Skip to main content ->
Ai2

Research - Papers

Explore a selection of our published work on a variety of key research challenges in AI.

Filter papers

TREC-COVID: Rationale and Structure of an Information Retrieval Shared Task for COVID-19

Kirk RobertsTasmeer AlamSteven BedrickWilliam R. Hersh
2020
JAMIA

TREC-COVID is an information retrieval (IR) shared task initiated to support clinicians and clinical research during the COVID-19 pandemic. IR for pandemics breaks many normal assumptions, which can… 

Ranking Significant Discrepancies in Clinical Reports

Sean MacAvaneyArman CohanNazli GoharianRoss Filice
2020
ECIR

Medical errors are a major public health concern and a leading cause of death worldwide. Many healthcare centers and hospitals use reporting systems where medical practitioners write a preliminary… 

Longformer: The Long-Document Transformer

Iz BeltagyMatthew E. PetersArman Cohan
2020
arXiv

Transformer-based models are unable to process long sequences due to their self-attention operation, which scales quadratically with the sequence length. To address this limitation, we introduce the… 

Just Add Functions: A Neural-Symbolic Language Model

David DemeterDoug Downey
2019
arXiv

Neural network language models (NNLMs) have achieved ever-improving accuracy due to more sophisticated architectures and increasing amounts of training data. However, the inductive bias of these… 

Pretrained Language Models for Sequential Sentence Classification

Arman CohanIz BeltagyDaniel KingDaniel S. Weld
2019
EMNLP

As a step toward better document-level understanding, we explore classification of a sequence of sentences into their corresponding categories, a task that requires understanding sentences in… 

SciBERT: A Pretrained Language Model for Scientific Text

Iz BeltagyKyle LoArman Cohan
2019
EMNLP

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… 

SpanBERT: Improving Pre-training by Representing and Predicting Spans

Mandar JoshiDanqi ChenYinhan LiuOmer Levy
2019
EMNLP

We present SpanBERT, a pre-training method that is designed to better represent and predict spans of text. Our approach extends BERT by (1) masking contiguous random spans, rather than random… 

GrapAL: Connecting the Dots in Scientific Literature

Christine BettsJoanna PowerWaleed Ammar
2019
ACL

We introduce GrapAL (Graph database of Academic Literature), a versatile tool for exploring and investigating a knowledge base of scientific literature, that was semi-automatically constructed using… 

ScispaCy: Fast and Robust Models for Biomedical Natural Language Processing

Mark NeumannDaniel KingIz BeltagyWaleed Ammar
2019
ACL • BioNLP Workshop

Despite recent advances in natural language processing, many statistical models for processing text perform extremely poorly under domain shift. Processing biomedical and clinical text is a… 

CEDR: Contextualized Embeddings for Document Ranking

Sean MacAvaneyAndrew YatesArman CohanNazli Goharian
2019
SIGIR

Although considerable attention has been given to neural ranking architectures recently, far less attention has been paid to the term representations that are used as input to these models. In this…