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

Temporal Common Sense Acquisition with Minimal Supervision

Ben ZhouQiang NingDaniel KhashabiDan Roth
2020
ACL

Temporal common sense (e.g., duration and frequency of events) is crucial for understanding natural language. However, its acquisition is challenging, partly because such information is often not… 

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

Arman CohanSergey FeldmanIz BeltagyDaniel S. Weld
2020
ACL

Representation learning is a critical ingredient for natural language processing systems. Recent Transformer language models like BERT learn powerful textual representations, but these models are… 

Stolen Probability: A Structural Weakness of Neural Language Models

David DemeterGregory KimmelDoug Downey
2020
ACL

Neural Network Language Models (NNLMs) generate probability distributions by applying a softmax function to a distance metric formed by taking the dot product of a prediction vector with all word… 

SciREX: A Challenge Dataset for Document-Level Information Extraction

Sarthak JainMadeleine van ZuylenHannaneh HajishirziIz Beltagy
2020
ACL

Extracting information from full documents is an important problem in many domains, but most previous work focus on identifying relationships within a sentence or a paragraph. It is challenging to… 

S2ORC: The Semantic Scholar Open Research Corpus

Kyle LoLucy Lu WangMark E NeumannDaniel S. Weld
2020
ACL

We introduce S2ORC, a large contextual citation graph of English-language academic papers from multiple scientific domains; the corpus consists of 81.1M papers, 380.5M citation edges, and associated… 

Language (Re)modelling: Towards Embodied Language Understanding

Ronen TamariChen ShaniTom HopeDafna Shahaf
2020
ACL

While natural language understanding (NLU) is advancing rapidly, today’s technology differs from human-like language understanding in fundamental ways, notably in its inferior efficiency,… 

QuASE: Question-Answer Driven Sentence Encoding.

Hangfeng HeQiang NingDan Roth
2020
ACL

Question-answering (QA) data often encodes essential information in many facets. This paper studies a natural question: Can we get supervision from QA data for other tasks (typically, non-QA ones)?… 

Obtaining Faithful Interpretations from Compositional Neural Networks

Sanjay SubramanianBen BoginNitish GuptaMatt Gardner
2020
ACL

Neural module networks (NMNs) are a popular approach for modeling compositionality: they achieve high accuracy when applied to problems in language and vision, while reflecting the compositional… 

A Formal Hierarchy of RNN Architectures

William. MerrillGail Garfinkel WeissYoav GoldbergEran Yahav
2020
ACL

We develop a formal hierarchy of the expressive capacity of RNN architectures. The hierarchy is based on two formal properties: space complexity, which measures the RNN's memory, and rational… 

A Mixture of h-1 Heads is Better than h Heads

Hao PengRoy SchwartzDianqi LiNoah A. Smith
2020
ACL

Multi-head attentive neural architectures have achieved state-of-the-art results on a variety of natural language processing tasks. Evidence has shown that they are overparameterized; attention…