Karan Saxena


2019

pdf
Zero-shot Word Sense Disambiguation using Sense Definition Embeddings
Sawan Kumar | Sharmistha Jat | Karan Saxena | Partha Talukdar
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

Word Sense Disambiguation (WSD) is a long-standing but open problem in Natural Language Processing (NLP). WSD corpora are typically small in size, owing to an expensive annotation process. Current supervised WSD methods treat senses as discrete labels and also resort to predicting the Most-Frequent-Sense (MFS) for words unseen during training. This leads to poor performance on rare and unseen senses. To overcome this challenge, we propose Extended WSD Incorporating Sense Embeddings (EWISE), a supervised model to perform WSD by predicting over a continuous sense embedding space as opposed to a discrete label space. This allows EWISE to generalize over both seen and unseen senses, thus achieving generalized zero-shot learning. To obtain target sense embeddings, EWISE utilizes sense definitions. EWISE learns a novel sentence encoder for sense definitions by using WordNet relations and also ConvE, a recently proposed knowledge graph embedding method. We also compare EWISE against other sentence encoders pretrained on large corpora to generate definition embeddings. EWISE achieves new state-of-the-art WSD performance.

pdf
Pentagon at MEDIQA 2019: Multi-task Learning for Filtering and Re-ranking Answers using Language Inference and Question Entailment
Hemant Pugaliya | Karan Saxena | Shefali Garg | Sheetal Shalini | Prashant Gupta | Eric Nyberg | Teruko Mitamura
Proceedings of the 18th BioNLP Workshop and Shared Task

Parallel deep learning architectures like fine-tuned BERT and MT-DNN, have quickly become the state of the art, bypassing previous deep and shallow learning methods by a large margin. More recently, pre-trained models from large related datasets have been able to perform well on many downstream tasks by just fine-tuning on domain-specific datasets (similar to transfer learning). However, using powerful models on non-trivial tasks, such as ranking and large document classification, still remains a challenge due to input size limitations of parallel architecture and extremely small datasets (insufficient for fine-tuning). In this work, we introduce an end-to-end system, trained in a multi-task setting, to filter and re-rank answers in the medical domain. We use task-specific pre-trained models as deep feature extractors. Our model achieves the highest Spearman’s Rho and Mean Reciprocal Rank of 0.338 and 0.9622 respectively, on the ACL-BioNLP workshop MediQA Question Answering shared-task.

2018

pdf
The RGNLP Machine Translation Systems for WAT 2018
Atul Kr. Ojha | Koel Dutta Chowdhury | Chao-Hong Liu | Karan Saxena
Proceedings of the 32nd Pacific Asia Conference on Language, Information and Computation: 5th Workshop on Asian Translation: 5th Workshop on Asian Translation