Extracting multiword expressions with a semantic tagger

Piao, Scott; Rayson, Paul; Archer, Dawn; Wilson, Andrew; McEnery, Tony

doi:10.3115/1119282.1119289

Cited by 24 publications

(16 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…This is due, as observed by Piao et al (2003), to the fact that the extraction of the MWE candidates is based only on the frequency of the bigrams, and only after the extraction of these candidates we applied the linguistic information (classification in grammatical classes).…”

Section: Comparison Between the 500-best Candidates Of Each Toolmentioning

confidence: 99%

“…For their data, for example, Piao et al (2003) found that 81.88% of the recognized MWEs were bigrams. The current study uses CETENFolha (Corpus de Extractos de Textos Electrónicos/NILC Folha de São Paulo) as a Brazilian Portuguese corpus, available on the Linguateca Portuguesa website, which is part of a project on the automatic processing of the Portuguese language (Kinoshita et al, 2006).…”

Section: Acknowledgmentsmentioning

confidence: 99%

See 1 more Smart Citation

Proceedings of the 4th International Workshop on Computational Terminology (Computerm)

2014

View full text Add to dashboard Cite

IntroductionComputational Terminology covers an increasingly important aspect in Natural Language Processing areas such as text mining, information retrieval, information extraction, summarisation, textual entailment, document management systems, question-answering systems, ontology building, etc. Terminological information is paramount for knowledge mining from texts for scientific discovery and competitive intelligence. Scientific needs in fast growing domains (such as biomedicine, chemistry and ecology) and the overwhelming amount of textual data published daily demand that terminology is acquired and managed systematically and automatically; while in well established domains (such as law, economy, banking and music) the demand is on fine-grained analyses of documents for knowledge description and acquisition. Moreover, capturing new concepts leads to the acquisition and management of new knowledge.The aim of this fourth CompuTerm workshop is to bring together Natural Language Processing researchers to discuss recent advances in computational terminology and its impact in many NLP applications. The topics addressed in this workshop are wide ranging:• term extraction, recognition and filtering, which is the core of the terminological activity that lays basis for other terminological topics and tasks;• event recognition and extraction, that extends the notion of the terminological entity from terms meaning static units up to terms meaning procedural and dynamic processes;• acquisition of semantic relations among terms, which is also an important research topic as the acquisition of semantic relationships between terms finds applications such as the population and update of existing knowledge bases, definition of domain specific templates in information extraction and disambiguation of terms;• term variation management, that helps to deal with the dynamic nature of terms, their acquisition from heterogeneous sources, their integration, standardisation and representation for a large range of applications and resources, is also increasingly important, as one has to address this research problem when working with various controlled vocabularies, thesauri, ontologies and textual data. Term variation is also related to their paraphrases and reformulations, due to historical, regional, local or personal issues. Besides, the discovery of synonym terms or term clusters is equally beneficial to many NLP applications;• definition acquisition, that covers important research and aims to provide precise and nonambiguous description of terminological entities. Such definitions may contain elements necessary for the formal description of terms and concepts within ontologies;• consideration of the user expertise, that is becoming a new issue in the terminological activity, takes into account the fact that specialized domains contain notions and terms often nonunderstandable to non-experts or to laymen (such as patients within the medical area, or bank clients within banking and economy areas). This aspect, although related to s...

show abstract

Section: Comparison Between the 500-best Candidates Of Each Toolmentioning

confidence: 99%

Section: Acknowledgmentsmentioning

confidence: 99%

Proceedings of the 4th International Workshop on Computational Terminology (Computerm)

2014

View full text Add to dashboard Cite

show abstract

“…We found 49,589 bigrams in the selected excerpts of texts, and the manual evaluation of each one, in order to decide which one is a MWE, would take too much time. So, we estimated the amount of MWEs for the total 49,589 bigrams as in (Piao et al, 2003). Using 100 excerpts of text we generated all the bigrams, with all frequencies.…”

Section: Comparison Of Different Classification Algorithmsmentioning

confidence: 99%

Identifying Portuguese Multiword Expressions using Different Classification Algorithms - A Comparative Analysis

Fonseca¹,

Sadat²,

Massé³

2014

Proceedings of the 4th International Workshop on Computational Terminology (Computerm)

View full text Add to dashboard Cite

This paper presents a comparative analysis based on different classification algorithms and tools for the identification of Portuguese multiword expressions. Our focus is on two-word expressions formed by nouns, adjectives and verbs. The candidates are selected on the basis of the frequency of the bigrams; then on the basis of the grammatical class of each bigram's constituent words. This analysis compares the performance of three different multi-layer perceptron training functions in the task of extracting different patterns of multiword expressions, using and comparing nine different classification algorithms, including decision trees, multilayer perceptron and SVM. Moreover, this analysis compares two different tools, Text-NSP and Termostat for the identification of multiword expressions using different association measures.

show abstract

“…After this step, association measures are computed. Piao et al (2003) use, what they call, a semantic field annotator. They use a semantic tagger for the English language called USAS, developed in Lancaster University.…”

Section: Introductionmentioning

confidence: 99%

Proceedings of the First Workshop on Computational Approaches to Compound Analysis (ComAComA 2014)

Verhoeven

Daelemans

Zaanen³

et al. 2014

View full text Add to dashboard Cite

ii IntroductionThe ComAComA workshop is an interdisciplinary platform for researchers working on compound processing in different languages, to present recent and ongoing work.The workshop has several related aims. Firstly, it brings together researchers from different backgrounds (e.g., computational linguistics, linguistics, neurolinguistics, psycholinguistics, language technology) to discuss and evaluate compound processing each from their own point of view. Secondly, based on the interaction between the participants, the workshop provides an overview of existing and desired resources for future research in this area. Finally, we expect that the interdisciplinary approach of the workshop will result in better methodologies to evaluate compound processing systems from different perspectives.Given the high productivity of compounding in a wide range of languages, compound processing is an interesting subject in linguistics, computational linguistics, and other applied disciplines. For example, for many language technology applications, compound processing remains a challenge (both morphologically and semantically), since novel compounds are created and interpreted on the fly. In order to deal with this productivity, systems that can analyse new compound forms and their meanings need to be developed. From an interdisciplinary perspective, we also need to better understand the process of compounding (as a cognitive process), in order to model its complexity.iii AbstractGerman particle verbs are a type of multi word expression which is often compositional with respect to a base verb. If they are compositional they tend to express the same types of semantic arguments, but they do not necessarily express them in the same syntactic subcategorization frame: some arguments may be expressed by differing syntactic subcategorization slots and other arguments may be only implicit in either the base or the particle verb. In this paper we present a method which predicts syntactic slot correspondences between syntactic slots of base and particle verb pairs. We can show that this method can predict subcategorization slot correspondences with a fair degree of success.

show abstract

Extracting multiword expressions with a semantic tagger

Cited by 24 publications

References 8 publications

Proceedings of the 4th International Workshop on Computational Terminology (Computerm)

Proceedings of the 4th International Workshop on Computational Terminology (Computerm)

Identifying Portuguese Multiword Expressions using Different Classification Algorithms - A Comparative Analysis

Proceedings of the First Workshop on Computational Approaches to Compound Analysis (ComAComA 2014)

Contact Info

Product

Resources

About