Papers with MWEs
A Canonical Form for Flexible Multiword Expressions (2024.lrec-main)
Copied to clipboard
| Challenge: | Until now, no well-defined canonical form exists for MWEs in Dutch . traditional dictionaries do not use a canonically form but an example to illustrate MWE . |
| Approach: | They propose a canonical form for Multiword Expressions in the Dutch language . it introduces a lexical resource with more than 11k Dutch multiword expressions in canonically form . |
| Outcome: | The proposed canonical form can be enriched with annotations to describe properties of the MWE and its components. |
Vector Spaces for Quantifying Disparity of Multiword Expressions in Annotated Text (2024.acl-srw)
Copied to clipboard
| Challenge: | We show that multiword expressions are a good study for linguistic diversity due to theiridiosyncratic nature. |
| Approach: | They train static MWE-aware word embeddings for verbal MWEs in 14 languages . they find that the disparity measure aggregatingthem at a global scale correlates with the number of types . |
| Outcome: | The proposed method is based on a set of vector spaces for VMWEs in 14 languages. |
Identification of Multiword Expressions in Tweets for Hate Speech Detection (2022.lrec-1)
Copied to clipboard
| Challenge: | Multiword expression (MWE) identification in tweets is a complex task due to the complex linguistic nature of MWEs combined with the non-standard language use in social networks. |
| Approach: | They propose a new architecture for incorporating multiword expression features into tweets to improve their accuracy. |
| Outcome: | The proposed system outperforms existing systems on the hate speech detection task on English Twitter. |
Latent semantic network induction in the context of linked example senses (D19-55)
Copied to clipboard
| Challenge: | Using the Princeton WordNet, we construct a network using the entirety of Wiktionary. |
| Approach: | They propose to use Wiktionary to construct a wordnet using the entirety of the open-source dictionary. |
| Outcome: | The proposed network induction process is similar to the Princeton WordNet, but with a more data-driven approach. |
Unsupervised Multilingual Word Embeddings (D18-1)
Copied to clipboard
| Challenge: | Prior art for learning UMWEs relies on a number of independently trained UBWEs to obtain multilingual embeddings. |
| Approach: | They propose a fully unsupervised framework that exploits the relations between all language pairs to learn multilingual embeddings without cross-lingual supervision. |
| Outcome: | The proposed framework outperforms supervised approaches on multilingual word translation and cross-lingual word similarity and beats a number of other approaches trained with cross-linguistic resources. |
LLM-based Literal Example Generation for Japanese Multiword Expressions (2026.acl-srw)
Copied to clipboard
| Challenge: | Existing work on Japanese multiword expressions has focused on detecting idiomatic usages in context, leaving literal readings underrepresented. |
| Approach: | They propose to use corpus non-literal usages as contrastive cues for controlled prompting . they compare their results to a test that compares model predictions with human judgments . |
| Outcome: | The proposed model provides more accurate literal examples than prompts that include no hints or literal information. |
Anchor-based Bilingual Word Embeddings for Low-Resource Languages (2021.acl-short)
Copied to clipboard
| Challenge: | Existing approaches to build monolingual word embeddings rely on a cheap bilingual signal and monolingual data. |
| Approach: | They propose a method where the vector space of the high resource source language is used as a starting point for training an embedding space for the low resource target language. |
| Outcome: | The proposed approach improves bilingual lexicon induction performance and target language MWE quality. |
A Hybrid Approach for Automatic Extraction of Bilingual Multiword Expressions from Parallel Corpora (L18-1)
Copied to clipboard
| Challenge: | Specific-domain bilingual lexicons are composed of MultiWord Expressions (MWEs) the manual construction of MWEs bilingual dictionaries is costly and time-consuming. |
| Approach: | They propose to use word alignment approaches to automatically construct bilingual lexicons of MWEs from parallel corpora by formalizing the alignment process as an integer linear programming problem. |
| Outcome: | The proposed approach extracts and aligns multiword expressions from parallel corpora and then filters them using linguistic patterns to build bilingual lexicons. |
A Hybrid Approach to Aspect Based Sentiment Analysis Using Transfer Learning (2024.lrec-main)
Copied to clipboard
| Challenge: | Aspect-Based Sentiment Analysis (ABSA) aims to identify terms or multiword expressions (MWEs) on which sentiments are expressed and the sentiment polarities associated with them. |
| Approach: | They propose a hybrid approach to Aspect-Based Sentiment Analysis using transfer learning . they exploit the strengths of large language models and traditional syntactic dependencies . |
| Outcome: | The proposed method exploits the strengths of large language models and traditional syntactic dependencies. |
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. |
Dictionary-Aided Translation for Handling Multi-Word Expressions in Low-Resource Languages (2024.findings-acl)
Copied to clipboard
| Challenge: | Multi-word expressions (MWEs) are a challenging task in natural language processing . they are defined as combinations of at least two words with distinct lexical, morphological, syntactic, semantic or statistical characteristics. |
