Semi-Compositional Noun+Verb Constructions: Theoretical Questions and Computational Linguistic Analyses

Vincze, Veronika

doi:10.14232/phd.1430

Cited by 6 publications

(21 citation statements)

References 65 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Multiword expressions can be divided into several groups (Vincze, 2011;, based on the parts of speech of their components or based on their syntactic and semantic behaviour. In this chapter, we present a classification of MWEs based on their syntactic behaviour.…”

Section: Chapter 2 the Characteristics Of Multiword Expressionsmentioning

confidence: 99%

“…Light verb constructions consist of a nominal and a verbal component, where the noun is usually taken in one of its literal senses, but the verb usually loses its original sense to some extent (Stevenson et al, 2004;Vincze, 2011). Some examples are offered here: take a decision -döntést hoz, make a contract -szerződést köt.…”

Section: Light Verb Constructionsmentioning

confidence: 99%

“…the verb has lost its meaning to some extent and the noun is used in one of its original senses, but the verb functions as the syntactic head (the whole construction fulfills the role of a verb in the clause) (Vincze, 2011).…”

Section: The Characteristics Of Light Verb Constructionsmentioning

confidence: 99%

“…The presentation of the types of light verb constructions is based on Vincze (2011) and Vincze et al (2013b). The papers present a test battery which is able to differentiate among different types of verb + noun combinations: productive constructions, light verb constructions and idioms.…”

Section: Types Of Light Verb Constructionsmentioning

confidence: 99%

“…Productive-like LVCs behave rather like productive constructions, whereas idiom-like constructions are more similar to idioms. Still, there is no sharp or distinct boundary in between the groups since belonging to a (sub)group is not determined by a dichotomy of the either-or type: the place of the construction on a scale is rather a question of degree and scalability, which is true for English and Hungarian as well (Vincze, 2011). Table 2.1 states the applicability of the tests for each type and these tests were used in annotating the corpora presented in Sections 3.…”

Section: Types Of Light Verb Constructionsmentioning

confidence: 99%

See 4 more Smart Citations

Detecting Multiword Expressions and Named Entities in Natural Language Texts

Nagy

View full text Add to dashboard Cite

Section: Chapter 2 the Characteristics Of Multiword Expressionsmentioning

confidence: 99%

Section: Light Verb Constructionsmentioning

confidence: 99%

Section: The Characteristics Of Light Verb Constructionsmentioning

confidence: 99%

Section: Types Of Light Verb Constructionsmentioning

confidence: 99%

Section: Types Of Light Verb Constructionsmentioning

confidence: 99%

See 3 more Smart Citations

Detecting Multiword Expressions and Named Entities in Natural Language Texts

Nagy

View full text Add to dashboard Cite

Detecting light verb constructions across languages

Nagy¹,

Rácz

Vincze

2019

Nat. Lang. Eng.

Self Cite

View full text Add to dashboard Cite

Light verb constructions (LVCs) are verb and noun combinations in which the verb has lost its meaning to some degree and the noun is used in one of its original senses, typically denoting an event or an action. They exhibit special linguistic features, especially when regarded in a multilingual context. In this paper, we focus on the automatic detection of LVCs in raw text in four different languages, namely, English, German, Spanish, and Hungarian. First, we analyze the characteristics of LVCs from a linguistic point of view based on parallel corpus data. Then, we provide a standardized (i.e., language-independent) representation of LVCs that can be used in machine learning experiments. After, we experiment on identifying LVCs in different languages: we exploit language adaptation techniques which demonstrate that data from an additional language can be successfully employed in improving the performance of supervised LVC detection for a given language. As there are several annotated corpora from several domains in the case of English and Hungarian, we also investigate the effect of simple domain adaptation techniques to reduce the gap between domains. Furthermore, we combine domain adaptation techniques with language adaptation techniques for these two languages. Our results show that both out-domain and additional language data can improve performance. We believe that our language adaptation method may have practical implications in several fields of natural language processing, especially in machine translation.

show abstract

Learning to detect english and hungarian light verb constructions

Vincze

Nagy

Zsibrita

2013

ACM Trans. Speech Lang. Process.

Self Cite

View full text Add to dashboard Cite

Light verb constructions consist of a verbal and a nominal component, where the noun preserves its original meaning while the verb has lost it (to some degree). They are syntactically flexible and their meaning can only be partially computed on the basis of the meaning of their parts, thus they require special treatment in natural language processing. For this purpose, the first step is to identify light verb constructions.In this study, we present our conditional random fields-based tool-called FXTagger-for identifying light verb constructions. The flexibility of the tool is demonstrated on two, typologically different, languages, namely, English and Hungarian. As earlier studies labeled different linguistic phenomena as light verb constructions, we first present a linguistics-based classification of light verb constructions and then show that FXTagger is able to identify different classes of light verb constructions in both languages.Different types of texts may contain different types of light verb constructions; moreover, the frequency of light verb constructions may differ from domain to domain. Hence we focus on the portability of models trained on different corpora, and we also investigate the effect of simple domain adaptation techniques to reduce the gap between the domains. Our results show that in spite of domain specificities, out-domain data can also contribute to the successful LVC detection in all domains.

show abstract

Semi-Compositional Noun+Verb Constructions: Theoretical Questions and Computational Linguistic Analyses

Cited by 6 publications

References 65 publications

Detecting Multiword Expressions and Named Entities in Natural Language Texts

Detecting Multiword Expressions and Named Entities in Natural Language Texts

Detecting light verb constructions across languages

Learning to detect english and hungarian light verb constructions

Contact Info

Product

Resources

About