Cross-lingual Induction of Selectional Preferences with Bilingual Vector Spaces
Lirias (KU Leuven)Published 2 June 2010Open access
Yves Peirsman, Sebastian Padó
Citations30
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
A cross-lingual method for the induction of selectional preferences for resource-poor languages, where no accurate monolingual models are available, and the predictions correlate well with human ratings, clearly outperformingmonolingual baseline models.
Abstract
We describe a cross-lingual method for the induction of selectional preferences for resourcepoor languages, where no accurate monolingual models are available. The method uses bilingual vector spaces to “translate ” foreign language predicate-argument structures into a resource-rich language like English. The only prerequisite for constructing the bilingual vector space is a large unparsed corpus in the resource-poor language, although the model can profit from (even noisy) syntactic knowledge. Our experiments show that the cross-lingual predictions correlate well with human ratings, clearly outperforming monolingual baseline models. 1
Keywords
Computer Science
Cheap and fast---but is it good?
1,906 Citations2008Rion Snow, Brendan O’Connor +2 more
This work explores the use of Amazon's Mechanical Turk system, a significantly cheaper and faster method for collecting annotations from a broad base of paid non-expert contributors over the Web, and proposes a technique for bias correction that significantly improves annotation quality on two tasks.
Computational LinguisticsAutomatic Labeling of Semantic Roles
1,647 Citations2002Daniel Gildea, Daniel Jurafsky
Journal of Memory and LanguageModeling the Influence of Thematic Fit (and Other Constraints) in On-line Sentence Comprehension
740 Citations1998Ken McRae, Michael J. Spivey-Knowlton +1 more
Measures of distributional similarity
586 Citations1999Lillian Lee
This work presents an empirical comparison of a broad range of measures; a classification of similarity functions based on the information that they incorporate; and the introduction of a novel function that is superior at evaluating potential proxy distributions.
Automatic identification of word translations from unrelated English and German corpora
455 Citations1999Reinhard Rapp
The current study, based on the assumption that there is a correlation between the patterns of word co-occurrences in corpora of different languages, makes a significant improvement to about 72% of word translations identified correctly.
Unsupervised learning of narrative schemas and their participants
410 Citations2009Nathanael Chambers, Dan Jurafsky
An unsupervised system for learning narrative schemas, coherent sequences or sets of events whose arguments are filled with participant semantic roles defined over words to improve on previous results in narrative/frame learning and induce rich frame-specific semantic roles.
Natural Language EngineeringBootstrapping parsers via syntactic projection across parallel texts
339 Citations2005Rebecca Hwa, Philip Resnik +3 more
Using parallel text to help solving the problem of creating syntactic annotation in more languages by annotating the English side of a parallel corpus, project the analysis to the second language, and train a stochastic analyzer on the resulting noisy annotations.
CognitionSelectional constraints: an information-theoretic model and its computational realization
296 Citations1996Philip Resnik
The information-theoretic approach avoids empirical problems associated with definitional theories of word meaning, accommodates the observation that semantic anomaly often appears to be a matter of degree, and provides an account of how selectional constraints can be learned.
Language Resources and EvaluationAnCora: Multilevel Annotated Corpora for Catalan and Spanish
291 Citations2008Mariona Taulé, M. Antònia Martí +1 more
AnCora is the largest multilayer annotated corpus of these languages freely available from http://clic.ub.edu/ancora, a multilingual corpus annotated at different linguistic levels consisting of 500,000 words in Catalan and Spanish.
An unsupervised method for word sense tagging using parallel corpora
232 Citations2001Mona Diab, Philip Resnik
An unsupervised method for word sense disambiguation that exploits translation correspondences in parallel corpora is presented, using pseudo-translations, created by machine translation systems, in order to make possible the evaluation of the approach against a standard test set.
Learning a translation lexicon from monolingual corpora
226 Citations2002Philipp Koehn, Kevin Knight
This paper presents work on the task of constructing a word-level translation lexicon purely from unrelated monolingual corpora and combines various clues such as cognates, similar context, preservation of word similarity, and word frequency to create a German-English noun lexicon.
Principle-based parsing without overgeneration
168 Citations1993Dekang Lin
A message passing algorithm for principle-based parsing that avoids the overgeneration problem is presented and has been implemented in C++ and successfully tested with example sentences from (van Riemsdijk and Williams, 1986).
