Discriminative Training Methods for Hidden Markov Models: Theory and Experiments with Perceptron Algorithms
- M. Collins
- Computer ScienceConference on Empirical Methods in Natural…
- 6 July 2002
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.
Head-Driven Statistical Models for Natural Language Parsing
- M. Collins
- Computer ScienceInternational Conference on Computational Logic
- 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.
Convolution Kernels for Natural Language
- M. Collins, Nigel P. Duffy
- Computer ScienceNIPS
- 3 January 2001
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.
Three Generative, Lexicalised Models for Statistical Parsing
- M. Collins
- Computer ScienceAnnual Meeting of the Association for…
- 17 June 1997
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.
Hidden Conditional Random Fields
- A. Quattoni, Sy Bor Wang, Louis-Philippe Morency, M. Collins, Trevor Darrell
- Computer ScienceIEEE Transactions on Pattern Analysis and Machine…
- 1 October 2007
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 random…
New Ranking Algorithms for Parsing and Tagging: Kernels over Discrete Structures, and the Voted Perceptron
- M. Collins, Nigel P. Duffy
- Computer ScienceAnnual Meeting of the Association for…
- 6 July 2002
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 sized…
Clause Restructuring for Statistical Machine Translation
- M. Collins, Philipp Koehn, I. Kucerova
- Computer ScienceAnnual Meeting of the Association for…
- 25 June 2005
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.
A Generalization of Principal Components Analysis to the Exponential Family
- M. Collins, S. Dasgupta, R. Schapire
- Computer ScienceNIPS
- 3 January 2001
This paper draws on ideas from the Exponential family, Generalized linear models, and Bregman distances to give a generalization of PCA to loss functions that it is argued are better suited to other data types.
Discriminative Reranking for Natural Language Parsing
- M. Collins, Terry Koo
- Computer ScienceComputational Linguistics
- 29 June 2000
The boosting approach to ranking problems described in Freund et al. (1998) is applied to parsing the Wall Street Journal treebank, and it is argued that the method is an appealing alternative-in terms of both simplicity and efficiency-to work on feature selection methods within log-linear (maximum-entropy) models.
A New Statistical Parser Based on Bigram Lexical Dependencies
- M. Collins
- Computer ScienceAnnual Meeting of the Association for…
- 6 May 1996
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.
...
...