Linguistically-Enriched and Context-Aware Zero-shot Slot Filling

Abstract

Slot filling is identifying contiguous spans of words in an utterance that correspond to certain parameters (i.e., slots) of a user request/query. Slot filling is one of the most important challenges in modern task-oriented dialog systems. Supervised learning approaches have proven effective at tackling this challenge, but they need a significant amount of labeled training data in a given domain. However, new domains (i.e., unseen in training) may emerge after deployment. Thus, it is imperative that these models seamlessly adapt and fill slots from both seen and unseen domains -- unseen domains contain unseen slot types with no training data, and even seen slots in unseen domains are typically presented in different contexts. This setting is commonly referred to as zero-shot slot filling. Little work has focused on this setting, with limited experimental evaluation. