A general framework for distributional similarity

Weeds, Julie; Weir, David

doi:10.3115/1119355.1119366

Cited by 91 publications

(114 citation statements)

References 9 publications

Supporting

Mentioning

110

Contrasting

Order By: Relevance

“…These measures give complementary perspectives on the similarity between the predicates, as the cosine similarity is symmetric between the LHS and RHS predicates, while BInc takes into account the directionality of the inference relation. Preliminary experiments with other measures, such as those of Lin (1998) and Weeds and Weir (2003) did not yield additional improvements.…”

Section: Feature Setmentioning

confidence: 99%

Lexical Inference over Multi-Word Predicates: A Distributional Approach

Abend¹,

Cohen²,

Steedman³

2014

Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

View full text Add to dashboard Cite

Representing predicates in terms of their argument distribution is common practice in NLP. Multi-word predicates (MWPs) in this context are often either disregarded or considered as fixed expressions. The latter treatment is unsatisfactory in two ways:(1) identifying MWPs is notoriously difficult, (2) MWPs show varying degrees of compositionality and could benefit from taking into account the identity of their component parts. We propose a novel approach that integrates the distributional representation of multiple sub-sets of the MWP's words. We assume a latent distribution over sub-sets of the MWP, and estimate it relative to a downstream prediction task. Focusing on the supervised identification of lexical inference relations, we compare against state-of-the-art baselines that consider a single sub-set of an MWP, obtaining substantial improvements. To our knowledge, this is the first work to address lexical relations between MWPs of varying degrees of compositionality within distributional semantics.

show abstract

Section: Feature Setmentioning

confidence: 99%

Lexical Inference over Multi-Word Predicates: A Distributional Approach

Abend¹,

Cohen²,

Steedman³

2014

Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

View full text Add to dashboard Cite

show abstract

“…For this reason, measures and weights have been extensively compared so far (Lee 1999;Curran and Moens 2002a;Weeds et al 2004), with varied results. Weeds and Wier's work (Weeds and Weir 2003) is worth attention here-they proposed new measures, namely, precision and recall, considering the context matching process as information retrieval. They also proposed a combined approach, which is generalization of several distributional similarity measures with tunable meta-parameters.…”

Section: Distributional Similaritymentioning

confidence: 99%

Supervised Synonym Acquisition Using Distributional Features and Syntactic Patterns

Hagiwara

Ogawa

Toyama

2009

Journal of Natural Language Processing

View full text Add to dashboard Cite

Distributional similarity has been widely used to capture the semantic relatedness of words in many NLP tasks. However, parameters such as similarity measures must be manually tuned to make distributional similarity work effectively. To address this problem, we propose a novel approach to synonym identification based on supervised learning and distributional features, which correspond to the commonality of individual context types shared by word pairs. This approach also enables the integration with pattern-based features. In our experiment, we have built and compared eight synonym classifiers, and showed a drastic performance increase of over 60% on F-1 measure, compared to the conventional similarity-based classification. Distributional features that we have proposed are better in classifying synonyms than the conventional common features, while the pattern-based features have appeared almost redundant.

show abstract

“…Therefore, they calculate the synonymy between two relations by comparing the arguments with which they occur. Several methods have been proposed [30,31,52,49,54], which differ in the representation of the predicates, the extracted features and the function used to compute the similarity of the feature vectors. To be effective, distributional metrics must rely on some weighting scheme over the relation features.…”

Section: Synonym Resolutionmentioning

confidence: 99%

Exploiting semantic annotations for open information extraction: an experience in the biomedical domain

Nebot

Berlanga

2012

Knowl Inf Syst

View full text Add to dashboard Cite

Abstract.The increasing amount of unstructured text published on the Web is demanding new tools and methods to automatically process and extract relevant information. Traditional information extraction has focused on harvesting domain-specific, pre-specified relations, which usually requires manual labor and heavy machinery. Especially in the biomedical domain the main efforts have been directed towards the recognition of welldefined entities such as genes or proteins, which constitutes the basis for extracting the relations between the recognized entities. The intrinsic features and scale of the Web demand new approaches able to cope with the diversity of documents, where the number of relations is unbounded and not known in advance. This paper presents a scalable method for the extraction of domain-independent relations from text that exploits the knowledge in the semantic annotations. The method is not geared to any specific domain (e.g., protein-protein interactions, drug-drug interactions, etc.) and does not require any manual input or deep processing. Moreover, the method uses the extracted relations to compute groups of abstract semantic relations characterized by their signature types and synonymous relation strings. This constitutes a valuable source of knowledge when constructing formal knowledge bases, as we enable seamless integration of the extracted relations with the available knowledge resources through the process of semantic annotation. The proposed approach has successfully been applied to a large text collection in the biomedical domain and the results are very encouraging.

show abstract

A general framework for distributional similarity

Cited by 91 publications

References 9 publications

Lexical Inference over Multi-Word Predicates: A Distributional Approach

Lexical Inference over Multi-Word Predicates: A Distributional Approach

Supervised Synonym Acquisition Using Distributional Features and Syntactic Patterns

Exploiting semantic annotations for open information extraction: an experience in the biomedical domain

Contact Info

Product

Resources

About