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

Is Attention Interpretable?

Sofia SerranoNoah A. Smith
2019
ACL

Attention mechanisms have recently boosted performance on a range of NLP tasks. Because attention layers explicitly weight input components' representations, it is also often assumed that attention… 

Conversing by Reading: Contentful Neural Conversation with On-demand Machine Reading

Lianhui QinMichel GalleyChris BrockettJianfeng Gao
2019
ACL

Although neural conversational models are effective in learning how to produce fluent responses, their primary challenge lies in knowing what to say to make the conversation contentful and… 

SemEval-2019 Task 10: Math Question Answering

Mark HopkinsRonan Le BrasCristian Petrescu-PrahovaRik Koncel-Kedziorski
2019
SemEval

We report on the SemEval 2019 task on math question answering. We provided a question set derived from Math SAT practice exams, including 2778 training questions and 1082 test questions. For a… 

Variational Pretraining for Semi-supervised Text Classification

Suchin GururanganTam DangDallas CardNoah A. Smith
2019
ACL

We introduce VAMPIRE, a lightweight pretraining framework for effective text classification when data and computing resources are limited. We pretrain a unigram document model as a variational… 

Be Consistent! Improving Procedural Text Comprehension using Label Consistency

Xinya DuBhavana Dalvi MishraNiket TandonClaire Cardie
2019
NAACL-HLT

Our goal is procedural text comprehension, namely tracking how the properties of entities (e.g., their location) change with time given a procedural text (e.g., a paragraph about photosynthesis, a… 

DROP: A Reading Comprehension Benchmark Requiring Discrete Reasoning Over Paragraphs

Dheeru DuaYizhong WangPradeep DasigiMatt Gardner
2019
NAACL-HLT

Reading comprehension has recently seen rapid progress, with systems matching humans on the most popular datasets for the task. However, a large body of work has highlighted the brittleness of these… 

Studying the Inductive Biases of RNNs with Synthetic Variations of Natural Languages

Shauli RavfogelYoav GoldbergTal Linzen
2019
NAACL

How do typological properties such as word order and morphological case marking affect the ability of neural sequence models to acquire the syntax of a language? Cross-linguistic comparisons of… 

Lipstick on a Pig: Debiasing Methods Cover up Systematic Gender Biases in Word Embeddings But do not Remove Them

Hila GonenYoav Goldberg
2019
NAACL

Word embeddings are widely used in NLP for a vast range of tasks. It was shown that word embeddings derived from text corpora reflect gender biases in society. This phenomenon is pervasive and… 

Value-based Search in Execution Space for Mapping Instructions to Programs

Dor MuhlgayJonathan HerzigJonathan Berant
2019
NAACL

Training models to map natural language instructions to programs given target world supervision only requires searching for good programs at training time. Search is commonly done using beam search… 

CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge

Alon TalmorJonathan HerzigNicholas LourieJonathan Berant
2019
NAACL

When answering a question, people often draw upon their rich world knowledge in addition to the particular context. Recent work has focused primarily on answering questions given some relevant…