Computational LinguisticsDisambiguating Nouns, Verbs, and Adjectives Using Automatically Acquired Selectional Preferences
141 Citations2003Diana McCarthy, John Carroll
Although the preferences perform well in comparison with other unsupervised WSD systems on the same corpus, the results show that for many applications, further knowledge sources would be required to achieve an adequate level of accuracy and coverage.
Columbia Academic Commons (Columbia University)Finding Terminology Translations From Non-Parallel Corpora
135 Citations1997Pascale Fung, Fung, Pascale
A statistical word feature, the Word Relation Matrix, which can be used to find translated pairs of words and terms from non-parallel corpora, across language groups, is presented.
Computational LinguisticsClass-Based Probability Estimation Using a Semantic Hierarchy
124 Citations2002Stephen Clark, David Weir
This article concerns the estimation of a particular kind of probability, namely, the probability of a noun sense appearing as a particular argument of a predicate, and a procedure is developed that uses a chi-square test to determine a suitable level of generalization.
Looking for candidate translational equivalents in specialized, comparable corpora
116 Citations2002Yun-Chuang Chiao, Pierre Zweigenbaum
This work starts from smaller non-parallel, comparable corpora and an initial bilingual medical lexicon, comparing the distributional contexts of source and target words, and finds the correct translation is found in the top 10 candidates for 50% of them.
Discriminative learning of selectional preference from unlabeled text
64 Citations2008Shane Bergsma, Dekang Lin +1 more
The model outperforms other recent approaches, achieving excellent correlation with human plausibility judgments, and identifies 66% more verb-object pairs in unseen text, and resolves 37% more pronouns correctly in a pronoun resolution experiment.
Lirias (KU Leuven)Size matters: tight and loose context definitions in English word space models
45 Citations2008Yves Peirsman, Kris Heylen +1 more
This paper investigates whether two general ways of loosening the context definition — by extending the context size from one to ten words, and by taking into account secondorder context words — produce equivalent results.
Evaluating and combining approaches to selectional preference acquisition
45 Citations2003Carsten Brockmann, Mirella Lapata
This paper focuses on class-based models of selectional preferences for German verbs and takes into account not only direct objects, but also subjects and prepositional complements, and demonstrates that model combination enhances agreement with human ratings.
Using a probabilistic class-based lexicon for lexical ambiguity resolution
44 Citations2000Detlef Prescher, Stefan Riezler +1 more
The method employs minimal but precise contextual information for disambiguation in target-word selection, enriched by the condensed information of a probabilistic class-based lexicon, which shows promising results in an evaluation on real-world translations.
arXiv (Cornell University)Learning Word Association Norms Using Tree Cut Pair Models
43 Citations1996Naoki Abe, Hang Li
Empirical Methods in Natural Language ProcessingFlexible, Corpus-Based Modelling of Human Plausibility Judgements
37 Citations2007Sebastian Padó, Ulrike Padó +1 more
A completely corpus-driven model is obtained for this task which rivals or exceeds deeper, resource-driven models while exhibiting higher coverage and can be combined with deeper models to obtain better predictions than from either model alone.
Bootstrapping dictionaries for cross-language information retrieval
27 Citations2005Kornél Markó, Stefan Schulz +2 more
This work introduces a methodology by which multilingual dictionaries (for Spanish and Swedish) emerge automatically from simple seed lexicons, automatically generated, by cognate mapping, from (previously manually constructed) Portuguese and German as well as English sources.
Lecture notes in computer scienceDistributional Thesaurus Versus WordNet: A Comparison of Backoff Techniques for Unsupervised PP Attachment
21 Citations2005Hiram Calvo, Alexander Gelbukh +1 more
This work evaluates two different backoff methods, one based on WordNet and the other on a distributional (automatically created) thesaurus, for Prepositional Phrase attachment on Spanish.
Lecture notes in computer scienceA Pilot Study of English Selectional Preferences and Their Cross-Lingual Compatibility with Basque
10 Citations2003Eneko Agirre, Izaskun Aldezabal +1 more
A wide-range of techniques and issues are studied, with the aim of providing an analysis of the interplay of selectional-learning techniques, domain and multilinguality, to acquire complex lexical information for verbs using multilingual sources.