Get our free extension to see links to code for papers anywhere online!

Add to Chrome

Add to Firefox

Picture for Arman Cohan

Arman Cohan

Embedding Recycling for Language Models

Jul 11, 2022
Jon Saad-Falcon, Amanpreet Singh, Luca Soldaini, Mike D'Arcy, Arman Cohan, Doug Downey

Figure 1 for Embedding Recycling for Language Models

Figure 2 for Embedding Recycling for Language Models

Figure 3 for Embedding Recycling for Language Models

Figure 4 for Embedding Recycling for Language Models

* Preprint

Access Paper or Ask Questions

Generating Scientific Claims for Zero-Shot Scientific Fact Checking

Mar 24, 2022
Dustin Wright, David Wadden, Kyle Lo, Bailey Kuehl, Arman Cohan, Isabelle Augenstein, Lucy Lu Wang

Figure 1 for Generating Scientific Claims for Zero-Shot Scientific Fact Checking

Figure 2 for Generating Scientific Claims for Zero-Shot Scientific Fact Checking

Figure 3 for Generating Scientific Claims for Zero-Shot Scientific Fact Checking

Figure 4 for Generating Scientific Claims for Zero-Shot Scientific Fact Checking

* Accepted to ACL 2022; 13 pages, 3 figures, 8 tables

Access Paper or Ask Questions

Utilizing Evidence Spans via Sequence-Level Contrastive Learning for Long-Context Question Answering

Dec 16, 2021
Avi Caciularu, Ido Dagan, Jacob Goldberger, Arman Cohan

Figure 1 for Utilizing Evidence Spans via Sequence-Level Contrastive Learning for Long-Context Question Answering

Figure 2 for Utilizing Evidence Spans via Sequence-Level Contrastive Learning for Long-Context Question Answering

Figure 3 for Utilizing Evidence Spans via Sequence-Level Contrastive Learning for Long-Context Question Answering

Figure 4 for Utilizing Evidence Spans via Sequence-Level Contrastive Learning for Long-Context Question Answering

Access Paper or Ask Questions

LongChecker: Improving scientific claim verification by modeling full-abstract context

Dec 02, 2021
David Wadden, Kyle Lo, Lucy Lu Wang, Arman Cohan, Iz Beltagy, Hannaneh Hajishirzi

Figure 1 for LongChecker: Improving scientific claim verification by modeling full-abstract context

Figure 2 for LongChecker: Improving scientific claim verification by modeling full-abstract context

Figure 3 for LongChecker: Improving scientific claim verification by modeling full-abstract context

Figure 4 for LongChecker: Improving scientific claim verification by modeling full-abstract context

* Preprint - work in progress. 9 pages

Access Paper or Ask Questions

Multi-Vector Models with Textual Guidance for Fine-Grained Scientific Document Similarity

Nov 16, 2021
Sheshera Mysore, Arman Cohan, Tom Hope

Figure 1 for Multi-Vector Models with Textual Guidance for Fine-Grained Scientific Document Similarity

Figure 2 for Multi-Vector Models with Textual Guidance for Fine-Grained Scientific Document Similarity

Figure 3 for Multi-Vector Models with Textual Guidance for Fine-Grained Scientific Document Similarity

Figure 4 for Multi-Vector Models with Textual Guidance for Fine-Grained Scientific Document Similarity

* Work in progress

Access Paper or Ask Questions

PRIMER: Pyramid-based Masked Sentence Pre-training for Multi-document Summarization

Oct 16, 2021
Wen Xiao, Iz Beltagy, Giuseppe Carenini, Arman Cohan

Figure 1 for PRIMER: Pyramid-based Masked Sentence Pre-training for Multi-document Summarization

Figure 2 for PRIMER: Pyramid-based Masked Sentence Pre-training for Multi-document Summarization

Figure 3 for PRIMER: Pyramid-based Masked Sentence Pre-training for Multi-document Summarization

Figure 4 for PRIMER: Pyramid-based Masked Sentence Pre-training for Multi-document Summarization

Access Paper or Ask Questions

FLEX: Unifying Evaluation for Few-Shot NLP

Jul 15, 2021
Jonathan Bragg, Arman Cohan, Kyle Lo, Iz Beltagy

Figure 1 for FLEX: Unifying Evaluation for Few-Shot NLP

Figure 2 for FLEX: Unifying Evaluation for Few-Shot NLP

Figure 3 for FLEX: Unifying Evaluation for Few-Shot NLP

Figure 4 for FLEX: Unifying Evaluation for Few-Shot NLP

* First two authors contributed equally. Code and leaderboard available at: https://github.com/allenai/flex

Access Paper or Ask Questions