| Approach: | They propose a method leveraging an available out-of-context lexicon to improve translations . they propose to use a dictionary-aided translation to better translate multi-word expressions based on human annotations. |
| Outcome: | The proposed method improves translations comparable to those of a human speaker. |
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 . |
Attention on Multiword Expressions: A Multilingual Study of BERT-based Models with Regard to Idiomaticity and Microsyntax (2025.findings-naacl)
Copied to clipboard
| Challenge: | Specifically, models fine-tuned on semantic tasks tend to distribute attention to idiomatic expressions more evenly across layers. |
| Approach: | They analyze attention patterns of encoder-only models towards two distinct types of Multiword Expressions (MWEs) idioms present challenges in semantic non-compositionality, while MSUs demonstrate unconventional syntactic behavior that does not conform to standard grammatical categorizations. |
| Outcome: | The proposed models show that fine-tuned models allocate attention to idiomatic expressions more evenly across layers. |
Verbal Multiword Expressions for Identification of Metaphor (2020.acl-main)
Copied to clipboard
| Challenge: | Metaphor is a linguistic device in which a concept is expressed by mentioning another . Verbal MWEs are examples of non-literal language in which multiple words form a single unit of meaning. |
| Approach: | They propose to analyze the interplay between metaphor and multiword expressions processing by informing the model of the presence of MWEs. |
| Outcome: | The proposed architecture reach state-of-the-art on two established metaphor datasets. |
Bridging the Gap: Attending to Discontinuity in Identification of Multiword Expressions (N19-1)
Copied to clipboard
| Challenge: | Existing approaches to identify discontinuous multiword expressions are limited in dealing with discontinuous occurrences. |
| Approach: | They propose a method to tag Multiword Expressions using a language-independent deep learning architecture to target discontinuity. |
| Outcome: | The proposed model outperforms baseline models on a multilingual dataset and scores higher than baseline models. |
Unsupervised Paraphrasing of Multiword Expressions (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for paraphrasing multiword expressions in context are unsupervised . multiwords are notoriously difficult to model because the meaning of the whole can diverge substantially from that of the component words. |
| Approach: | They propose an unsupervised approach to paraphrasing multiword expressions in context using monolingual corpus data and pre-trained language models. |
| Outcome: | The proposed method outperforms all unsupervised systems and rivals supervised systems on the SemEval 2022 idiomatic text similarity task. |
AStitchInLanguageModels: Dataset and Methods for the Exploration of Idiomaticity in Pre-Trained Language Models (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Existing datasets are limited to providing the degree of idiomaticity of expressions along with the literal and, where applicable, (a single) non-literal interpretation of MWEs. |
| Approach: | They propose to use a dataset to test the effectiveness of a language model in generating representations of sentences containing idioms. |
| Outcome: | The proposed model performs reasonably well on the one-shot and few-shot scenarios, but there is scope for improvement in the zero-shot scenario. |
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. |
An Unsupervised Method for Learning Representations of Multi-word Expressions for Semantic Classification (2020.coling-main)
Copied to clipboard
| Challenge: | Existing methods for learning multi-word expressions have language sparsity and are not supervised. |
| Approach: | They propose an unsupervised approach to learning a compositional representation function for multi-word expressions . they use a Tratz dataset to train the composition function on the word-semantic relation . |
| Outcome: | The proposed method outperforms the previous state-of-the-art method on the Tratz dataset with an F1 score of 50.4%. |
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. |
Pre-tokenization of Multi-word Expressions in Cross-lingual Word Embeddings (2020.emnlp-main)
Copied to clipboard
| Challenge: | Multi-Word Expressions (MWEs) are common in every language, but they are not translated by cross-lingual word embeddings. |
| Approach: | They propose a method for word translation of Multi-Word Expressions (MWEs) they compile lists of MWEs in each language and tokenize them as single tokens before training word embeddings. |
| Outcome: | The proposed method can translate multi-word expressions to and from English in 10 languages. |
MultiMWE: Building a Multi-lingual Multi-Word Expression (MWE) Parallel Corpora (2020.lrec-1)
Copied to clipboard
| Challenge: | Existing bilingual or multi-lingual MWE corpora are limited for multilingual use . only 871 pairs of English-German MWEs are available for research . |
| Approach: | They present a collection of bilingual and multi-lingual MWEs extracted from parallel corpora. |
| Outcome: | The available bilingual or multi-lingual MWE corpus is very limited . the collection is a small collection of 871 pairs of English-German MWEs . |
Graph-Assisted Culturally Adaptable Idiomatic Translation for Indic languages (2025.findings-acl)
Copied to clipboard
| Challenge: | a single source idiom can have multiple target-language equivalents depending on cultural references and contextual variations. |
| Approach: | They propose an adaptive graph neural network-based method that learns intricate mappings between idiomatic expressions and generalizes to both seen and unseen nodes during training. |
