Author pages are created from data sourced from our academic publisher partnerships and public sources.
- Publications
- Influence
Learning Bilingual Lexicons from Monolingual Corpora
- A. Haghighi, Percy Liang, Taylor Berg-Kirkpatrick, D. Klein
- Computer Science
- ACL
- 1 June 2008
We present a method for learning bilingual translation lexicons from monolingual corpora. Word types in each language are characterized by purely monolingual features, such as context counts and… Expand
Exploring Content Models for Multi-Document Summarization
- A. Haghighi, Lucy Vanderwende
- Computer Science
- HLT-NAACL
- 31 May 2009
We present an exploration of generative probabilistic models for multi-document summarization. Beginning with a simple word frequency based model (Nenkova and Vanderwende, 2005), we construct a… Expand
Prototype-Driven Learning for Sequence Models
- A. Haghighi, D. Klein
- Computer Science
- HLT-NAACL
- 4 June 2006
We investigate prototype-driven learning for primarily unsupervised sequence modeling. Prior knowledge is specified declaratively, by providing a few canonical examples of each target annotation… Expand
Joint Learning Improves Semantic Role Labeling
- Kristina Toutanova, A. Haghighi, Christopher D. Manning
- Computer Science
- ACL
- 25 June 2005
Despite much recent progress on accurate semantic role labeling, previous work has largely used independent classifiers, possibly combined with separate label sequence models via Viterbi decoding.… Expand
Structured Relation Discovery using Generative Models
- Limin Yao, A. Haghighi, S. Riedel, A. McCallum
- Computer Science
- EMNLP
- 27 July 2011
We explore unsupervised approaches to relation extraction between two named entities; for instance, the semantic bornIn relation between a person and location entity. Concretely, we propose a series… Expand
Simple Coreference Resolution with Rich Syntactic and Semantic Features
- A. Haghighi, D. Klein
- Computer Science
- EMNLP
- 6 August 2009
Coreference systems are driven by syntactic, semantic, and discourse constraints. We present a simple approach which completely modularizes these three aspects. In contrast to much current work,… Expand
A Global Joint Model for Semantic Role Labeling
- Kristina Toutanova, A. Haghighi, Christopher D. Manning
- Computer Science
- Computational Linguistics
- 1 June 2008
We present a model for semantic role labeling that effectively captures the linguistic intuition that a semantic argument frame is a joint structure, with strong dependencies among the arguments. We… Expand
Event Discovery in Social Media Feeds
- E. Benson, A. Haghighi, R. Barzilay
- Computer Science
- ACL
- 19 June 2011
We present a novel method for record extraction from social streams such as Twitter. Unlike typical extraction setups, these environments are characterized by short, one sentence messages with… Expand
Unsupervised Coreference Resolution in a Nonparametric Bayesian Model
- A. Haghighi, D. Klein
- Computer Science
- ACL
- 1 June 2007
We present an unsupervised, nonparametric Bayesian approach to coreference resolution which models both global entity identity across a corpus as well as the sequential anaphoric structure within… Expand
Coreference Resolution in a Modular, Entity-Centered Model
- A. Haghighi, D. Klein
- Computer Science
- HLT-NAACL
- 2 June 2010
Coreference resolution is governed by syntactic, semantic, and discourse constraints. We present a generative, model-based approach in which each of these factors is modularly encapsulated and… Expand