Papers
See AI2's Award Winning Papers
Learn more about AI2's Lasting Impact Award
Viewing 731-740 of 844 papers
Crowdsourcing Multiple Choice Science Questions
Johannes Welbl, Nelson F. Liu, and Matt GardnerEMNLP • Workshop on Noisy User-generated Text • 2017 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, relevance or diversity in the answer options. Our method…Deep Semantic Role Labeling: What Works and What's Next
Luheng He, Kenton Lee, Mike Lewis, Luke S. ZettlemoyerACL • 2017 We introduce a new deep learning model for semantic role labeling (SRL) that significantly improves the state of the art, along with detailed analyses to reveal its strengths and limitations. We use a deep highway BiLSTM architecture with constrained decoding…Distilling Task Knowledge from How-To Communities
Cuong Xuan Chu, Niket Tandon, and Gerhard WeikumWWW • 2017 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, knowledge graphs completely lack this kind of how-to…Domain-Targeted, High Precision Knowledge Extraction
Bhavana Dalvi, Niket Tandon, and Peter ClarkTACL • 2017 Our goal is to construct a domain-targeted, high precision knowledge base (KB), containing general (subject,predicate,object) statements about the world, in support of a downstream question-answering (QA) application. Despite recent advances in information…End-to-End Neural Ad-hoc Ranking with Kernel Pooling
Chenyan Xiong, Zhuyun Dai, Jamie Callan, Zhiyuan Liu, and Russell PowerSIGIR • 2017 This paper proposes K-NRM, a kernel based neural model for document ranking. Given a query and a set of documents, K-NRM uses a translation matrix that models word-level similarities via word embeddings, a new kernel-pooling technique that uses kernels to…End-to-end Neural Coreference Resolution
Kenton Lee, Luheng He, Mike Lewis, and Luke ZettlemoyerEMNLP • 2017 We introduce the first end-to-end coreference resolution model and show that it significantly outperforms all previous work without using a syntactic parser or handengineered mention detector. The key idea is to directly consider all spans in a document as…Explicit Semantic Ranking for Academic Search via Knowledge Graph Embedding
Chenyan Xiong, Russell Power and Jamie CallanWWW • 2017 This paper introduces Explicit Semantic Ranking (ESR), a new ranking technique that leverages knowledge graph embedding. Analysis of the query log from our academic search engine, SemanticScholar.org, reveals that a major error source is its inability to…How Good Are My Predictions? Efficiently Approximating Precision-Recall Curves for Massive Datasets
Ashish Sabharwal and Hanie SedghiUAI • 2017 Large scale machine learning produces massive datasets whose items are often associated with a confidence level and can thus be ranked. However, computing the precision of these resources requires human annotation, which is often prohibitively expensive and…Incorporating Ethics into Artificial Intelligence
Amitai Etzioni and Oren EtzioniJournal of Ethics • 2017 This article reviews the reasons scholars hold that driverless cars and many other AI equipped machines must be able to make ethical decisions, and the difficulties this approach faces. It then shows that cars have no moral agency, and that the term…Interactive Visualization for Linguistic Structure
Aaron Sarnat, Vidur Joshi, Cristian Petrescu-Prahova, Alvaro Herrasti, Brandon Stilson, and Mark HopkinsEMNLP • 2017 We provide a visualization library and web interface for interactively exploring a parse tree or a forest of parses. The library is not tied to any particular linguistic representation, but provides a generalpurpose API for the interactive exploration of…