Papers by Rajarshi Bhowmik

4 papers
Learning Rich Representation of Keyphrases from Text (2022.findings-naacl)

Copied to clipboard

Challenge: Prior work has referred to extractive (part of document) or abstractive (not part of document).
Approach: They propose to use a new pre-training objective to introduce keyphrases into transformer language models in discriminative and generative settings.
Outcome: The proposed model improves performance in discriminative and generative settings and also improves on named entity recognition, question answering, relation extraction and abstractive summarization tasks.
Generating Fine-Grained Open Vocabulary Entity Type Descriptions (P18-1)

Copied to clipboard

Challenge: Fig. 1 shows an example of a concise entity description presented to a user.
Approach: They propose a dynamic memory-based network that generates a short open vocabulary description of an entity by leveraging induced fact embeddings and dynamic context.
Outcome: The proposed network generates a short open vocabulary description of an entity . it can discern relevant information for more accurate generation of type description .
Unsupervised Contrast-Consistent Ranking with Language Models (2024.eacl-long)

Copied to clipboard

Challenge: Language models contain ranking-based knowledge and are powerful solvers of in-context ranking tasks.
Approach: They propose to use a model to elicit language models' ranking knowledge without supervision by using a pairwise, pointwise and listwise prompting method.
Outcome: The proposed method is inspired by an unsupervised probing method called Contrast-Consistent Search (CCS).
Leveraging Contextual Information for Effective Entity Salience Detection (2024.findings-naacl)

Copied to clipboard

Challenge: Prior work on salient entity detection focused on machine learning models that require heavy feature engineering.
Approach: They propose to fine-tune medium-sized language models with a cross-encoder style architecture to achieve significant performance gains over feature engineering approaches.
Outcome: The proposed model fine-tunes medium-sized pre-trained language models with a cross-encoder style architecture yields substantial performance gains over feature engineering approaches.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations