WSD

This paper presents preliminary experiments in the use of translation equivalences to disambiguate prepositions or case suffixes. The core of the method is to find translations of the occurrence of the target preposition or case suffix, and assign the ...

We develop a model of preposition definitions in a machine-readable dictionary using the theory of labeled directed graphs and analyze the resulting digraphs to determine a primitive set of preposition senses. We characterize these primitives and show ...

In this paper we discuss some philosophical questions related to the treatment of abstract and underspecified prepositions. We consider three issues in particular: (i) the relation between sense and meanings, (ii) the privileged status of abstract ...

In this document, we analyze several aspects related to the semantics of prepositions. We propose an approach and elements of a method to organize and to represent prepositions uses and senses. Complex polysemous behaviors are discussed, showing the use ...

We report on an empirical study of sense relations in the Senseval-2 test suite. We apply and extend the method described in (Resnik and Yarowsky, 1999), estimating proximity of sense pairs from the evidence collected from native-speaker translations of ...

This paper presents a comparative evaluation among the systems that participated in the Spanish and English lexical sample tasks of SENSEVAL-2. The focus is on pairwise comparisons among systems to assess the degree to which they agree, and on measuring ...

For SENSEVAL-2, we disambiguated the lexical sample using two different sense inventories. Official SENSEVAL-2 results were generated using WordNet, and separately using the New Oxford Dictionary of English (NODE). Since our initial submission, we have ...

This paper describes an experiment that uses translation equivalents derived from parallel corpora to determine sense distinctions that can be used for automatic sense-tagging and other disambiguation tasks. Our results show that sense distinctions ...

We describe a new version of the Dutch word sense disambiguation system trained and tested on a corrected version of the SENSEVAL-2 data. The system is an ensemble of word experts; each word expert is a memory-based classifier of which the parameters ...

This paper presents a novel method for unsupervised word sense disambiguation, which combines multiple information sources, including semantic relations, large unlabeled corpora, and cross-lingual distributional statistics. This method extends and ...

This paper discusses ensembles of simple but heterogeneous classifiers for word-sense disambiguation, examining the Stanford-CS224N system entered in the SENSEVAL-2 English lexical sample task. First-order classifiers are combined by a second-order ...

This paper presents an evaluation of an ensemble-based system that participated in the English and Spanish lexical sample tasks of SENSEVAL-2. The system combines decision trees of unigrams, bigrams, and co---occurrences into a single classifier. The ...

In this paper we present a maximum entropy Word Sense Disambiguation system we developed which performs competitively on SENSEVAL-2 test data for English verbs. We demonstrate that using richer linguistic contextual features significantly improves ...

In this paper, we evaluate the results of the Antwerp University word sense disambiguation system in the English all words task of SENSEVAL-2. In this approach, specialized memory-based word-experts were trained per word-POS combination. Through ...

We investigate the suitability of sub-categorization acquisition for evaluation of word sense disambiguation (WSD) systems. We modify an existing subcategorization acquisition system to enable it to benefit from WSD. We present a small scale experiment ...

The paper is intended to promote discussion on potential application oriented methodologies for the next SENSEVAL, and to suggest one possibility for an application-oriented task. Whilst the traditional gold-standard sense-tagging methodology has proved ...

Open Mind Word Expert is an implemented active learning system for collecting word sense tagging from the general public over the Web. It is available at http://teach-computers.org. We expect the system to yield a large volume of high-quality training ...