David Yarowsky

UNSUPERVISED WORD SENSE DISAMBIGUATION RIVALING SUPERVISED METHODS

This paper presents an unsupervised learning algorithm for sense disambiguation that, when trained on unannotated English text, rivals the performance of supervised techniques that require time-consuming hand annotations. The algorithm is based on two powerful constraints---that words tend to have one sense per discourse and one sense per collocation---exploited in an iterative bootstrapping procedure. Tested accuracy exceeds 96%.

Word-sense disambiguation using statistical models of Roget's categories trained on large corpora

This paper describes a program that disambiguates English word senses in unrestricted text using statistical models of the major Rogets Thesaurus categories. Rogets categories serve as approximations of conceptual classes. The categories listed for a word in Rogets index tend to correspond to sense distinctions; thus selecting the most likely category provides a useful level of sense disambiguation. The selection of categories is accomplished by identifying and weighting words that are indicative of each category when seen in context, using a Bayesian theoretical framework.Other statistical approaches have required special corpora or hand-labeled training examples for much of the lexicon. Our use of class models overcomes this knowledge acquisition bottleneck, enabling training on unrestricted monolingual text without human intervention. Applied to the 10 million word Groliers Encyclopedia, the system correctly disambiguated 92% of the instances of 12 polysemous words that have been previously studied in the literature.

A method for disambiguating word senses in a large corpus

Word sense disambiguation has been recognized as a major problem in natural language processing research for over forty years. Both quantitive and qualitative methods have been tried, but much of this work has been stymied by difficulties in acquiring appropriate lexical resources. The availability of this testing and training material has enabled us to develop quantitative disambiguation methods that achieve 92% accuracy in discriminating between two very distinct senses of a noun. In the training phase, we collect a number of instances of each sense of the polysemous noun. Then in the testing phase, we are given a new instance of the noun, and are asked to assign the instance to one of the senses. We attempt to answer this question by comparing the context of the unknown instance with contexts of known instances using a Bayesian argument that has been applied successfully in related tasks such as author identification and information retrieval. The proposed method is probably most appropriate for those aspects of sense disambiguation that are closest to the information retrieval task. In particular, the proposed method was designed to disambiguate senses that are usually associated with different topics.

Classifying latent user attributes in twitter

Social media outlets such as Twitter have become an important forum for peer interaction. Thus the ability to classify latent user attributes, including gender, age, regional origin, and political orientation solely from Twitter user language or similar highly informal content has important applications in advertising, personalization, and recommendation. This paper includes a novel investigation of stacked-SVM-based classification algorithms over a rich set of original features, applied to classifying these four user attributes. It also includes extensive analysis of features and approaches that are effective and not effective in classifying user attributes in Twitter-style informal written genres as distinct from the other primarily spoken genres previously studied in the user-property classification literature. Our models, singly and in ensemble, significantly outperform baseline models in all cases. A detailed analysis of model components and features provides an often entertaining insight into distinctive language-usage variation across gender, age, regional origin and political orientation in modern informal communication.

DECISION LISTS FOR LEXICAL AMBIGUITY RESOLUTION: Application to Accent Restoration in Spanish and French

This paper presents a statistical decision procedure for lexical ambiguity resolution. The algorithm exploits both local syntactic patterns and more distant collocational evidence, generating an efficient, effective, and highly perspicuous recipe for resolving a given ambiguity. By identifying and utilizing only the single best disambiguating evidence in a target context, the algorithm avoids the problematic complex modeling of statistical dependencies. Although directly applicable to a wide class of ambiguities, the algorithm is described and evaluated in a realistic case study, the problem of restoring missing accents in Spanish and French text. Current accuracy exceeds 99% on the full task, and typically is over 90% for even the most difficult ambiguities.

Unsupervised personal name disambiguation

This paper presents a set of algorithms for distinguishing personal names with multiple real referents in text, based on little or no supervision. The approach utilizes an unsupervised clustering technique over a rich feature space of biographic facts, which are automatically extracted via a language-independent bootstrapping process. The induced clustering of named entities are then partitioned and linked to their real referents via the automatically extracted biographic data. Performance is evaluated based on both a test set of handlabeled multi-referent personal names and via automatically generated pseudonames.

