Conference Papers
Permanent URI for this collectionhttps://idr.nitk.ac.in/handle/123456789/28506
Browse
5 results
Search Results
Item Improving convergence in Irgan with PPO(Association for Computing Machinery, 2020) Jain, M.; Kamath S․, S.Information retrieval modeling aims to optimise generative and discriminative retrieval strategies, where, generative retrieval focuses on predicting query-specific relevant documents and discriminative retrieval tries to predict relevancy given a query-document pair. IRGAN unifies the generative and discriminative retrieval approaches through a minimax game. However, training IRGAN is unstable and varies largely with the random initialization of parameters. In this work, we propose improvements to IRGAN training through a novel optimization objective based on proximal policy optimisation and gumbel-softmax based sampling for the generator, along with a modified training algorithm which performs the gradient update on both the models simultaneously for each training iteration. We benchmark our proposed approach against IRGAN on three different information retrieval tasks and present empirical evidence of improved convergence. © 2020 Copyright held by the owner/author(s). Publication rights licensed to ACM.Item A Probabilistic Precision Information Retrieval Model for Personalized Clinical Trial Recommendation based on Heterogeneous Data(Institute of Electrical and Electronics Engineers Inc., 2021) Kamath S․, S.; Veena Mayya; Priyadarshini, R.In modern healthcare practices, diagnosis and treatment for certain complex illnesses require specific information on the. patients' background, genealogy, heredity, demographic data etc. Even with a similar diagnosis, treatments may need to designed specifically to adapt well to the patients' genetic, cultural, and lifestyle aspects. Precision medicine mainly deals with enabling personalized care based on a given patient's conditions in a scientifically rigorous way. Because this entails recommending personalized therapies to patients and has the potential to affect the health of other people, the performance of a designed system must be accurate and exact. In this paper, a precision information retrieval system is proposed that leverages structured and unstructured data to retrieve. relevant knowledge for enabling personalized recommendations, The. proposed pipeline is validated with the cllnlcal trial dataset of the Precision medicine track of TREe 2017. A set of relevant ranked clinical trials for a given condition/disease that could not be cured using any of the traditional treatments suggested are retrieved using structured and unstructured patient data. 'We employ multiple IR techniques like Best Match 25, query reformulation and rearanking facilitated through deep neural networks, focusing on extracting highly accurate and relevant trials. The proposed pipeline achieved a high score of 0.58 in terms of Normalized Discounted Cumulative Gain (NDCG) score for ranking the relevant clinical trials, outperforming the state-of-the-art approaches. © 2021 IEEE.Item Sketch-Based Image Retrieval Using Convolutional Neural Networks Based on Feature Adaptation and Relevance Feedback(Springer Science and Business Media Deutschland GmbH, 2022) Kumar, N.; Ahmed, R.; B Honnakasturi, V.; Kamath S․, S.; Mayya, V.Sketch-based Image Retrieval (SBIR) is an approach where natural images are retrieved according to the given input sketch query. SBIR has many applications, for example, searching for a product given the sketch pattern in digital catalogs, searching for missing people given their prominent features from a digital people photo repository etc. The main challenge involved in implementing such a system is the absence of semantic information in the sketch query. In this work, we propose a combination of image prepossessing and deep learning-based methods to tackle this issue. A binary image highlighting the edges in the natural image is obtained using Canny-Edge detection algorithm. The deep features were extracted by an ImageNet based CNN model. Cosine similarity and Euclidean distance measures are adopted to generate the rank list of candidate natural images. Relevance feedback using Rocchio’s method is used to adapt the query of sketch images and feature weights according to relevant images and non-relevant images. During the experimental evaluation, the proposed approach achieved a Mean average precision (MAP) of 71.84%, promising performance in retrieving relevant images for the input query sketch images. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.Item Effective Information Retrieval, Question Answering and Abstractive Summarization on Large-Scale Biomedical Document Corpora(Springer Science and Business Media Deutschland GmbH, 2023) Shenoy, N.; Nayak, P.; Jain, S.; Kamath S․, S.; Sugumaran, V.During the COVID-19 pandemic, a concentrated effort was made to collate published literature on SARS-Cov-2 and other coronaviruses for the benefit of the medical community. One such initiative is the COVID-19 Open Research Dataset which contains over 400,000 published research articles. To expedite access to relevant information sources for health workers and researchers, it is vital to design effective information retrieval and information extraction systems. In this article, an IR approach leveraging transformer-based models to enable question-answering and abstractive summarization is presented. Various keyword-based and neural-network-based models are experimented with and incorporated to reduce the search space and determine relevant sentences from the vast corpus for ranked retrieval. For abstractive summarization, candidate sentences are determined using a combination of various standard scoring metrics. Finally, the summary and the user query are utilized for supporting question answering. The proposed model is evaluated based on standard metrics on the standard CovidQA dataset for both natural language and keyword queries. The proposed approach achieved promising performance for both query classes, while outperforming various unsupervised baselines. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.Item Transformer and Knowledge Based Siamese Models for Medical Document Retrieval(Institute of Electrical and Electronics Engineers Inc., 2023) Dash, A.; Merchant, A.M.; Chintawar, S.; Kamath S․, S.Vocabulary mismatch is a significant issue when it comes to query-based document retrieval in the medical field. Since the documents are typically authored by professionals, they may contain many specialized terms that are not widely understood or used. Traditional information retrieval (IR) models like vector space and best match-based models fail in this regard. Neural Learning to Rank (NLtR) and transformer models have attracted significant research attention in the field of IR. Recent works in the medical field utilize medical knowledge bases (KB) that map words to concepts and aid in connecting several words to the same concept. In this paper, we present various Siamese-structured transformer and knowledge-based retrieval models designed to address the retrieval issues in the medical domain. The experimental evaluation highlighted the superior performance of the proposed retrieval model, and the best one, based on the UMLSBert ENG transformer, achieved best-in-class performance with respect to all evaluation metrics. © 2023 IEEE.