Semi-Supervised New Intention Discovery for Syntactic Elimination and Fusion in Elastic Neighborhoods
Source abstract
Abstract
Semi-supervised new intent discovery is a significant research focus in natural language understanding. To address the limitations of current semi-supervised training data and the underutilization of implicit information, a S... | Find, read and cite all the research you need on Tech Science Press
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Rough Sets and Fuzzy Logic · Data Management and Algorithms · Time Series Analysis and Forecasting
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (43)
Show source-provided references
1. Zero-shot multitask intent and emotion prediction from multimodal data: a benchmark study10.1016/j.neucom.2023.127128 ↗
2. Tell me what you Like: introducing natural language preference elicitation strategies in a virtual assistant for the movie domain10.1007/s10844-023-00835-8 ↗
3. BERT for conversational question answering systems using semantic similarity estimation
4. An intent recognition pipeline for conversational AI
5. BERT: Pre-training of deep bidirectional transformers for language understanding
6. Liu Y. RoBERTa: a robustly optimized bert pretraining approach. arXiv:1907.11692. 2019.
7. Sanh V. DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter. arXiv:1910.01108. 2019.
8. Lan Z, Chen M, Goodman S, Gimpel K, Sharma P, Soricut R. ALBERT: a Lite BERT for self-supervised learning of language representations. arXiv:1909.11942. 2019.
9. Clark K, Luong MT, Le QV, Manning CD. ELECTRA: pre-training text encoders as discriminators rather than generators. arXiv:2003.10555. 2020.
10. Feature distillation from vision-language model for semisupervised action classification10.55730/1300-0632.4038 ↗
11. Back to common sense: oxford dictionary descriptive knowledge augmentation for aspect-based sentiment analysis10.1016/j.ipm.2022.103260 ↗
12. NCGNN: node-level capsule graph neural network for semisupervised classification10.1109/TNNLS.2022.3179306 ↗
13. Hybrid tensor networks for fully supervised and semi-supervised hyperspectral image classification10.1109/JSTARS.2023.3308723 ↗
14. Sequential visual and semantic consistency for semi-supervised text recognition10.1016/j.patrec.2024.01.008 ↗
15. Multivariate graph neural networks on enhancing syntactic and semantic for aspect-based sentiment analysis10.1007/s10489-024-05802-6 ↗
16. Prompt learning for metonymy resolution: enhancing performance with internal prior knowledge of pre-trained language models10.1016/j.knosys.2023.110928 ↗
17. EDA: easy data augmentation techniques for boosting performance on text classification tasks
18. Data augmentation for graph neural networks
19. LLM-powered data augmentation for enhanced cross-lingual performance
20. Augmented SBERT: data augmentation method for improving Bi-encoders for pairwise sentence scoring tasks
21. ILTS: inducing intention propagation in decentralized multi-agent tasks with large language models
22. Text data augmentation and pre-trained Language Model for enhancing text classification of low-resource languages10.7717/peerj-cs.1974 ↗
23. CC-GNN: a clustering contrastive learning network for graph semi-supervised learning10.1109/ACCESS.2024.3398356 ↗
24. Simple and asymmetric graph contrastive learning without augmentations
25. Improving diversity and discriminability based implicit contrastive learning for unsupervised domain adaptation10.1007/s10489-024-05351-y ↗
26. Intent detection and discovery from user logs via deep semi-supervised contrastive clustering
27. New intent discovery with attracting and dispersing prototype
28. ClusterPrompt: cluster semantic enhanced prompt learning for new intent discovery
29. Interactive supervision for new intent discovery10.1109/LSP.2024.3416882 ↗
30. Feature-weight and cluster-weight learning in fuzzy c-means method for semi-supervised clustering10.1016/j.asoc.2024.111712 ↗
31. New intent discovery with multi-view clustering
32. A diffusion weighted graph framework for new intent discovery
33. The Stanford CoreNLP natural language processing toolkit
34. Wantwords: an open-source online reverse dictionary system
35. New intent discovery with pre-training and contrastive learning
36. k-means++: the advantages of careful seeding
37. New user intent discovery with robust pseudo label training and source domain joint training10.1109/MIS.2023.3283909 ↗
38. Clark K. Electra: pre-training text encoders as discriminators rather than generators. arXiv:200310555. 2020.
39. Generalized category discovery with decoupled prototypical network
40. Mpnet: masked and permuted pre-training for language understanding
41. Zhang H, Xu H, Wang X, Long F, Gao K. USNID: a framework for unsupervised and semi-supervised new intent discovery. arXiv:2304.07699v1. 2023.
42. Effectiveness of pre-training for few-shot intent classification
43. Benchmarking natural language understanding services for building conversational agents