Hrituraj Singh
YOU?
Author Swipe
View article: PRISM: Patient Records Interpretation for Semantic clinical trial Matching system using large language models
PRISM: Patient Records Interpretation for Semantic clinical trial Matching system using large language models Open
View article: PRISM: Patient Records Interpretation for Semantic Clinical Trial Matching using Large Language Models
PRISM: Patient Records Interpretation for Semantic Clinical Trial Matching using Large Language Models Open
Clinical trial matching is the task of identifying trials for which patients may be potentially eligible. Typically, this task is labor-intensive and requires detailed verification of patient electronic health records (EHRs) against the st…
View article: Distilling large language models for matching patients to clinical trials
Distilling large language models for matching patients to clinical trials Open
Objective The objective of this study is to systematically examine the efficacy of both proprietary (GPT-3.5, GPT-4) and open-source large language models (LLMs) (LLAMA 7B, 13B, 70B) in the context of matching patients to clinical trials i…
View article: Onco-Retriever: Generative Classifier for Retrieval of EHR Records in Oncology
Onco-Retriever: Generative Classifier for Retrieval of EHR Records in Oncology Open
Retrieving information from EHR systems is essential for answering specific questions about patient journeys and improving the delivery of clinical care. Despite this fact, most EHR systems still rely on keyword-based searches. With the ad…
View article: Distilling Large Language Models for Matching Patients to Clinical Trials
Distilling Large Language Models for Matching Patients to Clinical Trials Open
The recent success of large language models (LLMs) has paved the way for their adoption in the high-stakes domain of healthcare. Specifically, the application of LLMs in patient-trial matching, which involves assessing patient eligibility …
View article: SemIE: Semantically-aware Image Extrapolation
SemIE: Semantically-aware Image Extrapolation Open
We propose a semantically-aware novel paradigm to perform image extrapolation that enables the addition of new object instances. All previous methods are limited in their capability of extrapolation to merely extending the already existing…
View article: DRAG: Director-Generator Language Modelling Framework for Non-Parallel\n Author Stylized Rewriting
DRAG: Director-Generator Language Modelling Framework for Non-Parallel\n Author Stylized Rewriting Open
Author stylized rewriting is the task of rewriting an input text in a\nparticular author's style. Recent works in this area have leveraged\nTransformer-based language models in a denoising autoencoder setup to generate\nauthor stylized tex…
View article: MIMOQA: Multimodal Input Multimodal Output Question Answering
MIMOQA: Multimodal Input Multimodal Output Question Answering Open
Hrituraj Singh, Anshul Nasery, Denil Mehta, Aishwarya Agarwal, Jatin Lamba, Balaji Vasan Srinivasan. Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technolo…
View article: DRAG: Director-Generator Language Modelling Framework for Non-Parallel Author Stylized Rewriting
DRAG: Director-Generator Language Modelling Framework for Non-Parallel Author Stylized Rewriting Open
Author stylized rewriting is the task of rewriting an input text in a particular author's style. Recent works in this area have leveraged Transformer-based language models in a denoising autoencoder setup to generate author stylized text w…
View article: Exploring Neural Models for Parsing Natural Language into First-Order Logic
Exploring Neural Models for Parsing Natural Language into First-Order Logic Open
Semantic parsing is the task of obtaining machine-interpretable representations from natural language text. We consider one such formal representation - First-Order Logic (FOL) and explore the capability of neural models in parsing English…
View article: STL-CQA: Structure-based Transformers with Localization and Encoding for Chart Question Answering
STL-CQA: Structure-based Transformers with Localization and Encoding for Chart Question Answering Open
Chart Question Answering (CQA) is the task of answering natural language questions about visualisations in the chart image. Recent solutions, inspired by VQA approaches, rely on image-based attention for question/answering while ignoring t…
View article: Incorporating Stylistic Lexical Preferences in Generative Language Models
Incorporating Stylistic Lexical Preferences in Generative Language Models Open
While recent advances in language modeling have resulted in powerful generation models, their generation style remains implicitly dependent on the training data and can not emulate a specific target style. Leveraging the generative capabil…
View article: Generating summaries tailored to target characteristics
Generating summaries tailored to target characteristics Open
Recently, research efforts have gained pace to cater to varied user preferences while generating text summaries. While there have been attempts to incorporate a few handpicked characteristics such as length or entities, a holistic view aro…