• Publications
• Influence

Dates

Co-Author

Journal/Conference

Has PDF

Sorted by Highly Influential CitationsSorted by CitationsSorted by AccelerationSorted by VelocitySorted by Recency

---

SciBERT: Pretrained Contextualized Embeddings for Scientific Text

Iz Beltagy, Arman Cohan, Kyle Lo

Computer Science

ArXiv

2019 (First Publication: 26 March 2019)

Obtaining large-scale annotated data for NLP tasks in the scientific domain is challenging and expensive. We release SciBERT, a pretrained contextualized embedding model based on BERT (Devlin et al.,… Continue Reading

SciBERT: A Pretrained Language Model for Scientific Text

Iz Beltagy, Kyle Lo, Arman Cohan

Computer Science

EMNLP/IJCNLP

2019 (First Publication: 26 March 2019)

Obtaining large-scale annotated data for NLP tasks in the scientific domain is challenging and expensive. We release SciBERT, a pretrained language model based on BERT (Devlin et al., 2018) to… Continue Reading

Construction of the Literature Graph in Semantic Scholar

Waleed Ammar, Dirk Groeneveld, +20 authors Oren Etzioni

Computer Science

NAACL-HLT

2018 (First Publication: 6 May 2018)

We describe a deployed scalable system for organizing published scientific literature into a heterogeneous graph to facilitate algorithmic manipulation and discovery. The resulting literature graph… Continue Reading

Ontology Alignment in the Biomedical Domain Using Entity Definitions and Context

Lucy Lu Wang, Chandra Bhagavatula, Mark Neumann, Kyle Lo, Christopher Wilhelm, Waleed Ammar

Computer Science

BioNLP

2018 (First Publication: 20 June 2018)

Ontology alignment is the task of identifying semantically equivalent entities from two given ontologies. Different ontologies have different representations of the same entity, resulting in a need… Continue Reading

GORC: A large contextual citation graph of academic papers

Kyle Lo, Lucy Lu Wang, Mark E Neumann, Rodney Michael Kinney, Dan Weld

Computer Science

ArXiv

2019 (First Publication: 7 November 2019)

We introduce the Semantic Scholar Graph of References in Context (GORC), a large contextual citation graph of 81.1M academic publications, including parsed full text for 8.1M open access papers,… Continue Reading

Combining Distant and Direct Supervision for Neural Relation Extraction

Iz Beltagy, Kyle Lo, Waleed Ammar

Computer Science

NAACL-HLT

2019 (First Publication: 30 October 2018)

In relation extraction with distant supervision, noisy labels make it difficult to train quality models. Previous neural models addressed this problem using an attention mechanism that attends to… Continue Reading

Cooperative Generator-Discriminator Networks for Abstractive Summarization with Narrative Flow

Saadia Gabriel, Antoine Bosselut, Ari Holtzman, Kyle Lo, Asli Çelikyilmaz, Yejin Choi

Computer Science

ArXiv

2019 (First Publication: 2 July 2019)

We introduce Cooperative Generator-Discriminator Networks (Co-opNet), a general framework for abstractive summarization with distinct modeling of the narrative flow in the output summary. Most… Continue Reading

Quantifying Sex Bias in Clinical Studies at Scale With Automated Data Extraction

Sergey Feldman, Waleed Ammar, Kyle Lo, Elly Trepman, Madeleine van Zuylen, Oren Etzioni

Medicine

JAMA network open

2019 (First Publication: 3 July 2019)

Importance Analyses of female representation in clinical studies have been limited in scope and scale. Objective To perform a large-scale analysis of global enrollment sex bias in clinical studies.… Continue Reading

Improving Distant Supervision with Maxpooled Attention and Sentence-Level Supervision

Iz Beltagy, Kyle Lo, Waleed Ammar

Computer Science

ArXiv

2018

We propose an effective multitask learning setup for reducing distant supervision noise by leveraging sentence-level supervision. We show how sentence-level supervision can be used to improve the… Continue Reading

Explanation-Based Tuning of Opaque Machine Learners with Application to Paper Recommendation

Benjamin Charles Germain Lee, Kyle Lo, Doug Downey, Daniel S. Weld

Computer Science, Mathematics

ArXiv

2020 (First Publication: 9 March 2020)

Research in human-centered AI has shown the benefits of machine-learning systems that can explain their predictions. Methods that allow users to tune a model in response to the explanations are… Continue Reading

• ‹
• 1
• 2
• ›