• Publications
  • Influence
Discriminative Training Methods for Hidden Markov Models: Theory and Experiments with Perceptron Algorithms
Experimental results on part-of-speech tagging and base noun phrase chunking are given, in both cases showing improvements over results for a maximum-entropy tagger. Expand
Head-Driven Statistical Models for Natural Language Parsing
  • M. Collins
  • Computer Science
  • Computational Linguistics
  • 1 December 2003
Three statistical models for natural language parsing are described, leading to approaches in which a parse tree is represented as the sequence of decisions corresponding to a head-centered, top-down derivation of the tree. Expand
Convolution Kernels for Natural Language
It is shown how a kernel over trees can be applied to parsing using the voted perceptron algorithm, and experimental results on the ATIS corpus of parse trees are given. Expand
Hidden Conditional Random Fields
We present a discriminative latent variable model for classification problems in structured domains where inputs can be represented by a graph of local observations. A hidden-state conditional randomExpand
New Ranking Algorithms for Parsing and Tagging: Kernels over Discrete Structures, and the Voted Perceptron
This paper introduces new learning algorithms for natural language processing based on the perceptron algorithm. We show how the algorithms can be efficiently applied to exponential sizedExpand
Clause Restructuring for Statistical Machine Translation
The reordering approach is applied as a pre-processing step in both the training and decoding phases of a phrase-based statistical MT system, showing an improvement from 25.2% Bleu score for a baseline system to 26.8% Blee score for the system with reordering. Expand
A New Statistical Parser Based on Bigram Lexical Dependencies
A new statistical parser which is based on probabilities of dependencies between head-words in the parse tree, which trains on 40,000 sentences in under 15 minutes and can be improved to over 200 sentences a minute with negligible loss in accuracy. Expand
Three Generative, Lexicalised Models for Statistical Parsing
A new statistical parsing model is proposed, which is a generative model of lexicalised context-free grammar and extended to include a probabilistic treatment of both subcategorisation and wh-movement. Expand
Unsupervised Models for Named Entity Classification
It is shown that the use of unlabeled data can reduce the requirements for supervision to just 7 simple "seed" rules, gaining leverage from natural redundancy in the data. Expand
Simple Semi-supervised Dependency Parsing
This work focuses on the problem of lexical representation, introducing features that incorporate word clusters derived from a large unannotated corpus, and shows that the cluster-based features yield substantial gains in performance across a wide range of conditions. Expand