Search Results for author: Oshin Agarwal

Found 14 papers, 4 papers with code

Summarization from Leaderboards to Practice: Choosing A Representation Backbone and Ensuring Robustness

no code implementations18 Jun 2023 David Demeter, Oshin Agarwal, Simon Ben Igeri, Marko Sterbentz, Neil Molino, John M. Conroy, Ani Nenkova

Academic literature does not give much guidance on how to build the best possible customer-facing summarization system from existing research components.

Temporal Effects on Pre-trained Models for Language Processing Tasks

1 code implementation24 Nov 2021 Oshin Agarwal, Ani Nenkova

Keeping the performance of language technologies optimal as time passes is of great practical interest.

Domain Adaptation Experimental Design +3

From Toxicity in Online Comments to Incivility in American News: Proceed with Caution

no code implementations EACL 2021 Anushree Hede, Oshin Agarwal, Linda Lu, Diana C. Mutz, Ani Nenkova

The ability to quantify incivility online, in news and in congressional debates, is of great interest to political scientists.

Knowledge Graph Based Synthetic Corpus Generation for Knowledge-Enhanced Language Model Pre-training

1 code implementation NAACL 2021 Oshin Agarwal, Heming Ge, Siamak Shakeri, Rami Al-Rfou

Prior work on Data-To-Text Generation, the task of converting knowledge graph (KG) triples into natural text, focused on domain-specific benchmark datasets.

Data-to-Text Generation Language Modelling +1

Interpretability Analysis for Named Entity Recognition to Understand System Predictions and How They Can Improve

no code implementations CL (ACL) 2021 Oshin Agarwal, Yinfei Yang, Byron C. Wallace, Ani Nenkova

We examine these questions by contrasting the performance of several variants of LSTM-CRF architectures for named entity recognition, with some provided only representations of the context as features.

named-entity-recognition Named Entity Recognition +1

Entity-Switched Datasets: An Approach to Auditing the In-Domain Robustness of Named Entity Recognition Models

1 code implementation8 Apr 2020 Oshin Agarwal, Yinfei Yang, Byron C. Wallace, Ani Nenkova

We propose a method for auditing the in-domain robustness of systems, focusing specifically on differences in performance due to the national origin of entities.

Fairness named-entity-recognition +2

Entity Linking via Dual and Cross-Attention Encoders

no code implementations7 Apr 2020 Oshin Agarwal, Daniel M. Bikel

Recently, a solution has been proposed for the former as a dual-encoder entity retrieval system (Gillick et al., 2019) that learns mention and entity representations in the same space, and performs linking by selecting the nearest entity to the mention in this space.

Entity Linking Entity Retrieval +1

Browsing Health: Information Extraction to Support New Interfaces for Accessing Medical Evidence

no code implementations WS 2019 Soham Parikh, Elizabeth Conrad, Oshin Agarwal, Iain Marshall, Byron Wallace, Ani Nenkova

Typical information needs, such as retrieving a full list of medical interventions for a given condition, or finding the reported efficacy of a particular treatment with respect to a specific outcome of interest cannot be straightforwardly posed in typical text-box search.

Evaluation of named entity coreference

no code implementations WS 2019 Oshin Agarwal, Sanjay Subramanian, Ani Nenkova, Dan Roth

It is therefore important that coreference resolution systems are able to link these different types of mentions to the correct entity name.

coreference-resolution

Predicting Annotation Difficulty to Improve Task Routing and Model Performance for Biomedical Information Extraction

no code implementations NAACL 2019 Yinfei Yang, Oshin Agarwal, Chris Tar, Byron C. Wallace, Ani Nenkova

Experiments on a complex biomedical information extraction task using expert and lay annotators show that: (i) simply excluding from the training data instances predicted to be difficult yields a small boost in performance; (ii) using difficulty scores to weight instances during training provides further, consistent gains; (iii) assigning instances predicted to be difficult to domain experts is an effective strategy for task routing.

Named Person Coreference in English News

no code implementations26 Oct 2018 Oshin Agarwal, Sanjay Subramanian, Ani Nenkova, Dan Roth

Here, we evaluate two state of the art coreference resolution systems on the subtask of Named Person Coreference, in which we are interested in identifying a person mentioned by name, along with all other mentions of the person, by pronoun or generic noun phrase.

coreference-resolution named-entity-recognition +2

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