Papers by Sawan Kumar
NILE : Natural Language Inference with Faithful Natural Language Explanations (2020.acl-main)
Copied to clipboard
| Challenge: | Recent growth in popularity of deep learning models on NLP classification tasks has accompanied the need for generating some form of natural language explanation of predicted labels. |
| Approach: | They propose a novel method which generates labels along with its faithful explanations. |
| Outcome: | The proposed method is more accurate than previously reported methods and has higher sensitivity than previous methods. |
Answer-level Calibration for Free-form Multiple Choice Question Answering (2022.acl-long)
Copied to clipboard
| Challenge: | Pre-trained language models exhibit few-shot and zero-shot learning capability on tasks such as commonsense reasoning. |
| Approach: | They propose to model context-independent biases in terms of the probability of a choice without the context and to remove it using an unsupervised estimate of similarity with the full context. |
| Outcome: | The proposed model improves over baselines on commonsense reasoning tasks. |
Improving Answer Selection and Answer Triggering using Hard Negatives (D19-1)
Copied to clipboard
| Challenge: | Existing approaches to answer selection and answer triggering have been proposed. |
| Approach: | They propose to use hard negatives with a siamese network and a suitable loss function for answer selection and answer triggering. |
| Outcome: | The proposed model improves on InsuranceQA, SelQA, and an internal QA dataset by 2.3 points over previous baselines. |
Zero-shot Word Sense Disambiguation using Sense Definition Embeddings (P19-1)
Copied to clipboard
| Challenge: | Word Sense Disambiguation (WSD) is an open problem in Natural Language Processing . current methods treat senses as discrete labels and predict the most-frequent-Sense for unseen senses . |
| Approach: | They propose a supervised model to perform Word Sense Disambiguation (WSD) by predicting over a continuous sense embedding space rather than a discrete label space. |
| Outcome: | The proposed model generalizes over seen and unseen senses, achieving zero-shot learning. |
Structured Dialogue Refinement: Building Retrieval-Augmented Question Answering on Goal-Oriented Dialogues (2026.findings-acl)
Copied to clipboard
| Challenge: | Retrieval-Augmented Generation (RAG) is widely used for knowledgeintensive question answering (QA), but a large amount of real-world problem-solving knowledge is captured in goal-oriented dialogues. |
| Approach: | They propose a framework that adapts dialogue corpora for RAG at both retrieval and generation stages without altering the underlying pipeline. |
| Outcome: | The proposed framework improves retrieval quality and QA performance under dialogue-specific structural challenges. |
Reordering Examples Helps during Priming-based Few-Shot Learning (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for learning from limited data are not efficient . we show that presenting examples in the right order is key for generalization . |
| Approach: | They propose a method to learn from limited data using examples as prompts . they propose PERO, which uses examples as search over set of permutations . |
| Outcome: | The proposed method can generalize using as few as 10 examples, the authors show . it can be used on sentiment classification, natural language inference and fact retrieval tasks . |