Papers › Induction Networks for Few-Shot Text Classification

Induction Networks for Few-Shot Text Classification

27 Feb 2019IJCNLP 2019 11arXiv:1902.10482archive 2025-07-28

Ruiying Geng, Binhua Li, Yongbin Li, Xiaodan Zhu, Ping Jian, Jian Sun

Text classification tends to struggle when data is deficient or when it needs to adapt to unseen classes. In such challenging scenarios, recent studies have used meta-learning to simulate the few-shot task, in which new queries are compared to a small support set at the sample-wise level. However, this sample-wise comparison may be severely disturbed by the various expressions in the same class. Therefore, we should be able to learn a general representation of each class in the support set and then compare it to new queries. In this paper, we propose a novel Induction Network to learn such a generalized class-wise representation, by innovatively leveraging the dynamic routing algorithm in meta-learning. In this way, we find the model is able to induce and generalize better. We evaluate the proposed model on a well-studied sentiment classification dataset (English) and a real-world dialogue intent classification dataset (Chinese). Experiment results show that on both datasets, the proposed model significantly outperforms the existing state-of-the-art approaches, proving the effectiveness of class-wise generalization in few-shot text classification.

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

hongshengxin/Induction_network mentioned on GitHubpytorch report
laohur/LearnToCompareText mentioned on GitHubpytorch report
laohur/RelationNet mentioned on GitHubpytorch report
mhw32/prototransformer-public mentioned on GitHubpytorchMIT report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Few-Shot Text ClassificationGeneral ClassificationIntent ClassificationMeta-LearningSentiment AnalysisSentiment ClassificationText Classificationintent-classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Few-Shot Text Classification ODIC 10-way (10-shot) Induction Networks Accuracy 81.64 #1 of 1 Archive leaderboard report
Few-Shot Text Classification ODIC 10-way (5-shot) Induction Networks Accuracy 78.27 #1 of 1 Archive leaderboard report
Few-Shot Text Classification ODIC 5-way (10-shot) Induction Networks Accuracy 88.49 #1 of 1 Archive leaderboard report
Few-Shot Text Classification ODIC 5-way (5-shot) Induction Networks Accuracy 87.16 #1 of 1 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

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