumpf, Alejandra Tijerina García

Abstract:

Discourse analysis research approaches belong to the central research strategies applied throughout the humanities; they focus on the countless forms and ways digital texts and images shape present-day notions of the world. Despite the constantly growing number of relevant digital, multimodal discourse resources, digital humanities (DH) methods are thus far not systematically developed and accessible for discourse analysis approaches. Specifically, the significance of multimodality and meaning plurality modelling are yet to be sufficiently addressed. In order to address this research gap, the D-WISE project aims to develop a prototypical working environment as digital support for the sociology of knowledge approach to discourse analysis and new IT-analysis approaches for the use of context-oriented embedding representations. Playing an essential role throughout our research endeavor is the constant optimization of hermeneutical methodology in the use of (semi)automated processes and their corresponding epistemological reflection. Among the discourse analyses, the sociology of knowledge approach to discourse analysis is characterised by the reconstructive and accompanying research into the formation of knowledge systems in social negotiation processes. The approach analyses how dominant understandings of a phenomenon develop, i.e., the way they are expressed and consolidated by various actors in specific arenas of discourse until a specific understanding of the phenomenon and its socially accepted structure are established. This article presents insights and initial findings from D-WISE, a joint research project running since 2021 between the Institute of Anthropological Studies in Culture and History and the Language Technology Group of the Department of Informatics at the University of Hamburg. As an interdisciplinary team, we develop central innovations with regard to the availability of relevant DH applications by building up a uniform working environment, which supports the procedure of the sociology of knowledge approach to discourse analysis within open corpora and heterogeneous, multimodal data sources for researchers in the humanities. We are hereby expanding the existing range of DH methods by developing contextualized embeddings for improved modelling of the plurality of meaning and the integrated processing of multimodal data. The alignment of this methodological and technical innovation is based on the epistemological working methods according to grounded theory as a hermeneutic methodology. In order to systematically relate, compare, and reflect the approaches of structural-IT and hermeneutic-interpretative analysis, the discourse analysis is carried out both manually and digitally. Using the example of current discourses on digitization in the healthcare sector and the associated issues regarding data protection, we have manually built an initial data corpus of which the relevant actors and discourse positions are analysed in conventional qualitative discourse analysis. At the same time, we are building an extensive digital corpus on the same topic based on the use and further development of entity-centered research tools such as topic crawlers and automated newsreaders. In addition to the text material, this consists of multimodal sources such as images, video sequences, and apps. In a blended reading process, the data material is filtered, annotated, and finally coded with the help of NLP tools such as dependency parsing, named entity recognition, co-reference resolution, entity linking, sentiment analysis, and other project-specific tools that are being adapted and developed. The coding process is carried out (semi-)automated by programs that propose coding paradigms based on the calculated entities and their relationships. Simultaneously, these can be specifically trained by manual coding in a closed reading process and specified according to the content issues. Overall, this approach enables purely qualitative, fully automated, and semi-automated analyses to be compared and reflected upon.

Keywords: entanglement of structural IT and hermeneutic-interpretative analysis, multimodality, plurality of meaning, sociology of knowledge approach to discourse analysis

Procedia PDF Downloads 226