• Publications
  • Influence
The Stanford CoreNLP Natural Language Processing Toolkit
tl;dr
We describe the design and use of the Stanford CoreNLP toolkit, an extensible pipeline that provides core natural language analysis. Expand
  • 4,680
  • 571
  • Open Access
Multi-instance Multi-label Learning for Relation Extraction
tl;dr
We propose a novel approach to multi-instance multi-label learning for RE, which jointly models all the instances of a pair of entities in text and all their labels using a graphical model with latent variables. Expand
  • 560
  • 91
  • Open Access
The CoNLL 2008 Shared Task on Joint Parsing of Syntactic and Semantic Dependencies
tl;dr
The Conference on Computational Natural Language Learning is accompanied every year by a shared task whose purpose is to promote natural language processing applications and evaluate them in a standard setting. Expand
  • 478
  • 68
  • Open Access
Deterministic Coreference Resolution Based on Entity-Centric, Precision-Ranked Rules
tl;dr
We propose a new deterministic approach to coreference resolution that combines the global information and precise features of modern machine-learning models with the transparency and modularity of deterministic, rule-based systems. Expand
  • 395
  • 61
  • Open Access
Stanford's Multi-Pass Sieve Coreference Resolution System at the CoNLL-2011 Shared Task
tl;dr
This paper describes the coreference resolution system used by Stanford at the CoNLL-2011 shared task (Pradhan et al., 2011). Expand
  • 448
  • 56
  • Open Access
The CoNLL-2009 Shared Task: Syntactic and Semantic Dependencies in Multiple Languages
tl;dr
We define the shared task, describe how the data sets were created and show their quantitative properties, report the results and summarize the approaches of the participating systems. Expand
  • 489
  • 48
  • Open Access
A Multi-Pass Sieve for Coreference Resolution
tl;dr
We propose a simple coreference architecture based on a sieve that applies tiers of deterministic coreference models one at a time from highest to lowest precision. Expand
  • 365
  • 28
  • Open Access
Using Predicate-Argument Structures for Information Extraction
tl;dr
In this paper we present a novel, customizable IE paradigm that takes advantage of predicate-argument structures. Expand
  • 408
  • 20
  • Open Access
FALCON: Boosting Knowledge for Answer Engines
tl;dr
This paper discusses FALCON, an answer engine that integrates different forms of syntactic, semantic and pragmatic knowledge for the goal of achieving better performance. Expand
  • 315
  • 19
Learning to Rank Answers to Non-Factoid Questions from Web Collections
tl;dr
We show that it is possible to exploit existing large collections of question–answer pairs (from online social Question Answering sites) to extract such features and train ranking models which combine them effectively. Expand
  • 153
  • 17
  • Open Access