Word sense disambiguation vs. statistical machine translation
Published 1 January 2005Open access
Marine Carpuat, Dekai Wu
Citations126
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
It is found that word sense disambiguation does not yield significantly better translation quality than the statistical machine translation system alone.
Abstract
We directly investigate a subject of much recent debate: do word sense disambiguation models help statistical machine translation quality? We present empirical results casting doubt on this common, but unproved, assumption. Using a state-of-the-art Chinese word sense disambiguation model to choose translation candidates for a typical IBM statistical MT system, we find that word sense disambiguation does not yield significantly better translation quality than the statistical machine translation system alone. Error analysis suggests several key factors behind this surprising finding, including inherent limitations of current statistical MT architectures.
Keywords
Computer Science
Journal of Computer and System SciencesA Decision-Theoretic Generalization of On-Line Learning and an Application to Boosting
20,320 Citations1997Yoav Freund, Robert E. Schapire
Neural ComputationNonlinear Component Analysis as a Kernel Eigenvalue Problem
8,078 Citations1998Bernhard Schölkopf, Alexander J. Smola +1 more
A new method for performing a nonlinear form of principal component analysis by the use of integral operator kernel functions is proposed and experimental results on polynomial feature extraction for pattern recognition are presented.
Computational LinguisticsA Systematic Comparison of Various Statistical Alignment Models
3,928 Citations2003Franz Josef Och, Hermann Ney
An important result is that refined alignment models with a first-order dependence and a fertility model yield significantly better results than simple heuristic models.
Machine LearningBoosTexter: A Boosting-based System for Text Categorization
2,194 Citations2000Robert E. Schapire, Yoram Singer
This work describes in detail an implementation, called BoosTexter, of the new boosting algorithms for text categorization tasks, and presents results comparing the performance of Boos Texter and a number of other text-categorization algorithms on a variety of tasks.
Discriminative training and maximum entropy models for statistical machine translation
1,044 Citations2001Franz Josef Och, Hermann Ney
A framework for statistical machine translation of natural languages based on direct maximum entropy models, which contains the widely used source-channel approach as a special case and shows that a baseline statistical machinetranslation system is significantly improved using this approach.
Statistical language modeling using the CMU-cambridge toolkit
564 Citations1997Philip Clarkson, Roni Rosenfeld
The conventional language modeling technology, as implemented in the toolkit, is outlined, and the extra e(cid:14)ciency and functionality that the new toolkit provides as compared to previous software for this task is described.
Word-sense disambiguation using statistical methods
369 Citations1991Peter F. Brown, Stephen A. Della Pietra +2 more
A statistical technique for assigning senses to words is described, which incorporated into the statistical machine translation system the error rate of the system decreased by thirteen percent.
Named Entity Extraction using AdaBoost
185 Citations2002Xavier Carreras, Lluı́s Màrquez +1 more
This paper presents a Named Entity Extraction (NEE) system for the CoNLL 2002 competition, which makes use of binary AdaBoost classifiers.
A polynomial-time algorithm for statistical machine translation
155 Citations1996Dekai Wu
A polynomial-time algorithm for statistical machine translation that employs the stochastic bracketing transduction grammar (SBTG) model to replace earlier word alignment channel models, while retaining a bigram language model.
Exploiting parallel texts for word sense disambiguation
144 Citations2003Hwee Tou Ng, Bin Wang +1 more
This paper evaluates an approach to automatically acquire sense-tagged training data from English-Chinese parallel corpora, which are then used for disambiguating the nouns in the SENSEVAL-2 English lexical sample task.
Natural Language EngineeringEvaluating sense disambiguation across diverse parameter spaces
118 Citations2002David Yarowsky, Radu Florian
This paper presents a comprehensive empirical exploration and evaluation of a diverse range of data characteristics which influence word sense disambiguation performance, including three variants of Bayesian classifiers, a cosine model, non-hierarchical decision lists, and a transformation-based learning model.
Reordering constraints for phrase-based statistical machine translation
114 Citations2004Richard Zens, Hermann Ney +2 more
This work investigates different reordering constraints for phrase-based statistical machine translation, namely the IBM constraints and the ITG constraints and presents efficient dynamic programming algorithms for both constraints.
Conditional structure versus conditional estimation in NLP models
99 Citations2002Dan Klein, Christopher D. Manning
Error analysis on part-of-speech tagging shows that the actual tagging errors made by the conditionally structured model derive not only from label bias, but also from other ways in which the independence assumptions of the conditional model structure are unsuited to linguistic sequences.
Machine translation with a stochastic grammatical channel
74 Citations1998Dekai Wu, Hongsing Wong Hkust
A stochastic grammatical channel model for machine translation, that synthesizes several desirable characteristics of both statistical and grammatical machine translation and achieves significant speed gains over the earlier model.
Greedy decoding for statistical machine translation in almost linear time
73 Citations2003Ulrich Germann
Improvements to a greedy decoding algorithm for statistical machine translation are presented that reduce its time complexity from at least cubic (O(n6) when applied naively) to practically linear time1 without sacrificing translation quality.
Computational LinguisticsWord Translation Disambiguation Using Bilingual Bootstrapping
72 Citations2004Hang Li, Cong Li
Word translation disambiguation using Bilingual Bootstrapping
34 Citations2001Cong Li, Hang Li
Experimental results indicate that word translation disambiguation based on bilingual bootstrapping consistently and significantly outperforms existing methods that are based on monolingualbootstrapping.
Relieving the data acquisition bottleneck in word sense disambiguation
34 Citations2004Mona Diab
This paper presents an unsupervised bootstrapping approach for WSD which exploits huge amounts of automatically generated noisy data for training within a supervised learning framework.
A kernel PCA method for superior word sense disambiguation
26 Citations2004Dekai Wu, Weifeng Su +1 more
A new method for disambiguating word senses that exploits a nonlinear Kernel Principal Component Analysis (KPCA) technique to achieve accuracy superior to the best published individual models.
Proceedings of the 17th international conference on Computational linguistics -Machine translation with a stochastic grammatical channel
18 Citations1998Dekai Wu, Hongsing Wong Hkust
Meeting of the Association for Computational LinguisticsAugmenting Ensemble Classification for Word Sense Disambiguation with a Kernel PCA Model
18 Citations2004Marine Carpuat, Weifeng Su +1 more
Among an ensemble of four different kinds of voted models, the KPCA-based model, along with the maximum entropy model, outperforms the boosting model and the highest entropy model.