# Vector Representations of Idioms in Conversational Systems

arXiv: https://arxiv.org/abs/2205.03666 · HTML: https://mlsanity.com/paper/2205.03666/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 50 references that are in the map.
- First posted on arXiv 7 May 2022.

## Builds on (most cited first, 20 of 20)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [XLNet: Generalized Autoregressive Pretraining for Language Understanding](https://mlsanity.com/paper/1906.08237/) (2019)
- [ALBERT: A Lite BERT for Self-supervised Learning of Language Representations](https://mlsanity.com/paper/1909.11942/) (2019)
- [DialoGPT: Large-Scale Generative Pre-training for Conversational Response Generation](https://mlsanity.com/paper/1911.00536/) (2019)
- [Personalizing Dialogue Agents: I have a dog, do you have pets too?](https://mlsanity.com/paper/1801.07243/) (2018)
- [MultiWOZ -- A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modelling](https://mlsanity.com/paper/1810.00278/) (2018)
- [DailyDialog: A Manually Labelled Multi-turn Dialogue Dataset](https://mlsanity.com/paper/1710.03957/) (2017)
- [Recipes for building an open-domain chatbot](https://mlsanity.com/paper/2004.13637/) (2020)
- [Towards a Human-like Open-Domain Chatbot](https://mlsanity.com/paper/2001.09977/) (2020)
- [How NOT To Evaluate Your Dialogue System: An Empirical Study of Unsupervised Evaluation Metrics for Dialogue Response Generation](https://mlsanity.com/paper/1603.08023/) (2016)
- [The GEM Benchmark: Natural Language Generation, its Evaluation and Metrics](https://mlsanity.com/paper/2102.01672/) (2021)
- [Unifying Human and Statistical Evaluation for Natural Language Generation](https://mlsanity.com/paper/1904.02792/) (2019)
- [Investigating Robustness of Dialog Models to Popular Figurative Language Constructs](https://mlsanity.com/paper/2110.00687/) (2021)
- [Potential Idiomatic Expression (PIE)-English: Corpus for Classes of Idioms](https://mlsanity.com/paper/2105.03280/) (2021)
- [Smaaprat: DialoGPT for Natural Language Generation of Swedish Dialogue by Transfer Learning](https://mlsanity.com/paper/2110.06273/) (2021)
- [HaT5: Hate Language Identification using Text-to-Text Transfer Transformer](https://mlsanity.com/paper/2202.05690/) (2022)
- [ML_LTU at SemEval-2022 Task 4: T5 Towards Identifying Patronizing and Condescending Language](https://mlsanity.com/paper/2204.07432/) (2022)

## Built on by (most cited first, 4 of 4)

- [Enhancing Idiomatic Representation in Multiple Languages via an Adaptive Contrastive Triplet Loss](https://mlsanity.com/paper/2406.15175/) (2024)
- [T5 for Hate Speech, Augmented Data and Ensemble](https://mlsanity.com/paper/2210.05480/) (2022)
- [When Meaning Isn't Literal: Exploring Idiomatic Meaning Across Languages and Modalities](https://mlsanity.com/paper/2604.10787/) (2026)
- [Investigating Idiomaticity in Word Representations](https://mlsanity.com/paper/2411.02610/) (2024)

## Abstract (arXiv)

We demonstrate, in this study, that an open-domain conversational system trained on idioms or figurative language generates more fitting responses to prompts containing idioms. Idioms are part of everyday speech in many languages, across many cultures, but they pose a great challenge for many Natural Language Processing (NLP) systems that involve tasks such as Information Retrieval (IR) and Machine Translation (MT), besides conversational AI. We utilize the Potential Idiomatic Expression (PIE)-English idioms corpus for the two tasks that we investigate: classification and conversation generation. We achieve state-of-the-art (SoTA) result of 98% macro F1 score on the classification task by using the SoTA T5 model. We experiment with three instances of the SoTA dialogue model, Dialogue Generative Pre-trained Transformer (DialoGPT), for conversation generation. Their performances are evaluated using the automatic metric perplexity and human evaluation. The results show that the model trained on the idiom corpus generates more fitting responses to prompts containing idioms 71.9% of the time, compared to a similar model not trained on the idioms corpus. We contribute the model checkpoint/demo and code on the HuggingFace hub for public access.