• Publications
  • Influence
Exploring Various Knowledge in Relation Extraction
TLDR
This paper investigates the incorporation of diverse lexical, syntactic and semantic knowledge in feature-based relation extraction using SVM. Expand
  • 610
  • 51
  • PDF
A Composite Kernel to Extract Relations between Entities with Both Flat and Structured Features
TLDR
This paper proposes a novel composite kernel for relation extraction. Expand
  • 263
  • 35
  • PDF
A Phrase-Based Statistical Model for SMS Text Normalization
TLDR
We propose a phrase-based statistical method to normalize SMS messages. Expand
  • 254
  • 31
  • PDF
A Joint Source-Channel Model for Machine Transliteration
TLDR
This paper presents a new framework that allows direct orthographical mapping (DOM) between two languages, through a joint source-channel model, also called n-gram transliteration model (TM). Expand
  • 270
  • 31
  • PDF
Fast and Accurate Shift-Reduce Constituent Parsing
TLDR
We propose a simple yet effective extension to the shift-reduce process to address this problem, which eliminates size differences between action sequences in beam-search. Expand
  • 142
  • 24
  • PDF
Tree Kernel-Based Relation Extraction with Context-Sensitive Structured Parse Tree Information
TLDR
This paper proposes a tree kernel with contextsensitive structured parse tree information for relation extraction. Expand
  • 209
  • 16
  • PDF
Report of NEWS 2009 Machine Transliteration Shared Task
TLDR
This report documents the details of the Machine Transliteration Shared Task conducted as a part of the Named Entities Workshop (NEWS), an ACL-IJCNLP 2009 workshop. Expand
  • 89
  • 12
Exploring Syntactic Features for Relation Extraction using a Convolution Tree Kernel
TLDR
This paper proposes to use a convolution kernel over parse trees to model syntactic structure information for relation extraction. Expand
  • 107
  • 11
  • PDF
Cache-based Document-level Statistical Machine Translation
TLDR
This paper proposes a cache-based approach for document-level translation using a static cache and a dynamic cache. Expand
  • 87
  • 8
  • PDF
Joint Models for Chinese POS Tagging and Dependency Parsing
TLDR
This paper proposes a solution by jointly optimizing POS tagging and dependency parsing in a unique model. Expand
  • 72
  • 8
  • PDF