---
title: "Open Intent Extraction from Natural Language Interactions (Extended Abstract)"
authors:
  - "Nikhita Vedula"
  - "Nedim Lipka"
  - "Pranav Maneriker"
  - "Srinivasan Parthasarathy"
doi: "10.24963/ijcai.2021/663"
url: "https://ijcai.org/proceedings/2021/663"
pdf: "https://ijcai.org/proceedings/2021/0663.pdf"
venue: "Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence"
year: 2021
pages: "4844-4848"
track: "Sister Conferences Best Papers"
keywords:
  - "Natural Language Processing: Natural Language Semantics"
  - "Natural Language Processing: NLP Applications and Tools"
  - "Natural Language Processing: Natural Language Processing"
  - "Machine Learning: Deep Learning"
---

# Open Intent Extraction from Natural Language Interactions (Extended Abstract)

Nikhita Vedula, Nedim Lipka, Pranav Maneriker, Srinivasan Parthasarathy

*Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence*, pages 4844-4848. DOI: [10.24963/ijcai.2021/663](https://doi.org/10.24963/ijcai.2021/663)

## Abstract

Accurately discovering user intents from their written or spoken language plays a critical role in natural language understanding and automated dialog response. Most existing research models this as a classification task with a single intent label per utterance. Going beyond this formulation, we define and investigate a new problem of open intent discovery. It involves discovering one or more generic intent types from text utterances, that may not have been encountered during training. We propose a novel, domain-agnostic approach, OPINE, which formulates the problem as a sequence tagging task in an open-world setting. It employs a CRF on top of a bidirectional LSTM to extract intents in a consistent format, subject to constraints among intent tag labels. We apply multi-headed self-attention and adversarial training to effectively learn dependencies between distant words, and robustly adapt our model across varying domains. We also curate and release an intent-annotated dataset of 25K real-life utterances spanning diverse domains. Extensive experiments show that OPINE outperforms state-of-art baselines by 5-15% F1 score.