Dialog Intent Induction with Deep Multi-View Clustering

  title={Dialog Intent Induction with Deep Multi-View Clustering},
  author={Hugh Perkins and Yi Yang},
We introduce the dialog intent induction task and present a novel deep multi-view clustering approach to tackle the problem. Dialog intent induction aims at discovering user intents from user query utterances in human-human conversations such as dialogs between customer support agents and customers. Motivated by the intuition that a dialog intent is not only expressed in the user query utterance but also captured in the rest of the dialog, we split a conversation into two independent views and… Expand
Rationalizing Text Matching: Learning Sparse Alignments via Optimal Transport
This work introduces novel constrained variants of the OT problem that result in highly sparse alignments with controllable sparsity and achieves very sparse rationale selections with high fidelity while preserving prediction accuracy compared to strong attention baseline models. Expand
Open Intent Discovery through Unsupervised Semantic Clustering and Dependency Parsing
It is empirically show that the proposed unsupervised approach can generate meaningful intent labels automatically and achieves high precision and recall in utterance clustering and intent discovery. Expand
Discovering New Intents with Deep Aligned Clustering
This work proposes an effective method (Deep Aligned Clustering) to discover new intents with the aid of limited known intent data and proposes an alignment strategy to tackle the label inconsistency during clustering assignments. Expand
TEXTOIR: An Integrated and Visualized Platform for Text Open Intent Recognition
  • Hanlei Zhang, Xiaoteng Li, Hua Xu, Panpan Zhang, Kang Zhao, Kai Gao
  • Computer Science
  • Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing: System Demonstrations
  • 2021
TEXTOIR provides useful toolkits and convenient visualized interfaces for each sub-module, and designs a framework to implement a complete process to both identify known intents and discover open intents. Expand
Intent Mining from past conversations for Conversational Agent
This paper presents an intent discovery framework that can mine a vast amount of conversational logs and to generate labeled data sets for training intent models, and introduced an extension to the DBSCAN algorithm and a density-based clustering algorithm ITER-DBSCAN for unbalanced data clustering. Expand
Intra-/Inter-Interaction Network with Latent Interaction Modeling for Multi-turn Response Selection
This work proposes Intra-/Inter-Interaction Network (I^3) with latent interaction modeling to comprehensively model multi-level interactions between the utterance context and the response. Expand


Supervised Clustering of Questions into Intents for Dialog System Applications
A model for automatically clustering questions into user intents to help the design tasks by using powerful semantic classifiers from question duplicate/matching research along with a novel idea of supervised clustering methods based on structured output is proposed. Expand
The Dialog State Tracking Challenge
The dialog state tracking challenge seeks to address this by providing a heterogeneous corpus of 15K human-computer dialogs in a standard format, along with a suite of 11 evaluation metrics, and shows that the suite of performance metrics cluster into 4 natural groups. Expand
MixKMeans: Clustering Question-Answer Archives
This paper presents a clustering method that exploits the two-part question-answer structure in QA datasets to improve clustering quality, and significantly outperforms state-of-the-art clustering methods for the task of clustering question- Answer archives. Expand
Sequence clustering and labeling for unsupervised query intent discovery
This work presents an unsupervised method for clustering queries with similar intent and for producing a pattern consisting of a sequence of semantic concepts and/or lexical items for each intent and uses the discovered intent patterns to automatically annotate a large number of queries beyond those used in clustering. Expand
Multi-domain Dialog State Tracking using Recurrent Neural Networks
This paper shows that dialog data drawn from different dialog domains can be used to train a general belief tracking model which can operate across all of these domains, exhibiting superior performance to each of the domain-specific models. Expand
Jointly Deep Multi-View Learning for Clustering Analysis
This work proposes a novel Joint framework for Deep Multi-view Clustering (DMJC), where multiple deep embedded features, multi-view fusion mechanism and clustering assignments can be learned simultaneously and is the first work to model the multi-View clustering in a deep joint framework. Expand
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
A new language representation model, BERT, designed to pre-train deep bidirectional representations from unlabeled text by jointly conditioning on both left and right context in all layers, which can be fine-tuned with just one additional output layer to create state-of-the-art models for a wide range of tasks. Expand
The Second Dialog State Tracking Challenge
The results suggest that while large improvements on a competitive baseline are possible, trackers are still prone to degradation in mismatched conditions and ensemble learning demonstrates the most accurate tracking can be achieved by combining multiple trackers. Expand
A Survey of Available Corpora for Building Data-Driven Dialogue Systems
A wide survey of publicly available datasets suitable for data-driven learning of dialogue systems is carried out and important characteristics of these datasets are discussed and how they can be used to learn diverse dialogue strategies. Expand
The fifth dialog state tracking challenge
This edition of the fourth dialog state tracking challenge again focused on human-human dialogs, but introduced the task of cross-lingual adaptation of trackers, which received a total of 32 entries from 9 research groups. Expand