Inducing multilingual text analysis tools via robust projection across aligned corpora

This paper describes a system and set of algorithms for automatically inducing stand-alone monolingual part-of-speech taggers, base noun-phrase bracketers, named-entity taggers and morphological analyzers for an arbitrary foreign language. Case studies include French, Chinese, Czech and Spanish.Existing text analysis tools for English are applied to bilingual text corpora and their output projected onto the second language via statistically derived word alignments. Simple direct annotation projection is quite noisy, however, even with optimal alignments. Thus this paper presents noise-robust tagger, bracketer and lemmatizer training procedures capable of accurate system bootstrapping from noisy and incomplete initial projections.Performance of the induced stand-alone part-of-speech tagger applied to French achieves 96% core part-of-speech (POS) tag accuracy, and the corresponding induced noun-phrase bracketer exceeds 91% F-measure. The induced morphological analyzer achieves over 99% lemmatization accuracy on the complete French verbal system.This achievement is particularly noteworthy in that it required absolutely no hand-annotated training data in the given language, and virtually no language-specific knowledge or resources beyond raw text. Performance also significantly exceeds that obtained by direct annotation projection.

Distinguishing systems and distinguishing senses: new evaluation methods for Word Sense Disambiguation

Resnik and Yarowsky (1997) made a set of observations about the state-of-the-art in automatic word sense disambiguation and, motivated by those observations, offered several specific proposals regarding improved evaluation criteria, common training and testing resources, and the definition of sense inventories. Subsequent discussion of those proposals resulted in SENSEVAL, the first evaluation exercise for word sense disambiguation (Kilgarriff and Palmer 2000). This article is a revised and extended version of our 1997 workshop paper, reviewing its observations and proposals and discussing them in light of the SENSEVAL exercise. It also includes a new in-depth empirical study of translingually-based sense inventories and distance measures, using statistics collected from native-speaker annotations of 222 polysemous contexts across 12 languages. These data show that monolingual sense distinctions at most levels of granularity can be effectively captured by translations into some set of second languages, especially as language family distance increases. In addition, the probability that a given sense pair will tend to lexicalize differently across languages is shown to correlate with semantic salience and sense granularity; sense hierarchies automatically generated from such distance matrices yield results remarkably similar to those created by professional monolingual lexicographers.

Inducing multilingual POS taggers and NP bracketers via robust projection across aligned corpora

This paper investigates the potential for projecting linguistic annotations including part-of-speech tags and base noun phrase bracketings from one language to another via automatically word-aligned parallel corpora. First, experiments assess the accuracy of unmodified direct transfer of tags and brackets from the source language English to the target languages French and Chinese, both for noisy machine-aligned sentences and for clean hand-aligned sentences. Performance is then substantially boosted over both of these baselines by using training techniques optimized for very noisy data, yielding 94-96% core French part-of-speech tag accuracy and 90% French bracketing F-measure for stand-alone monolingual tools trained without the need for any human-annotated data in the given language.

Estimating Upper and Lower Bounds on the Performance of Word-Sense Disambiguation Programs

We have recently reported on two new word-sense disambiguation systems, one trained on bilingual material (the Canadian Hansards) and the other trained on monolingual material (Rogets Thesaurus and Groliers Encyclopedia). After using both the monolingual and bilingual classifiers for a few months, we have convinced ourselves that the performance is remarkably good. Nevertheless, we would really like to be able to make a stronger statement, and therefore, we decided to try to develop some more objective evaluation measures. Although there has been a fair amount of literature on sense-disambiguation, the literature does not offer much guidance in how we might establish the success or failure of a proposed solution such as the two systems mentioned in the previous paragraph. Many papers avoid quantitative evaluations altogether, because it is so difficult to come up with credible estimates of performance.This paper will attempt to establish upper and lower bounds on the level of performance that can be expected in an evaluation. An estimate of the lower bound of 75% (averaged over ambiguous types) is obtained by measuring the performance produced by a baseline system that ignores context and simply assigns the most likely sense in all cases. An estimate of the upper bound is obtained by assuming that our ability to measure performance is largely limited by our ability obtain reliable judgments from human informants. Not surprisingly, the upper bound is very dependent on the instructions given to the judges. Jorgensen, for example, suspected that lexicographers tend to depend too much on judgments by a single informant and found considerable variation over judgments (only 68% agreement), as she had suspected. In our own experiments, we have set out to find word-sense disambiguation tasks where the judges can agree often enough so that we could show that they were outperforming the baseline system. Under quite different conditions, we have found 96.8% agreement over judges.