| Outcome: | The proposed method improves translation quality even in resource-constrained settings, facilitating improved idiomatic translation in smaller models. |
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. |
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 . |
Konbitzul: an MWE-specific database for Spanish-Basque (L18-1)
Copied to clipboard
| Challenge: | Multiword Expressions (MWEs) are combinations of words which express a single meaning. |
| Approach: | They present an online database of verb+noun MWEs in Spanish and Basque. |
| Outcome: | The proposed database helps to identify occurrences of MWEs in multiple morphosyntactic variants and improve translation quality in rule-based MT. |
For a Fistful of Puns: Evaluating a Puns in Multiword Expressions Identification Algorithm Without Dedicated Dataset (2025.findings-emnlp)
Copied to clipboard
| Challenge: | a recent study has shown that multiword expressions and wordplays impact their performance and are idiosyncratic and pervasive across languages. |
| Approach: | They propose an alignment-based PMWE identification and tagging algorithm to identify different types of PMWEs. |
| Outcome: | The proposed algorithm can identify different types of PMWEs and perform a snowclone detection task in English. |
Multiword Expression aware Neural Machine Translation (2020.lrec-1)
Copied to clipboard
| Challenge: | Multiword Expressions (MWEs) are a pervasive phenomenon in all natural languages and challenge NLP applications because of their unpredictable morpho-syntactic and lexico--semantic behaviour. |
| Approach: | They propose to use linguistic resources to improve MWE translation and MWE generation by up to 5.09 BLEU points on MWE test sets. |
| Outcome: | The proposed annotation and data augmentation improve translation quality and increase performance by up to 5.09 BLEU points on MWE test sets. |
Rigor Mortis: Annotating MWEs with a Gamified Platform (2020.lrec-1)
Copied to clipboard
| Challenge: | gamification of the platform should be improved, in order to attract and retain more players. |
| Approach: | They propose to use a gamified crowdsourcing platform to evaluate the intuition of speakers and then train them to annotate multi-word expressions in French corpora. |
| Outcome: | The proposed platform evaluates the speakers' intuition and trains them to annotate multi-word expressions in French corpora. |
Detecting Multiword Expression Type Helps Lexical Complexity Assessment (2020.lrec-1)
Copied to clipboard
| Challenge: | Multiword expressions (MWEs) represent lexemes that should be treated as single lexical units due to their idiosyncratic nature. |
| Approach: | They re-annotate a complex word identification shared task 2018 dataset . they find that a lexical complexity assessment system benefits from the information . |
| Outcome: | The proposed dataset provides valuable information for the text simplification community. |
Training on Lexical Resources (2022.lrec-1)
Copied to clipboard
| Challenge: | In this paper, we fine-tune pretrained deep nets such as BERT and ERNIE . at inference time, these nets can be used to distinguish synonyms from antonyms . |
| Approach: | They propose to use lexical resources to fine-tune pretrained deep nets such as BERT and ERNIE to distinguish synonyms from antonyms. |
| Outcome: | The proposed method can be applied to multiword expressions, out of vocabulary words, morphological variants and more. |
Extracting Headless MWEs from Dependency Parse Trees: Parsing, Tagging, and Joint Modeling Approaches (2020.acl-main)
Copied to clipboard
| Challenge: | Headless multi-word expressions are frequent in natural language but lack internal syntactic dominance relations. |
| Approach: | They propose an efficient joint decoding algorithm that combines scores from both strategies. |
| Outcome: | The proposed algorithm combines scores from parsing and tagging for predicting flat MWEs . the proposed algorithm is more accurate than parse and more efficient for non-BERT features . |
MWE-Finder: A Demonstration (2024.lrec-main)
Copied to clipboard
| Challenge: | MWE Finder is an application to search for flexible multiword expressions in text corpora. |
| Approach: | They introduce and demonstrate an application to search for flexible multiword expressions in Dutch text corpora. |
| Outcome: | The proposed system can find flexible multiword expressions in large text corpus faster and more reliable than other search applications. |
Lemmatization of Polish Multi-word Expressions (2025.emnlp-main)
Copied to clipboard
| Challenge: | PolEval task is complicated by linguistic irregularities and historical factors. |
| Approach: | They propose to use fine-tuned plT5 and mT5 models to improve lemmatization of multi-word expressions and proper names in Polish instead of rule-based methods. |
| Outcome: | The proposed model achieved 86.23% AccCS, 89.43% accCI and 88.79% on a gold-standard dataset derived from Wikipedia . |
CoAM: Corpus of All-Type Multiword Expressions (2025.acl-long)
Copied to clipboard
Yusuke Ide, Joshua Tanner, Adam Nohejl, Jacob Hoffman, Justin Vasselli, Hidetaka Kamigaito, Taro Watanabe
| 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. |
Textual Coverage of Eventive Entries in Lexical Semantic Resources (2024.lrec-main)
Copied to clipboard
| Challenge: | Several English, German, Spanish and Czech lexical semantic resources (which, for the most part, focus on verbs and predicates) have been selected for this experiment. |
| Approach: | They propose to quantify coverage gaps in lexical semantic resources when applied to running texts taken from the internet. |
| Outcome: | The proposed resources cover eventive entries (verbs, predicates, etc.) of well-known lexical semantic resources when applied to running texts taken from the internet. |