Browse State-of-the-Art › Intent Detection

Intent Detection

121 papers with code · 19 benchmarks · 25 datasets archive 2025-07-28

Natural Language Processing

Intent Detection is a task of determining the underlying purpose or goal behind a user's search query given a context. The task plays a significant role in search and recommendations. A traditional approach for intent detection implies using an intent detector model to classify user search query into predefined intent categories, given a context. One of the key challenges of the task implies identifying user intents for cold-start sessions, i.e., search sessions initiated by a non-logged-in or unrecognized user.

Source: Analyzing and Predicting Purchase Intent in E-commerce: Anonymous vs. Identified Customers

Description from the archive archive 2025-07-28.

Benchmarks archive 2025-07-28

19 leaderboard tables shown for this task, 19 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. 10 shown of 19 until expanded.

Syntology 2 newer papers were judged to report on this task's benchmarks so far (Claude Sonnet 4.5, reading their tables: a model's judgement, not a result; 1 placed): SNIPS (1 judged, 1 placed), BANKING77 (2 judged, 0 placed), HWU64 (1 judged, 0 placed). Drawn from 8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read).

DatasetBest model (first row in archive order)PaperCodeSyntologyCompare
ATIS (16 rows) Bi-model with decoder A Bi-model based RNN Semantic Frame Parsing Model for Intent... code — Compare
MixSNIPS (16 rows) SSRAN A Scope Sensitive and Result Attentive Model for Multi-Intent... — — Compare
MixATIS (15 rows) DGIF A Dynamic Graph Interactive Framework with Label-Semantic... — — Compare
SNIPS (10 rows) CTRAN CTRAN: CNN-Transformer-based Network for Natural Language Understanding code — Compare
ASOS.com user intent (3 rows) plain-LSTM “Where is My Parcel?” Fast and Efficient Classifiers to Detect... code — Compare
BANKING77 (2 rows) RoBERTa-Large + ICDA Selective In-Context Data Augmentation for Intent Detection using... — — Compare
BANKING77 10-shot (1 row) RoBERTa-Large + ICDA Selective In-Context Data Augmentation for Intent Detection using... — — Compare
BANKING77 5-shot (1 row) RoBERTa-Large + ICDA Selective In-Context Data Augmentation for Intent Detection using... — — Compare
CAIS (1 row) CM-Net CM-Net: A Novel Collaborative Memory Network for Spoken Language... code — Compare
CLINC150 (1 row) RoBERTa-Large + ICDA Selective In-Context Data Augmentation for Intent Detection using... — — Compare
CLINC150 10-shot (1 row) RoBERTa-Large + ICDA Selective In-Context Data Augmentation for Intent Detection using... — — Compare
CLINC150 5-shot (1 row) RoBERTa-Large + ICDA Selective In-Context Data Augmentation for Intent Detection using... — — Compare
Dialogue State Tracking Challenge (1 row) MIDAS MIDAS: Multi-level Intent, Domain, And Slot Knowledge Distillation... code — Compare
HWU64 (1 row) RoBERTa-Large + ICDA Selective In-Context Data Augmentation for Intent Detection using... — — Compare
HWU64 10-shot (1 row) RoBERTa-Large + ICDA Selective In-Context Data Augmentation for Intent Detection using... — — Compare
HWU64 5-shot (1 row) RoBERTa-Large + ICDA Selective In-Context Data Augmentation for Intent Detection using... — — Compare
MULTIWOZ 2.2 (1 row) MIDAS MIDAS: Multi-level Intent, Domain, And Slot Knowledge Distillation... code — Compare
ProSLU (1 row) General SLU Model w/ Profile Text is no more Enough! A Benchmark for Profile-based Spoken... code — Compare
ATIS (vi) (1 row) JointBERT-CAE CAE: Mechanism to Diminish the Class Imbalanced in SLU Slot Filling Task 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

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

Subtasks archive 2025-07-28

1 subtask in the archive's task tree.

Papers archive 2025-07-28

archive papers tagged: 330 · with a code link: 121 · where Syntology ran a sample: 12 (12 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 (12 of 330 tagged: 12 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument)

Page 1 of 4: papers 1 to 100 of 330, 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.

Syntology lines on 10 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