Challenge: Verbal multiword expressions (VMWEs) are difficult for machine translation because their meanings are often not recoverable from their component words.
Approach: They analyze the impact of verbal idioms, verb-particle constructions, and light verb constructions on machine translation quality from English to multiple languages.
Outcome: The proposed system improves translation quality by focusing on verb idioms, verb-particle constructions and light verb constructions.

Similar Papers

A Deep Analysis of the Impact of Multiword Expressions and Named Entities on Chinese-English Machine Translations (2024.findings-emnlp)

Copied to clipboard

Challenge: a study on the impact of multiword expressions and multiword named entities (NEs) on the performance of Chinese-English machine translation systems is presented.
Approach: They propose to use Chinese multiword expressions and multiword named entities (NEs) to evaluate machine translation performance.
Outcome: The proposed methods show that Chinese-English machine translation systems perform significantly worse on Chinese sentences with most kinds of MWEs and NEs.
Construction of Large-scale English Verbal Multiword Expression Annotated Corpus (L18-1)

Copied to clipboard

Challenge: In this paper, we focus on verbal MWEs, whose accurate recognition is challenging because they could be discontinuous.
Approach: They conduct large-scale annotations of VMWEs on the Wall Street Journal portion of Ontonotes . they first construct a VMwe dictionary based on the english-language Wiktionary .
Outcome: The proposed resource annotates 7,833 VMWE instances belonging to various categories . the authors hope the results will help to develop models for MWE recognition and dependency parsing .
Verbal Multiword Expression Identification: Do We Need a Sledgehammer to Crack a Nut? (2020.coling-main)

Copied to clipboard

Challenge: Multiword expressions (MWEs) are word combinations idiosyncratic with respect to syntax or semantics.
Approach: They propose to use a language-independent system to identify previously seen VMWEs by combining filters to obtain the best averaged F-score over 11 languages and the best score for both seen and unseen VMwes.
Outcome: The proposed system obtains the best averaged F-score over 11 languages and even the best score for both seen and unseen VMWEs due to the high proportion of seen VMwes in texts.
CoAM: Corpus of All-Type Multiword Expressions (2025.acl-long)

Copied to clipboard

Challenge: Existing datasets for multiword expressions are inconsistently annotated, limited to a single type of MWE, or limited in size.
Approach: They propose to use a new interface to generate MWE annotations for the first time in a dataset of MWE identification.
Outcome: The proposed model outperforms existing models on the DiMSUM dataset.
Benchmarking the Performance of Machine Translation Evaluation Metrics with Chinese Multiword Expressions (2024.lrec-main)

Copied to clipboard

Challenge: Multiword Expressions (MWEs) are hard nuts for many natural language processing tasks.
Approach: They annotate 28 types of Chinese MWEs and then examine 31 MTE metrics on groups of sentences containing different MWE.
Outcome: The results show that MT systems and MTE metrics still suffer from MWEs .
If you’ve seen some, you’ve seen them all: Identifying variants of multiword expressions (C18-1)

Copied to clipboard

Challenge: Multiword expressions (VMWEs) show idiosyncratic variability, which is challenging for NLP applications.
Approach: They propose to use a model to identify variants of previously seen VMWEs by comparing VMWAs with morpho-syntactic variations.
Outcome: The proposed approach outperforms a baseline by 4 percent points of F-measure on a French corpus.
Dedicated Language Resources for Interdisciplinary Research on Multiword Expressions: Best Thing since Sliced Bread (2020.lrec-1)

Copied to clipboard

Challenge: Multiword expressions are challenging for disciplines like NLP, psycholinguistics and second language acquisition due to their more or less fixed character.
Approach: They propose to develop tools and language resources that are crucial for multifaceted research.
Outcome: The proposed tools and language resources are crucial for this kind of multifaceted research.
Towards a Variability Measure for Multiword Expressions (N18-2)

Copied to clipboard

Challenge: Multiword expressions (MWEs) are groups of words whose meaning does not derive from the meaning of their components and from their syntactic structure in a regular way.
Approach: They propose to use a language-independent measure of variability dedicated to verbal MWEs based on syntactic and discontinuity-related clues to assess its relevance with respect to a linguistic benchmark.
Outcome: The proposed measure is useful for VMWE classification and variant identification on a French corpus.
Cross-type French Multiword Expression Identification with Pre-trained Masked Language Models (2024.lrec-main)

Copied to clipboard

Challenge: Multiword expressions (MWEs) have linguistic features that distinguish them from regular word groupings.
Approach: They propose a combination of two systems that learn verbal multiword expressions and non-verbal MWEs to improve performance on a cross-type dataset .
Outcome: The proposed system improves the F1 score on a french treebank with VMWEs and nVMWES training data.
A Large Automatically-Acquired All-Words List of Multiword Expressions Scored for Compositionality (L18-1)

Copied to clipboard

Challenge: Existing literature on semantically idiosyncratic multiword expressions is limited to English . idiomatic expressions are phraseological units consisting of more than one lexeme and exhibit some kind of idiom.
Approach: They propose to make available a large automatically-acquired all-words list of English multiword expressions scored for compositionality.
Outcome: The proposed list improves the BLEU scores of the English multiword expressions.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations