Papers by Oshin Agarwal
Temporal Effects on Pre-trained Models for Language Processing Tasks (2022.tacl-1)
Copied to clipboard
| Challenge: | a recent study shows that language models can be improved as time passes . a number of approaches to solving language tasks have evolved rapidly without a model . |
| Approach: | They examine temporal effects on model performance on downstream language tasks . they also examine the efficacy of two approaches for temporal domain adaptation without human annotations . |
| Outcome: | The proposed methods improve self-labeling and named entity recognition on new data. |
From Toxicity in Online Comments to Incivility in American News: Proceed with Caution (2021.eacl-main)
Copied to clipboard
| Challenge: | Existing tools for quantifying incivility online, in news and in congressional debates are inadequate for the analysis of incivility in news. |
| Approach: | They develop a Jigsaw Perspective API to quantify incivility in news . they show that toxicity models are inadequate for the analysis of incivility in news. |
| Outcome: | The Jigsaw Perspective API detects incivility on a corpus of American news articles. |
Predicting Annotation Difficulty to Improve Task Routing and Model Performance for Biomedical Information Extraction (N19-1)
Copied to clipboard
| Challenge: | Modern NLP systems require high-quality annotations, but experts are expensive and lay annotators may not have the knowledge to provide high- quality annotations. |
| Approach: | They propose to directly model instance difficulty to improve model performance and to route instances to appropriate annotators. |
| Outcome: | The proposed model improves performance on a biomedical information extraction task using expert and lay annotations. |
The Utility and Interplay of Gazetteers and Entity Segmentation for Named Entity Recognition in English (2021.findings-acl)
Copied to clipboard
| Challenge: | Recent papers introduce methods to incorporate gazetteer features and entity segmentation techniques in neural named entity recognition models. |
| Approach: | They propose to integrate gazetteer features and entity segmentation techniques into neural named entity recognition models. |
| Outcome: | The proposed methods improve entity segmentation and not just entity typing. |
Knowledge Graph Based Synthetic Corpus Generation for Knowledge-Enhanced Language Model Pre-training (2021.naacl-main)
Copied to clipboard
| Challenge: | Existing work on data-to-text generation focused on domain-specific benchmark datasets. |
| Approach: | They use a KG-Wikipedia text aligned corpus to verbalize the entire English Wikidata KG . they show that this approach can be used to integrate structured KGs and natural language corpora . |
| Outcome: | The proposed method improves on open domain QA and the LAMA knowledge probe. |
Named Entity Recognition in a Very Homogenous Domain (2023.findings-eacl)
Copied to clipboard
| Challenge: | Developing models that perform well on several domains is important, but domain is vague and can be adapted to a new domain. |
| Approach: | They find that even news articles from the same newspaper in English can be considered different domains. |
| Outcome: | The proposed model performs better on out-of-domain data than on specialized data. |