Learning the Latent Semantics of a Concept from its Definition
Published 1 January 2012Open access
Weiwei Guo, Mona Diab
Citations6
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
This paper learns low-dimensional latent semantic vectors of concept definitions to construct a more robust sense similarity measure wmfvec, achieving results comparable to state of the art WSD systems.
Abstract
In this paper we study unsupervised word sense disambiguation (WSD) based on sense definition. We learn low-dimensional latent semantic vectors of concept definitions to construct a more robust sense similarity measure wmfvec. Experiments on four all-words WSD data sets show significant improvement over the baseline WSD systems and LDA based similarity measures, achieving results comparable to state of the art WSD systems.
Keywords
Computer Science
Journal of Machine Learning ResearchLatent dirichlet allocation
27,049 Citations2003David M. Blei, Andrew Y. Ng +1 more
Language<b>WordNet: An electronic lexical database</b> . Ed. by Christiane Fellbaum. Cambridge, MA: MIT Press, 1998. Pp. xxii, 423.
11,687 Citations2000Adam Kilgarriff
The lexical database: nouns in WordNet, George A. Miller modifiers in WordNet, Katherine J. Miller a semantic network of English verbs, and applications of WordNet: building semantic concordances are presented.
Proceedings of the National Academy of SciencesFinding scientific topics
6,017 Citations2004Thomas L. Griffiths, Mark Steyvers
A generative model for documents is described, introduced by Blei, Ng, and Jordan, and a Markov chain Monte Carlo algorithm is presented for inference in this model, which is used to analyze abstracts from PNAS by using Bayesian model selection to establish the number of topics.
Feature-rich part-of-speech tagging with a cyclic dependency network
2,851 Citations2003Kristina Toutanova, Dan Klein +2 more
A new part-of-speech tagger is presented that demonstrates the following ideas: explicit use of both preceding and following tag contexts via a dependency network representation, broad use of lexical features, and effective use of priors in conditional loglinear models.
WordNet::Similarity
817 Citations2004Ted Pedersen, Siddharth Patwardhan +1 more
WordNet::Similarity is a freely available software package that makes it possible to measure the semantic similarity and relatedness between a pair of concepts (or synsets).
Extended gloss overlaps as a measure of semantic relatedness
719 Citations2003Satanjeev Banerjee, Ted Pedersen
A new measure of semantic relatedness between concepts that is based on the number of shared words (overlaps) in their definitions (glosses) and reasonably correlates to human judgments is presented.
International Conference on Machine LearningWeighted low-rank approximations
702 Citations2003Nathan Srebro, Tommi Jaakkola
This work provides a simple and efficient algorithm for solving weighted low-rank approximation problems, which, unlike their unweighted version, do not admit a closed-form solution in general.
Personalizing PageRank for word sense disambiguation
535 Citations2009Eneko Agirre, Aitor Soroa
This paper proposes a new graph-based method that uses the knowledge in a LKB (based on WordNet) in order to perform unsupervised Word Sense Disambiguation, performing better than previous approaches in English all-words datasets.
Unsupervised large-vocabulary word sense disambiguation with graph-based algorithms for sequence data labeling
508 Citations2005Rada Mihalcea
The algorithm is illustrated and tested in the context of an unsupervised word sense disambiguation problem, and shown to significantly outperform the accuracy achieved through individual label assignment, as measured on standard sense-annotated data sets.
Finding predominant word senses in untagged text
315 Citations2004Diana McCarthy, Rob Koeling +2 more
This work presents work on the use of a thesaurus acquired from raw textual corpora and the WordNet similarity package to find predominant noun senses automatically, and demonstrates that this method discovers appropriate predominant senses for words from two domain-specific corpora.
International Conference on Semantic Computing (ICSC 2007)Unsupervised Graph-basedWord Sense Disambiguation Using Measures of Word Semantic Similarity
230 Citations2007Ravi Sinha, Rada Mihalcea
Modeling Sentences in the Latent Space
119 Citations2012Weiwei Guo, Mona Diab
By carefully handling words that are not in the sentences (missing words), a reliable latent variable model on sentences is trained and a new evaluation framework for sentence similarity is proposed: Concept Definition Retrieval.
Topic Models for Word Sense Disambiguation and Token-Based Idiom Detection
67 Citations2010Linlin Li, Benjamin Roth +1 more
A probabilistic model for sense disambiguation which chooses the best sense based on the conditional probability of sense paraphrases given a context is presented, using a topic model to decompose this conditional probability into two conditional probabilities with latent variables.
Ensemble methods for unsupervised WSD
55 Citations2006Samuel Brody, Roberto Navigli +1 more
This paper investigates several voting- and arbiter-based combination strategies over a diverse pool of unsupervised WSD systems and demonstrates that their ensembles yield significantly better results when compared with state-of-the-art.
ScopusImproving Word Sense Disambiguation Using Topic Features
40 Citations2007Junfu Cai, Wee Sun Lee +1 more
This paper presents a novel approach for exploiting the global context for the task of word sense disambiguation by using topic features constructed using the latent dirichlet allocation (LDA) algorithm on unlabeled data.
Semantic Topic Models: Combining Word Distributional Statistics andDictionary Definitions
32 Citations2011Weiwei Guo, Mona Diab
A novel topic model based on incorporating dictionary definitions is proposed and it is shown that explicitly modeling word definitions helps improve performance significantly over the baseline for a text categorization task.
Combining Orthogonal Monolingual and Multilingual Sources of Evidence for All Words WSD
25 Citations2010Weiwei Guo, Mona Diab
This paper reports the highest results obtained to date on the SENSEVAL 2 standard data set using an unsupervised method, and achieves an overall F measure of 64.58 using a voting scheme.