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

Chrome logo Add to Chrome

Firefox logo Add to Firefox
Picture for Arman Cohan

Arman Cohan

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

MultiCite: Modeling realistic citations requires moving beyond the single-sentence single-label setting


Jul 01, 2021
Anne Lauscher, Brandon Ko, Bailey Kuhl, Sophie Johnson, David Jurgens, Arman Cohan, Kyle Lo

Figure 1 for MultiCite: Modeling realistic citations requires moving beyond the single-sentence single-label setting
Figure 2 for MultiCite: Modeling realistic citations requires moving beyond the single-sentence single-label setting
Figure 3 for MultiCite: Modeling realistic citations requires moving beyond the single-sentence single-label setting
Figure 4 for MultiCite: Modeling realistic citations requires moving beyond the single-sentence single-label setting

  Access Paper or Ask Questions

A Dataset of Information-Seeking Questions and Answers Anchored in Research Papers


May 07, 2021
Pradeep Dasigi, Kyle Lo, Iz Beltagy, Arman Cohan, Noah A. Smith, Matt Gardner

Figure 1 for A Dataset of Information-Seeking Questions and Answers Anchored in Research Papers
Figure 2 for A Dataset of Information-Seeking Questions and Answers Anchored in Research Papers
Figure 3 for A Dataset of Information-Seeking Questions and Answers Anchored in Research Papers
Figure 4 for A Dataset of Information-Seeking Questions and Answers Anchored in Research Papers
* Accepted at NAACL 2021; Project page: https://allenai.org/project/qasper 
  Access Paper or Ask Questions

Simplified Data Wrangling with ir_datasets


Mar 03, 2021
Sean MacAvaney, Andrew Yates, Sergey Feldman, Doug Downey, Arman Cohan, Nazli Goharian

Figure 1 for Simplified Data Wrangling with ir_datasets
Figure 2 for Simplified Data Wrangling with ir_datasets
Figure 3 for Simplified Data Wrangling with ir_datasets
Figure 4 for Simplified Data Wrangling with ir_datasets

  Access Paper or Ask Questions

Cross-Document Language Modeling


Jan 02, 2021
Avi Caciularu, Arman Cohan, Iz Beltagy, Matthew E. Peters, Arie Cattan, Ido Dagan

Figure 1 for Cross-Document Language Modeling
Figure 2 for Cross-Document Language Modeling
Figure 3 for Cross-Document Language Modeling
Figure 4 for Cross-Document Language Modeling

  Access Paper or Ask Questions

On Generating Extended Summaries of Long Documents


Dec 28, 2020
Sajad Sotudeh, Arman Cohan, Nazli Goharian

Figure 1 for On Generating Extended Summaries of Long Documents
Figure 2 for On Generating Extended Summaries of Long Documents
Figure 3 for On Generating Extended Summaries of Long Documents
Figure 4 for On Generating Extended Summaries of Long Documents
* Accepted at SDU 2021 
  Access Paper or Ask Questions

ParsiNLU: A Suite of Language Understanding Challenges for Persian


Dec 11, 2020
Daniel Khashabi, Arman Cohan, Siamak Shakeri, Pedram Hosseini, Pouya Pezeshkpour, Malihe Alikhani, Moin Aminnaseri, Marzieh Bitaab, Faeze Brahman, Sarik Ghazarian, Mozhdeh Gheini, Arman Kabiri, Rabeeh Karimi Mahabadi, Omid Memarrast, Ahmadreza Mosallanezhad, Erfan Noury, Shahab Raji, Mohammad Sadegh Rasooli, Sepideh Sadeghi, Erfan Sadeqi Azer, Niloofar Safi Samghabadi, Mahsa Shafaei, Saber Sheybani, Ali Tazarv, Yadollah Yaghoobzadeh

Figure 1 for ParsiNLU: A Suite of Language Understanding Challenges for Persian
Figure 2 for ParsiNLU: A Suite of Language Understanding Challenges for Persian
Figure 3 for ParsiNLU: A Suite of Language Understanding Challenges for Persian
Figure 4 for ParsiNLU: A Suite of Language Understanding Challenges for Persian
* (work in progress) 
  Access Paper or Ask Questions

ABNIRML: Analyzing the Behavior of Neural IR Models


Nov 02, 2020
Sean MacAvaney, Sergey Feldman, Nazli Goharian, Doug Downey, Arman Cohan

Figure 1 for ABNIRML: Analyzing the Behavior of Neural IR Models
Figure 2 for ABNIRML: Analyzing the Behavior of Neural IR Models
Figure 3 for ABNIRML: Analyzing the Behavior of Neural IR Models
Figure 4 for ABNIRML: Analyzing the Behavior of Neural IR Models

