# Unified Representation for Non-compositional and Compositional Expressions

arXiv: https://arxiv.org/abs/2310.19127 · HTML: https://mlsanity.com/paper/2310.19127/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 55 references that are in the map.
- First posted on arXiv 29 Oct 2023.

## Builds on (most cited first, 23 of 23)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [Neural Machine Translation of Rare Words with Subword Units](https://mlsanity.com/paper/1508.07909/) (2015)
- [Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation](https://mlsanity.com/paper/1609.08144/) (2016)
- [MPNet: Masked and Permuted Pre-training for Language Understanding](https://mlsanity.com/paper/2004.09297/) (2020)
- [SpanBERT: Improving Pre-training by Representing and Predicting Spans](https://mlsanity.com/paper/1907.10529/) (2019)
- [AdapterFusion: Non-Destructive Task Composition for Transfer Learning](https://mlsanity.com/paper/2005.00247/) (2020)
- [MAD-X: An Adapter-Based Framework for Multi-Task Cross-Lingual Transfer](https://mlsanity.com/paper/2005.00052/) (2020)
- [AdapterHub: A Framework for Adapting Transformers](https://mlsanity.com/paper/2007.07779/) (2020)
- [PAWS: Paraphrase Adversaries from Word Scrambling](https://mlsanity.com/paper/1904.01130/) (2019)
- [Bidirectional Attention Flow for Machine Comprehension](https://mlsanity.com/paper/1611.01603/) (2016)
- [Dict-BERT: Enhancing Language Model Pre-training with Dictionary](https://mlsanity.com/paper/2110.06490/) (2021)
- [Investigating Robustness of Dialog Models to Popular Figurative Language Constructs](https://mlsanity.com/paper/2110.00687/) (2021)
- [Idiomatic Expression Identification using Semantic Compatibility](https://mlsanity.com/paper/2110.10064/) (2021)
- [Classifying Idiomatic and Literal Expressions Using Topic Models and Intensity of Emotions](https://mlsanity.com/paper/1802.09961/) (2018)
- [Adaptive Joint Learning of Compositional and Non-Compositional Phrase Embeddings](https://mlsanity.com/paper/1603.06067/) (2016)
- [Are Representations Built from the Ground Up? An Empirical Examination of Local Composition in Language Models](https://mlsanity.com/paper/2210.03575/) (2022)
- [MICE: Mining Idioms with Contextual Embeddings](https://mlsanity.com/paper/2008.05759/) (2020)
- [Idiomatic Expression Paraphrasing without Strong Supervision](https://mlsanity.com/paper/2112.08592/) (2021)

## Built on by (most cited first, 2 of 2)

- [Enhancing Idiomatic Representation in Multiple Languages via an Adaptive Contrastive Triplet Loss](https://mlsanity.com/paper/2406.15175/) (2024)
- [Investigating Idiomaticity in Word Representations](https://mlsanity.com/paper/2411.02610/) (2024)

## Abstract (arXiv)

Accurate processing of non-compositional language relies on generating good representations for such expressions. In this work, we study the representation of language non-compositionality by proposing a language model, PIER, that builds on BART and can create semantically meaningful and contextually appropriate representations for English potentially idiomatic expressions (PIEs). PIEs are characterized by their non-compositionality and contextual ambiguity in their literal and idiomatic interpretations. Via intrinsic evaluation on embedding quality and extrinsic evaluation on PIE processing and NLU tasks, we show that representations generated by PIER result in 33% higher homogeneity score for embedding clustering than BART, whereas 3.12% and 3.29% gains in accuracy and sequence accuracy for PIE sense classification and span detection compared to the state-of-the-art IE representation model, GIEA. These gains are achieved without sacrificing PIER's performance on NLU tasks (+/- 1% accuracy) compared to BART.