USzeged: Identifying Verbal Multiword Expressions with POS Tagging
            and Parsing Techniques

Simkó, Katalin; Kovács, Viktória; Vincze, Veronika

doi:10.18653/v1/w17-1705

Cited by 10 publications

(10 citation statements)

References 6 publications

(6 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Another way to classify MWE identification approaches is based on whether the process of MWE prediction takes place before, during, or after (syntactic and/or semantic) parsing. The joint solution is typically considered as most promising in that it can potentially improve both MWE identification and parsing results (Constant and Nivre, 2016;Le Roux et al, 2014;Nasr et al, 2015;Simkó et al, 2018). On this scale, our method clearly fits into the family of post-processing approaches, since it requires the dependency trees on input.…”

Section: Related Workmentioning

confidence: 86%

A Neural Graph-based Approach to Verbal MWE Identification

Waszczuk

Ehren²,

Stodden

et al. 2019

Proceedings of the Joint Workshop on Multiword Expressions and WordNet (MWE-WN 2019)

View full text Add to dashboard Cite

We propose to tackle the problem of verbal multiword expression (VMWE) identification using a neural graph parsing-based approach. Our solution involves encoding VMWE annotations as labellings of dependency trees and, subsequently, applying a neural network to model the probabilities of different labellings. This strategy can be particularly effective when applied to discontinuous VMWEs and, thanks to dense, pre-trained word vector representations, VMWEs unseen during training. Evaluation of our approach on three PARSEME datasets (German, French, and Polish) shows that it allows to achieve performance on par with the previous state-ofthe-art (Al Saied et al., 2018).

show abstract

Section: Related Workmentioning

confidence: 86%

A Neural Graph-based Approach to Verbal MWE Identification

Waszczuk

Ehren²,

Stodden

et al. 2019

Proceedings of the Joint Workshop on Multiword Expressions and WordNet (MWE-WN 2019)

View full text Add to dashboard Cite

show abstract

“…In the PARSEME Shared Tasks, several machine learning-based methods competed on the four languages under investigation, among others. Some of them relied on parsing (Al Saied, Constant, and Candito 2017;Nerima, Foufi, and Wehrli 2017;Simkó, Kovács, and Vincze 2017;Waszczuk 2018), whereas others exploited sequence labeling using CRFs (Boroş et al 2017;Maldonado et al 2017;Moreau et al 2018) and neural networks (Klyueva, Doucet, and Straka 2017;Berk et al 2018;Boroş and Burtica 2018;Ehren, Lichte, and Samih 2018;Stodden, QasemiZadeh, and Kallmeyer 2018;Zampieri et al 2018).…”

Section: Methods For Identifying Lvcsmentioning

confidence: 99%

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

“…Similar to the phrase-structure case, Candito and Constant (2014) consider MWE identification as a side product of dependency parsing into joint representations. This parse-then-extract strategy is widely adopted (Vincze et al, 2013;Nasr et al, 2015;Simkó et al, 2017). Waszczuk et al (2019) introduce additional parameterized scoring functions for the arc labelers and use global decoding to produce consistent structures during arc-labeling steps once unlabeled dependency parse trees are predicted.…”

Section: Related Workmentioning

confidence: 99%

Extracting Headless MWEs from Dependency Parse Trees: Parsing, Tagging, and Joint Modeling Approaches

Shi

Lee

2020

Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

View full text Add to dashboard Cite

An interesting and frequent type of multiword expression (MWE) is the headless MWE, for which there are no true internal syntactic dominance relations; examples include many named entities ("Wells Fargo") and dates ("July 5, 2020") as well as certain productive constructions ("blow for blow", "day after day"). Despite their special status and prevalence, current dependency-annotation schemes require treating such flat structures as if they had internal syntactic heads, and most current parsers handle them in the same fashion as headed constructions. Meanwhile, outside the context of parsing, taggers are typically used for identifying MWEs, but taggers might benefit from structural information. We empirically compare these two common strategies-parsing and tagging-for predicting flat MWEs. Additionally, we propose an efficient joint decoding algorithm that combines scores from both strategies. Experimental results on the MWE-Aware English Dependency Corpus and on six non-English dependency treebanks with frequent flat structures show that: (1) tagging is more accurate than parsing for identifying flat-structure MWEs, (2) our joint decoder reconciles the two different views and, for non-BERT features, leads to higher accuracies, and (3) most of the gains result from feature sharing between the parsers and taggers.

show abstract

USzeged: Identifying Verbal Multiword Expressions with POS Tagging and Parsing Techniques

Cited by 10 publications

References 6 publications

A Neural Graph-based Approach to Verbal MWE Identification

A Neural Graph-based Approach to Verbal MWE Identification

Detecting light verb constructions across languages

Extracting Headless MWEs from Dependency Parse Trees: Parsing, Tagging, and Joint Modeling Approaches

Contact Info

Product

Resources

About