  Access Paper or Ask Questions

SLEDGE-Z: A Zero-Shot Baseline for COVID-19 Literature Search


Oct 12, 2020
Sean MacAvaney, Arman Cohan, Nazli Goharian

Figure 1 for SLEDGE-Z: A Zero-Shot Baseline for COVID-19 Literature Search
Figure 2 for SLEDGE-Z: A Zero-Shot Baseline for COVID-19 Literature Search
Figure 3 for SLEDGE-Z: A Zero-Shot Baseline for COVID-19 Literature Search
Figure 4 for SLEDGE-Z: A Zero-Shot Baseline for COVID-19 Literature Search
* EMNLP 2020. This article draws heavily from arXiv:2005.02365 
  Access Paper or Ask Questions

SPECTER: Document-level Representation Learning using Citation-informed Transformers


May 20, 2020
Arman Cohan, Sergey Feldman, Iz Beltagy, Doug Downey, Daniel S. Weld

Figure 1 for SPECTER: Document-level Representation Learning using Citation-informed Transformers
Figure 2 for SPECTER: Document-level Representation Learning using Citation-informed Transformers
Figure 3 for SPECTER: Document-level Representation Learning using Citation-informed Transformers
Figure 4 for SPECTER: Document-level Representation Learning using Citation-informed Transformers
* ACL 2020 
  Access Paper or Ask Questions

SLEDGE: A Simple Yet Effective Baseline for Coronavirus Scientific Knowledge Search


May 06, 2020
Sean MacAvaney, Arman Cohan, Nazli Goharian

Figure 1 for SLEDGE: A Simple Yet Effective Baseline for Coronavirus Scientific Knowledge Search
Figure 2 for SLEDGE: A Simple Yet Effective Baseline for Coronavirus Scientific Knowledge Search
Figure 3 for SLEDGE: A Simple Yet Effective Baseline for Coronavirus Scientific Knowledge Search
Figure 4 for SLEDGE: A Simple Yet Effective Baseline for Coronavirus Scientific Knowledge Search

  Access Paper or Ask Questions

TLDR: Extreme Summarization of Scientific Documents


May 02, 2020
Isabel Cachola, Kyle Lo, Arman Cohan, Daniel S. Weld

Figure 1 for TLDR: Extreme Summarization of Scientific Documents
Figure 2 for TLDR: Extreme Summarization of Scientific Documents
Figure 3 for TLDR: Extreme Summarization of Scientific Documents
Figure 4 for TLDR: Extreme Summarization of Scientific Documents

  Access Paper or Ask Questions

Fact or Fiction: Verifying Scientific Claims


May 01, 2020
David Wadden, Kyle Lo, Lucy Lu Wang, Shanchuan Lin, Madeleine van Zuylen, Arman Cohan, Hannaneh Hajishirzi

Figure 1 for Fact or Fiction: Verifying Scientific Claims
Figure 2 for Fact or Fiction: Verifying Scientific Claims
Figure 3 for Fact or Fiction: Verifying Scientific Claims
Figure 4 for Fact or Fiction: Verifying Scientific Claims
* 16 pages (including appendices), 10 figures, 7 tables. GitHub: https://github.com/allenai/scifact 
  Access Paper or Ask Questions

Document-level Representation Learning using Citation-informed Transformers


Apr 15, 2020
Arman Cohan, Sergey Feldman, Iz Beltagy, Doug Downey, Daniel S. Weld

Figure 1 for Document-level Representation Learning using Citation-informed Transformers
Figure 2 for Document-level Representation Learning using Citation-informed Transformers
Figure 3 for Document-level Representation Learning using Citation-informed Transformers
Figure 4 for Document-level Representation Learning using Citation-informed Transformers
* ACL 2020 
  Access Paper or Ask Questions

Longformer: The Long-Document Transformer


Apr 10, 2020
Iz Beltagy, Matthew E. Peters, Arman Cohan

Figure 1 for Longformer: The Long-Document Transformer
Figure 2 for Longformer: The Long-Document Transformer
Figure 3 for Longformer: The Long-Document Transformer
Figure 4 for Longformer: The Long-Document Transformer

  Access Paper or Ask Questions

Ranking Significant Discrepancies in Clinical Reports


Jan 18, 2020
Sean MacAvaney, Arman Cohan, Nazli Goharian, Ross Filice

Figure 1 for Ranking Significant Discrepancies in Clinical Reports
Figure 2 for Ranking Significant Discrepancies in Clinical Reports
* ECIR 2020 (short) 
  Access Paper or Ask Questions

Pretrained Language Models for Sequential Sentence Classification


Sep 22, 2019
Arman Cohan, Iz Beltagy, Daniel King, Bhavana Dalvi, Daniel S. Weld

Figure 1 for Pretrained Language Models for Sequential Sentence Classification
Figure 2 for Pretrained Language Models for Sequential Sentence Classification
Figure 3 for Pretrained Language Models for Sequential Sentence Classification
Figure 4 for Pretrained Language Models for Sequential Sentence Classification
* EMNLP 2019 
  Access Paper or Ask Questions

