Browse State-of-the-Art › Intent Discovery

Intent Discovery

20 papers with code · 3 benchmarks · 3 datasets archive 2025-07-28

Natural Language Processing

Given a set of labelled and unlabelled utterances, the idea is to identify existing (known) intents and potential (new intents) intents. This method can be utilised in conversational system setting.

Description from the archive archive 2025-07-28.

Benchmarks archive 2025-07-28

3 leaderboard tables shown for this task, 3 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted.

DatasetBest model (first row in archive order)PaperCodeSyntologyCompare
ATIS (1 row) k-PCA + HDBSCAN A Hybrid Architecture for Out of Domain Intent Detection and... code — Compare
Persian-ATIS (1 row) k-PCA + HDBSCAN A Hybrid Architecture for Out of Domain Intent Detection and... code — Compare
SNIPS (1 row) k-PCA + HDBSCAN A Hybrid Architecture for Out of Domain Intent Detection and... code — Compare

Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. Each line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the row's paper, the line starts with that repository's state (“official” is the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from. A dash means no Syntology record for that paper, not a recorded non-run. Each “ran” line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.

Libraries

Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.

Datasets archive 2025-07-28

3 datasets whose archive record lists this task, ordered by the archive's paper count.

Subtasks archive 2025-07-28

No subtask under this task in the archive's task tree.

Papers archive 2025-07-28

archive papers tagged: 42 · with a code link: 20 · where Syntology ran a sample: 0 (0 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument) Syntology

Show: all tagged papersonly where code ran: none of the 42 tagged papers has a Syntology run on record

Page 1 of 1: papers 1 to 42 of 42, in archive order: by repositories listed in the archive (most first), then newest first, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers that list no repository come after every paper that lists one.

Papers without a page here are shown as plain text. A Syntology line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code); hover it for the repositories the samples that ran came from. The first sentence of the abstract is shown for the first 30 papers; every abstract is on its paper's page.

