Search Results for author: Dhruvesh Patel

Found 8 papers, 2 papers with code

Word2Box: Learning Word Representation Using Box Embeddings

no code implementations28 Jun 2021 Shib Sankar Dasgupta, Michael Boratko, Shriya Atmakuri, Xiang Lorraine Li, Dhruvesh Patel, Andrew McCallum

Learning vector representations for words is one of the most fundamental topics in NLP, capable of capturing syntactic and semantic relationships useful in a variety of downstream NLP tasks.

Representation Learning Word Similarity

Looking Beyond Sentence-Level Natural Language Inference for Question Answering and Text Summarization

no code implementations NAACL 2021 Anshuman Mishra, Dhruvesh Patel, Aparna Vijayakumar, Xiang Lorraine Li, Pavan Kapanipathi, Kartik Talamadupula

Natural Language Inference (NLI) has garnered significant attention in recent years; however, the promise of applying NLI breakthroughs to other downstream NLP tasks has remained unfulfilled.

Natural Language Inference Question Answering +2

Weakly Supervised Medication Regimen Extraction from Medical Conversations

no code implementations EMNLP (ClinicalNLP) 2020 Dhruvesh Patel, Sandeep Konam, Sai P. Selvaraj

Automated Medication Regimen (MR) extraction from medical conversations can not only improve recall and help patients follow through with their care plan, but also reduce the documentation burden for doctors.

General Classification

Reading Comprehension as Natural Language Inference: A Semantic Analysis

no code implementations4 Oct 2020 Anshuman Mishra, Dhruvesh Patel, Aparna Vijayakumar, Xiang Li, Pavan Kapanipathi, Kartik Talamadupula

We transform the one of the largest available MRC dataset (RACE) to an NLI form, and compare the performances of a state-of-the-art model (RoBERTa) on both these forms.

Natural Language Inference Question Answering +1

Looking Beyond Sentence-Level Natural Language Inference for Downstream Tasks

no code implementations18 Sep 2020 Anshuman Mishra, Dhruvesh Patel, Aparna Vijayakumar, Xiang Li, Pavan Kapanipathi, Kartik Talamadupula

In recent years, the Natural Language Inference (NLI) task has garnered significant attention, with new datasets and models achieving near human-level performance on it.

Natural Language Inference Question Answering +1

Representing Joint Hierarchies with Box Embeddings

1 code implementation AKBC 2020 Dhruvesh Patel, Shib Sankar Dasgupta, Michael Boratko, Xiang Li, Luke Vilnis, Andrew McCallum

Box Embeddings [Vilnis et al., 2018, Li et al., 2019] represent concepts with hyperrectangles in $n$-dimensional space and are shown to be capable of modeling tree-like structures efficiently by training on a large subset of the transitive closure of the WordNet hypernym graph.

Cannot find the paper you are looking for? You can Submit a new open access paper.