Discriminative Nearest Neighbor Few-Shot Intent Detection by Transferring Natural Language Inference
By Jianguo Zhang, Kazuma Hashimoto, Wenhao Liu, Chien-Sheng Wu, Yao Wan, Philip S. Yu, Richard Socher, Caiming Xiong. 2020
99 citations recorded by the source corpus.
Intent detection is one of the core components of goal-oriented dialog systems, and detecting out-of-scope (OOS) intents is also a practically important skill. Few-shot learning is attracting much attention to mitigate data scarcity, but OOS detection becomes even more challenging. In this paper, we present a simple yet effective approach, discriminative nearest neighbor classification with deep self-attention. Unlike softmax classifiers, we leverage BERT-style pairwise encoding to train a binary classifier that estimates the best matched training example for a user input. We propose to boost the discriminative ability by transferring a natural language inference (NLI) model. Our extensive experiments on a large-scale multi-domain intent detection task show that our method achieves more stable and accurate in-domain and OOS detection accuracy than RoBERTa-based classifiers and embedding-based nearest neighbor approaches. More notably, the NLI transfer enables our 10-shot model to perform competitively with 50-shot or even full-shot classifiers, while we can keep the inference time constant by leveraging a faster embedding retrieval model.
Subfields: Artificial Intelligence
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Luke S. Zettlemoyer
- Philip S. Yu
- Wenpeng Yin
- Kelvin Guu
- Caiming Xiong
- Luheng He
- Mohit Bansal
- Percy Liang
Citations in the corpus
- Incremental Few-shot Text Classification with Multi-round New Classes: Formulation, Dataset and System (2021, positive): “For the IFS-R ELATION benchmark, we only compare E NTAIL - MENT with DNNC since H YBRID is not applicable for this dataset.”
- Neural Data Augmentation via Example Extrapolation (2021, positive): “The teacher models are finetuned for 3 epochs for FewRel and 10 epochs for CLINC150/SNIPS.”
- Continual Few-shot Intent Detection (2022, methodology): “For DNNC, we follow the settings in Zhang et al. (2020).”