Extracting evidence of supplement-drug interactions from literature


Sep 17, 2019
Lucy Lu Wang, Oyvind Tafjord, Sarthak Jain, Arman Cohan, Sam Skjonsberg, Carissa Schoenick, Nick Botner, Waleed Ammar

Figure 1 for Extracting evidence of supplement-drug interactions from literature
Figure 2 for Extracting evidence of supplement-drug interactions from literature
Figure 3 for Extracting evidence of supplement-drug interactions from literature
Figure 4 for Extracting evidence of supplement-drug interactions from literature
* 11 pages, 2 figures, 3 tables 
  Access Paper or Ask Questions

Ontology-Aware Clinical Abstractive Summarization


May 14, 2019
Sean MacAvaney, Sajad Sotudeh, Arman Cohan, Nazli Goharian, Ish Talati, Ross W. Filice

Figure 1 for Ontology-Aware Clinical Abstractive Summarization
Figure 2 for Ontology-Aware Clinical Abstractive Summarization
Figure 3 for Ontology-Aware Clinical Abstractive Summarization
* 4 pages; SIGIR 2019 Short Paper 
  Access Paper or Ask Questions

CEDR: Contextualized Embeddings for Document Ranking


Apr 24, 2019
Sean MacAvaney, Andrew Yates, Arman Cohan, Nazli Goharian

Figure 1 for CEDR: Contextualized Embeddings for Document Ranking
Figure 2 for CEDR: Contextualized Embeddings for Document Ranking
Figure 3 for CEDR: Contextualized Embeddings for Document Ranking
* Accepted to SIGIR 2019, camera ready to follow 
  Access Paper or Ask Questions

Contextualized Word Representations for Document Re-Ranking


Apr 15, 2019
Sean MacAvaney, Andrew Yates, Arman Cohan, Nazli Goharian

Figure 1 for Contextualized Word Representations for Document Re-Ranking
Figure 2 for Contextualized Word Representations for Document Re-Ranking
Figure 3 for Contextualized Word Representations for Document Re-Ranking
* Accepted to SIGIR 2019, camera ready to follow 
  Access Paper or Ask Questions

Structural Scaffolds for Citation Intent Classification in Scientific Publications


Apr 02, 2019
Arman Cohan, Waleed Ammar, Madeleine van Zuylen, Field Cady

Figure 1 for Structural Scaffolds for Citation Intent Classification in Scientific Publications
Figure 2 for Structural Scaffolds for Citation Intent Classification in Scientific Publications
Figure 3 for Structural Scaffolds for Citation Intent Classification in Scientific Publications
Figure 4 for Structural Scaffolds for Citation Intent Classification in Scientific Publications
* NAACL 2019 
  Access Paper or Ask Questions

SciBERT: Pretrained Contextualized Embeddings for Scientific Text


Mar 26, 2019
Iz Beltagy, Arman Cohan, Kyle Lo

Figure 1 for SciBERT: Pretrained Contextualized Embeddings for Scientific Text
Figure 2 for SciBERT: Pretrained Contextualized Embeddings for Scientific Text
* https://github.com/allenai/scibert 
  Access Paper or Ask Questions

SMHD: A Large-Scale Resource for Exploring Online Language Usage for Multiple Mental Health Conditions


Jul 10, 2018
Arman Cohan, Bart Desmet, Andrew Yates, Luca Soldaini, Sean MacAvaney, Nazli Goharian

Figure 1 for SMHD: A Large-Scale Resource for Exploring Online Language Usage for Multiple Mental Health Conditions
Figure 2 for SMHD: A Large-Scale Resource for Exploring Online Language Usage for Multiple Mental Health Conditions
Figure 3 for SMHD: A Large-Scale Resource for Exploring Online Language Usage for Multiple Mental Health Conditions
Figure 4 for SMHD: A Large-Scale Resource for Exploring Online Language Usage for Multiple Mental Health Conditions
* COLING 2018 
  Access Paper or Ask Questions

RSDD-Time: Temporal Annotation of Self-Reported Mental Health Diagnoses


Jun 20, 2018
Sean MacAvaney, Bart Desmet, Arman Cohan, Luca Soldaini, Andrew Yates, Ayah Zirikly, Nazli Goharian

Figure 1 for RSDD-Time: Temporal Annotation of Self-Reported Mental Health Diagnoses
Figure 2 for RSDD-Time: Temporal Annotation of Self-Reported Mental Health Diagnoses
Figure 3 for RSDD-Time: Temporal Annotation of Self-Reported Mental Health Diagnoses
Figure 4 for RSDD-Time: Temporal Annotation of Self-Reported Mental Health Diagnoses
* 6 pages, accepted for publication at the CLPsych workshop at NAACL-HLT 2018 
  Access Paper or Ask Questions