Search results for: Rosy Chaudhary

Authors: Shraddha Chaudhary, Raksha Agarwal, Niladri Chatterjee

Abstract:

This work demonstrates a web crawler-based generalized end-to-end open domain Question Answering (QA) system. An efficient QA system requires a significant amount of domain knowledge to answer any question with the aim to find an exact and correct answer in the form of a number, a noun, a short phrase, or a brief piece of text for the user's questions. Analysis of the question, searching the relevant document, and choosing an answer are three important steps in a QA system. This work uses a web scraper (Beautiful Soup) to extract K-documents from the web. The value of K can be calibrated on the basis of a trade-off between time and accuracy. This is followed by a passage ranking process using the MS-Marco dataset trained on 500K queries to extract the most relevant text passage, to shorten the lengthy documents. Further, a QA system is used to extract the answers from the shortened documents based on the query and return the top 3 answers. For evaluation of such systems, accuracy is judged by the exact match between predicted answers and gold answers. But automatic evaluation methods fail due to the linguistic ambiguities inherent in the questions. Moreover, reference answers are often not exhaustive or are out of date. Hence correct answers predicted by the system are often judged incorrect according to the automated metrics. One such scenario arises from the original Google Natural Question (GNQ) dataset which was collected and made available in the year 2016. Use of any such dataset proves to be inefficient with respect to any questions that have time-varying answers. For illustration, if the query is where will be the next Olympics? Gold Answer for the above query as given in the GNQ dataset is “Tokyo”. Since the dataset was collected in the year 2016, and the next Olympics after 2016 were in 2020 that was in Tokyo which is absolutely correct. But if the same question is asked in 2022 then the answer is “Paris, 2024”. Consequently, any evaluation based on the GNQ dataset will be incorrect. Such erroneous predictions are usually given to human evaluators for further validation which is quite expensive and time-consuming. To address this erroneous evaluation, the present work proposes an automated approach for evaluating time-dependent question-answer pairs. In particular, it proposes a metric using the current timestamp along with top-n predicted answers from a given QA system. To test the proposed approach GNQ dataset has been used and the system achieved an accuracy of 78% for a test dataset comprising 100 QA pairs. This test data was automatically extracted using an analysis-based approach from 10K QA pairs of the GNQ dataset. The results obtained are encouraging. The proposed technique appears to have the possibility of developing into a useful scheme for gathering precise, reliable, and specific information in a real-time and efficient manner. Our subsequent experiments will be guided towards establishing the efficacy of the above system for a larger set of time-dependent QA pairs.

Keywords: web-based information retrieval, open domain question answering system, time-varying QA, QA evaluation

Procedia PDF Downloads 101

Authors: Suman Chaudhary, Rupinder K. Kanwar, Jagat R. Kanwar

Abstract:

Azadirachta indica, also known as Neem belonging to the mahogany family is actively gaining interest in the era of modern day medicine due to its extensive applications in homeopathic medicine such as Ayurveda and Unani. More than 140 phytochemicals have been extracted from neem leaves, seed, bark and flowers for agro-medicinal applications. Among the various components, neem leaf protein (NLP) is currently the most investigated active ingredient, due to its immunomodulatory activities against tumor growth. However, these therapeutic ingredients of neem are susceptible to degradation and cannot withstand the drastic pH changes under physiological environment, and therefore, there is an urgent need of an alternative strategy such as a nano-delivery system to exploit its medicinal benefits. This study hypothesizes that guar gum (GG) derived biodegradable nano-carrier based encapsulation of NLP will improve its stability, specificity and sensitivity, thus facilitating targeted anti-cancer therapeutics. GG is a galactomannan derived from the endosperm of the guar beans seeds. Synthesis of guar nanocapsules (NCs) was performed using nanoprecipitation technique where the GG was encapsulated with NLP. Preliminary experiments conducted to characterize the NCs confirmed spherical morphology with a narrow size distribution of 30-40 nm. Differential scanning colorimetric analysis (DSC) validated the stability of these NCs even at a temperature range of 50-60°C which was well within the physiological and storage conditions. Thermogravimetric (TGA) analysis indicated high decomposition temperature of these NCs ranging upto 350°C. Additionally, Fourier Transform Infrared spectroscopy (FTIR) and the SDS-PAGE data acquired confirmed the successful encapsulation of NLP in the NCs. The anti-cancerous therapeutic property of this NC was tested on colon cancer cells (caco-2) as they are one of the most prevalent form of cancer. These NCs (both NLP loaded and void) were also tested on human intestinal epithelial cells (FHs 74) cells to evaluate their effect on normal cells. Cytotoxicity evaluation of the NCs in the cell lines confirmed that the IC50 for NLP in FHs 74 cells was ~2 fold higher than in caco-2 cells, indicating that this nanoformulation system possessed biocompatible anti-cancerous properties Immunoconfocal microscopy analysis confirmed the time dependent internalization of the NCs within 6h. Recent findings performed using Annexin V and PI staining indicated a significant increase (p ≤ 0.001) in the early and late apoptotic cell population when treated with the NCs signifying the role of NLP in inducing apoptosis in caco-2 cells. This was further validated using Western blot, Polymerase chain reaction (PCR) and Fluorescence activated cell sorter (FACS) aided protein expressional analysis which presented a downregulation of survivin, an anti-apoptotic cell marker and upregulation of Bax/Bcl-2 ratio (pro-apoptotic indicator). Further, both the NLP NC and unencapsulated NLP treatment destabilized the mitochondrial membrane potential subsequently facilitating the release of the pro-apoptotic caspase cascade initiator, cytochrome-c. Future studies will be focused towards granting specificity to these NCs towards cancer cells, along with a comprehensive analysis of the anti-cancer potential of this naturally occurring compound in different cancer and in vivo animal models, will validate the clinical application of this unprecedented protein therapeutic.

Keywords: anti-tumor, guar gum, nanocapsules, neem leaf protein

Procedia PDF Downloads 177