  • 15 Aug 2022 2 repositories listed
    In our evaluation, we first analyze the quality of the model after adaptive fine-tuning on known classes.
  • 13 Sep 2021 2 repositories listed
    It is composed of two main modules: open intent detection and open intent discovery.
  • 10 Jun 2025 1 repository listed
    Intent detection aims to identify user intents from natural language inputs, where supervised methods rely heavily on labeled in-domain (IND) data and struggle with out-of-domain (OOD) intents, limiting their practical…
  • 31 Mar 2025 1 repository listed
    New Intent Discovery (NID) is a crucial task that aims to identify these novel intents while maintaining the capability to recognize existing ones.
  • 26 Oct 2024 1 repository listed
    To enable better knowledge transfer, we design a prototype learning method integrating the supervised and pseudo signals from IND and OOD samples.
  • 12 Jul 2024 1 repository listed
    This paper presents a novel and comprehensive solution to enhance both the robustness and efficiency of question answering (QA) systems through supervised contrastive learning (SCL).
  • 24 Oct 2023 1 repository listed Syntology official: harvested, nothing ran · 0 ran · 1 unverified (of 1 harvested sample)
    New Intent Discovery (NID) aims to recognize both new and known intents from unlabeled data with the aid of limited labeled data containing only known intents.
  • 16 Oct 2023 1 repository listed
    In a practical dialogue system, users may input out-of-domain (OOD) queries.
  • 16 Oct 2023 1 repository listed
    The tasks of out-of-domain (OOD) intent discovery and generalized intent discovery (GID) aim to extend a closed intent classifier to open-world intent sets, which is crucial to task-oriented dialogue (TOD) systems.
  • 31 May 2023 1 repository listed
    Intent discovery is the task of inferring latent intents from a set of unlabeled utterances, and is a useful step towards the efficient creation of new conversational agents.
  • 28 May 2023 1 repository listed
    Previous methods suffer from a coupling of pseudo label disambiguation and representation learning, that is, the reliability of pseudo labels relies on representation learning, and representation learning is restricted…
  • 16 Apr 2023 1 repository listed
    New intent discovery is of great value to natural language processing, allowing for a better understanding of user needs and providing friendly services.
  • 7 Mar 2023 1 repository listed
    On the other side, a labeled dataset is needed to train a model for Intent Detection in task-oriented dialogue systems.
  • 17 Oct 2022 1 repository listed
    For OOD clustering stage, we propose a KCC method to form compact clusters by mining true hard negative samples, which bridges the gap between clustering and representation learning.
  • 13 Sep 2022 1 repository listed
    Traditional intent classification models are based on a pre-defined intent set and only recognize limited in-domain (IND) intent classes.
  • 25 May 2022 1 repository listed
    Existing approaches typically rely on a large amount of labeled utterances and employ pseudo-labeling methods for representation learning and clustering, which are label-intensive, inefficient, and inaccurate.
  • 24 May 2022 1 repository listed
    We use this framework to report baseline intent discovery results over VIRADialogs, that highlight the difficulty of this task.
  • 1 May 2022 1 repository listed
    Discovering Out-of-Domain(OOD) intents is essential for developing new skills in a task-oriented dialogue system.
  • 25 Apr 2021 1 repository listed
    This paper presents an unsupervised two-stage approach to discover intents and generate meaningful intent labels automatically from a collection of unlabeled utterances in a domain.
  • 22 May 2020 1 repository listed
    In this paper, we present an intent discovery framework that involves 4 primary steps: Extraction of textual utterances from a conversation using a pre-trained domain agnostic Dialog Act Classifier (Data Extraction)…
  • From Intent Discovery to Recognition with Topic Modeling and Synthetic Data
    16 May 2025 0 repositories listed
    Understanding and recognizing customer intents in AI systems is crucial, particularly in domains characterized by short utterances and the cold start problem, where recommender systems must include new products or…
  • Dial-In LLM: Human-Aligned LLM-in-the-loop Intent Clustering for Customer Service Dialogues
    12 Dec 2024 0 repositories listed
    Discovering customer intentions in dialogue conversations is crucial for automated service agents.
  • IntentGPT: Few-shot Intent Discovery with Large Language Models
    16 Nov 2024 0 repositories listed
    In today's digitally driven world, dialogue systems play a pivotal role in enhancing user interactions, from customer service to virtual assistants.
  • KULCQ: An Unsupervised Keyword-based Utterance Level Clustering Quality Metric
    15 Nov 2024 0 repositories listed
    Intent discovery is crucial for both building new conversational agents and improving existing ones.
  • Auto-Intent: Automated Intent Discovery and Self-Exploration for Large Language Model Web Agents
    29 Oct 2024 0 repositories listed
    In this paper, we introduce Auto-Intent, a method to adapt a pre-trained large language model (LLM) as an agent for a target domain without direct fine-tuning, where we empirically focus on web navigation tasks.
  • Assured Automatic Programming via Large Language Models
    24 Oct 2024 0 repositories listed
    With the advent of AI-based coding engines, it is possible to convert natural language requirements to executable code in standard programming languages.
  • A Survey of Ontology Expansion for Conversational Understanding
    19 Oct 2024 0 repositories listed
    In the rapidly evolving field of conversational AI, Ontology Expansion (OnExp) is crucial for enhancing the adaptability and robustness of conversational agents.
  • Controllable Discovery of Intents: Incremental Deep Clustering Using Semi-Supervised Contrastive Learning
    18 Oct 2024 0 repositories listed
    Deriving value from a conversational AI system depends on the capacity of a user to translate the prior knowledge into a configuration.
  • Towards Real-world Scenario: Imbalanced New Intent Discovery
    5 Jun 2024 0 repositories listed
    New Intent Discovery (NID) aims at detecting known and previously undefined categories of user intent by utilizing limited labeled and massive unlabeled data.
  • RoNID: New Intent Discovery with Generated-Reliable Labels and Cluster-friendly Representations
    13 Apr 2024 0 repositories listed
    New Intent Discovery (NID) strives to identify known and reasonably deduce novel intent groups in the open-world scenario.
  • New Intent Discovery with Attracting and Dispersing Prototype
    25 Mar 2024 0 repositories listed
  • IntenDD: A Unified Contrastive Learning Approach for Intent Detection and Discovery
    25 Oct 2023 0 repositories listed
  • Utilisation of open intent recognition models for customer support intent detection
    31 Jul 2023 0 repositories listed
  • Going beyond research datasets: Novel intent discovery in the industry setting
    9 May 2023 0 repositories listed
  • 1 Jul 2022 0 repositories listed
  • Intent Discovery for Enterprise Virtual Assistants: Applications of Utterance Embedding and Clustering to Intent Mining
    1 Jul 2022 0 repositories listed
  • Multimodal Intent Discovery from Livestream Videos
    1 Jul 2022 0 repositories listed
  • UNICON: Unsupervised Intent Discovery via Semantic-level Contrastive Learning
    16 Nov 2021 0 repositories listed
  • Semi-supervised Intent Discovery with Contrastive Learning
    1 Nov 2021 0 repositories listed
  • Unknown Intent Detection Using Multi-Objective Optimization on Deep Learning Classifiers
    1 Sep 2021 0 repositories listed
  • Intent Discovery With Or Without Labeled Data Using Dependency Parser
    15 Oct 2020 0 repositories listed
  • Towards Open Intent Discovery for Conversational Text
    17 Apr 2019 0 repositories listed

Syntology lines on 1 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced; each line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections