Discriminative Nearest Neighbor Few-Shot Intent Detection by Transferring Natural Language Inference
This addresses data scarcity and OOS detection challenges in goal-oriented dialog systems, representing an incremental improvement over existing methods.
The paper tackles few-shot intent detection with out-of-scope (OOS) detection by proposing a discriminative nearest neighbor method using BERT-style pairwise encoding and natural language inference (NLI) transfer, achieving stable and accurate results where the 10-shot model performs competitively with 50-shot or full-shot classifiers.
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.