Romanian Multiword Expression Detection Using Multilingual Adversarial Training and Lateral Inhibition
Multiword expressions are a key ingredient for developing large-scale and linguistically sound natural language processing technology. This paper describes our improvements in automatically identifying Romanian multiword expressions on the corpus released for the PARSEME v1.2 shared task. Our approach assumes a multilingual perspective based on the recently introduced lateral inhibition layer and adversarial training to boost the performance of the employed multilingual language models. With the help of these two methods, we improve the F1-score of XLM-RoBERTa by approximately 2.7% on unseen multiword expressions, the main task of the PARSEME 1.2 edition. In addition, our results can be considered SOTA performance, as they outperform the previous results on Romanian obtained by the participants in this competition.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
A Romanian Treebank Annotated with Verbal Multiword Expressions
In this paper we present a new version of the Romanian journalistic treebank annotated with verbal multiword expressions of four types: idioms, light verb constructions, reflexive verbs and inherently adpositional verbs,…
The Romanian Corpus Annotated with Verbal Multiword Expressions
This paper reports on the Romanian journalistic corpus annotated with verbal multiword expressions following the PARSEME guidelines. The corpus is sentence split, tokenized, part-of-speech tagged, lemmatized, syntactical…
DiversitySentenceHear about Verbal Multiword Expressions in the Bulgarian and the Romanian Wordnets Straight from the Horse's Mouth
In this paper we focus on verbal multiword expressions (VMWEs) in Bulgarian and Romanian as reflected in the wordnets of the two languages. The annotation of VMWEs relies on the classification defined within the PARSEME …
ClassificationGeneral ClassificationIt Takes Two to Tango – Towards a Multilingual MWE Resource
Mature wordnets offer the opportunity of digging out interesting linguistic information otherwise not explicitly marked in the network. The focus in this paper is on the ways the results already obtained at two levels, d…
Vocal Bursts Valence PredictionLeaving No Stone Unturned When Identifying and Classifying Verbal Multiword Expressions in the Romanian Wordnet
We present here the enhancement of the Romanian wordnet with a new type of information, very useful in language processing, namely types of verbal multi-word expressions. All verb literals made of two or more words are a…