# Learning Class-Transductive Intent Representations for Zero-shot Intent Detection

arXiv: https://arxiv.org/abs/2012.01721 · HTML: https://mlsanity.com/paper/2012.01721/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Dec 2020.

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

- [A Simple Meta-learning Paradigm for Zero-shot Intent Classification with Mixture Attention Mechanism](https://mlsanity.com/paper/2206.02179/) (2022)
- [A Survey of Ontology Expansion for Conversational Understanding](https://mlsanity.com/paper/2410.15019/) (2024)
- [Template-based Approach to Zero-shot Intent Recognition](https://mlsanity.com/paper/2206.10914/) (2022)
- [Liberating Seen Classes: Boosting Few-Shot and Zero-Shot Text Classification via Anchor Generation and Classification Reframing](https://mlsanity.com/paper/2405.03565/) (2024)

## Abstract (arXiv)

Zero-shot intent detection (ZSID) aims to deal with the continuously emerging intents without annotated training data. However, existing ZSID systems suffer from two limitations: 1) They are not good at modeling the relationship between seen and unseen intents. 2) They cannot effectively recognize unseen intents under the generalized intent detection (GZSID) setting. A critical problem behind these limitations is that the representations of unseen intents cannot be learned in the training stage. To address this problem, we propose a novel framework that utilizes unseen class labels to learn Class-Transductive Intent Representations (CTIR). Specifically, we allow the model to predict unseen intents during training, with the corresponding label names serving as input utterances. On this basis, we introduce a multi-task learning objective, which encourages the model to learn the distinctions among intents, and a similarity scorer, which estimates the connections among intents more accurately. CTIR is easy to implement and can be integrated with existing methods. Experiments on two real-world datasets show that CTIR brings considerable improvement to the baseline systems.