Search Results for author: Rajarshi Bhowmik

Found 6 papers, 5 papers with code

Learning Rich Representation of Keyphrases from Text

1 code implementation Findings (NAACL) 2022 Mayank Kulkarni, Debanjan Mahata, Ravneet Arora, Rajarshi Bhowmik

In the discriminative setting, we introduce a new pre-training objective - Keyphrase Boundary Infilling with Replacement (KBIR), showing large gains in performance (upto 8. 16 points in F1) over SOTA, when the LM pre-trained using KBIR is fine-tuned for the task of keyphrase extraction.

Abstractive Text Summarization Keyphrase Extraction +5

Fast and Effective Biomedical Entity Linking Using a Dual Encoder

1 code implementation EACL (Louhi) 2021 Rajarshi Bhowmik, Karl Stratos, Gerard de Melo

Additionally, we modify our dual encoder model for end-to-end biomedical entity linking that performs both mention span detection and entity disambiguation and out-performs two recently proposed models.

Entity Disambiguation Entity Linking

Explainable Link Prediction for Emerging Entities in Knowledge Graphs

1 code implementation1 May 2020 Rajarshi Bhowmik, Gerard de Melo

Despite their large-scale coverage, cross-domain knowledge graphs invariably suffer from inherent incompleteness and sparsity.

Knowledge Graphs Link Prediction +1

Be Concise and Precise: Synthesizing Open-Domain Entity Descriptions from Facts

1 code implementation16 Apr 2019 Rajarshi Bhowmik, Gerard de Melo

Despite being vast repositories of factual information, cross-domain knowledge graphs, such as Wikidata and the Google Knowledge Graph, only sparsely provide short synoptic descriptions for entities.

Entity Disambiguation Knowledge Graphs

Generating Fine-Grained Open Vocabulary Entity Type Descriptions

1 code implementation ACL 2018 Rajarshi Bhowmik, Gerard de Melo

While large-scale knowledge graphs provide vast amounts of structured facts about entities, a short textual description can often be useful to succinctly characterize an entity and its type.

Knowledge Graphs

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