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

Question Answering as Global Reasoning over Semantic Abstractions

Daniel KhashabiTushar KhotAshish Sabharwaland Dan Roth
2018
AAAI

We propose a novel method for exploiting the semantic structure of text to answer multiple-choice questions. The approach is especially suitable for domains that require reasoning over a diverse set… 

SciTail: A Textual Entailment Dataset from Science Question Answering

Tushar KhotAshish Sabharwaland Peter Clark
2018
AAAI

We present a new dataset and model for textual entailment, derived from treating multiple-choice question-answering as an entailment problem. SCITAIL is the first entailment set that is created… 

Commonsense Knowledge in Machine Intelligence

Niket TandonAparna S. VardeGerard de Melo
2017
SIGMOD Record

There is growing conviction that the future of computing depends on our ability to exploit big data on theWeb to enhance intelligent systems. This includes encyclopedic knowledge for factual… 

Men Also Like Shopping: Reducing Gender Bias Amplification using Corpus-level Constraints

Jieyu ZhaoTianlu WangMark YatskarKai-Wei Chang
2017
EMNLP

Language is increasingly being used to define rich visual recognition problems with supporting image collections sourced from the web. Structured prediction models are used in these tasks to take… 

Answering Complex Questions Using Open Information Extraction

Tushar KhotAshish Sabharwaland Peter Clark
2017
ACL

While there has been substantial progress in factoid question-answering (QA), answering complex questions remains challenging, typically requiring both a large body of knowledge and inference… 

Learning a Neural Semantic Parser from User Feedback

Srinivasan IyerIoannis KonstasAlvin Cheungand Luke Zettlemoyer
2017
ACL

We present an approach to rapidly and easily build natural language interfaces to databases for new domains, whose performance improves over time based on user feedback, and requires minimal… 

WebChild 2.0: Fine-Grained Commonsense Knowledge Distillation

Niket TandonGerard de Meloand Gerhard Weikum
2017
ACL

Despite important progress in the area of intelligent systems, most such systems still lack commonsense knowledge that appears crucial for enabling smarter, more human-like decisions. In this paper,… 

Automatic Selection of Context Configurations for Improved Class-Specific Word Representations

Ivan VulicRoy SchwartzAri Rappoportand Anna Korhonen
2017
CoNLL

This paper is concerned with identifying contexts useful for training word representation models for different word classes such as adjectives (A), verbs (V), and nouns (N). We introduce a simple… 

Crowdsourcing Multiple Choice Science Questions

Johannes WelblNelson F. Liuand Matt Gardner
2017
EMNLP • Workshop on Noisy User-generated Text

We present a novel method for obtaining high-quality, domain-targeted multiple choice questions from crowd workers. Generating these questions can be difficult without trading away originality,… 

Distilling Task Knowledge from How-To Communities

Cuong Xuan ChuNiket Tandonand Gerhard Weikum
2017
WWW

Knowledge graphs have become a fundamental asset for search engines. A fair amount of user queries seek information on problem-solving tasks such as building a fence or repairing a bicycle. However,…