# Idiomatic Expression Identification using Semantic Compatibility

arXiv: https://arxiv.org/abs/2110.10064 · HTML: https://mlsanity.com/paper/2110.10064/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 79 references that are in the map.
- First posted on arXiv 19 Oct 2021.

## Builds on (most cited first, 9 of 9)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Bidirectional LSTM-CRF Models for Sequence Tagging](https://mlsanity.com/paper/1508.01991/) (2015)
- [Bidirectional Attention Flow for Machine Comprehension](https://mlsanity.com/paper/1611.01603/) (2016)
- [Highway Networks](https://mlsanity.com/paper/1505.00387/) (2015)
- [Encode, Tag, Realize: High-Precision Text Editing](https://mlsanity.com/paper/1909.01187/) (2019)
- [EditNTS: An Neural Programmer-Interpreter Model for Sentence Simplification through Explicit Editing](https://mlsanity.com/paper/1906.08104/) (2019)
- [Examining the Tip of the Iceberg: A Data Set for Idiom Translation](https://mlsanity.com/paper/1802.04681/) (2018)
- [Classifying Idiomatic and Literal Expressions Using Topic Models and Intensity of Emotions](https://mlsanity.com/paper/1802.09961/) (2018)
- [Geometry of Compositionality](https://mlsanity.com/paper/1611.09799/) (2016)

## Built on by (most cited first, 19 of 19)

- [SemEval-2022 Task 2: Multilingual Idiomaticity Detection and Sentence Embedding](https://mlsanity.com/paper/2204.10050/) (2022)
- [Sign of the Times: Evaluating the use of Large Language Models for Idiomaticity Detection](https://mlsanity.com/paper/2405.09279/) (2024)
- [Rolling the DICE on Idiomaticity: How LLMs Fail to Grasp Context](https://mlsanity.com/paper/2410.16069/) (2024)
- [Semantics of Multiword Expressions in Transformer-Based Models: A Survey](https://mlsanity.com/paper/2401.15393/) (2024)
- [Idiomatic Expression Paraphrasing without Strong Supervision](https://mlsanity.com/paper/2112.08592/) (2021)
- [Constructions are Revealed in Word Distributions](https://mlsanity.com/paper/2503.06048/) (2025)
- [Getting BART to Ride the Idiomatic Train: Learning to Represent Idiomatic Expressions](https://mlsanity.com/paper/2207.03679/) (2022)
- [HIT at SemEval-2022 Task 2: Pre-trained Language Model for Idioms Detection](https://mlsanity.com/paper/2204.06145/) (2022)
- [Multilingual Multi-Figurative Language Detection](https://mlsanity.com/paper/2306.00121/) (2023)
- [Unified Representation for Non-compositional and Compositional Expressions](https://mlsanity.com/paper/2310.19127/) (2023)
- [NLP Datasets for Idiom and Figurative Language Tasks](https://mlsanity.com/paper/2511.16345/) (2025)
- [IEKG: A Commonsense Knowledge Graph for Idiomatic Expressions](https://mlsanity.com/paper/2312.06053/) (2023)
- [Investigating Idiomaticity in Word Representations](https://mlsanity.com/paper/2411.02610/) (2024)
- [MetaphorShare: A Dynamic Collaborative Repository of Open Metaphor Datasets](https://mlsanity.com/paper/2411.18260/) (2024)
- [HYU at SemEval-2022 Task 2: Effective Idiomaticity Detection with Consideration at Different Levels of Contextualization](https://mlsanity.com/paper/2206.11854/) (2022)
- [Detecting Idiomatic Multiword Expressions in Clinical Terminology using Definition-Based Representation Learning](https://mlsanity.com/paper/2305.06801/) (2023)
- [Attention on Multiword Expressions: A Multilingual Study of BERT-based Models with Regard to Idiomaticity and Microsyntax](https://mlsanity.com/paper/2505.06062/) (2025)
- [Span Modeling for Idiomaticity and Figurative Language Detection with Span Contrastive Loss](https://mlsanity.com/paper/2603.22799/) (2026)
- [IdioLink: Retrieving Meaning Beyond Words Across Idiomatic and Literal Expressions](https://mlsanity.com/paper/2605.22247/) (2026)

## Abstract (arXiv)

Idiomatic expressions are an integral part of natural language and constantly being added to a language. Owing to their non-compositionality and their ability to take on a figurative or literal meaning depending on the sentential context, they have been a classical challenge for NLP systems. To address this challenge, we study the task of detecting whether a sentence has an idiomatic expression and localizing it. Prior art for this task had studied specific classes of idiomatic expressions offering limited views of their generalizability to new idioms. We propose a multi-stage neural architecture with the attention flow mechanism for identifying these expressions. The network effectively fuses contextual and lexical information at different levels using word and sub-word representations. Empirical evaluations on three of the largest benchmark datasets with idiomatic expressions of varied syntactic patterns and degrees of non-compositionality show that our proposed model achieves new state-of-the-art results. A salient feature of the model is its ability to identify idioms unseen during training with gains from 1.4% to 30.8% over competitive baselines on the largest dataset.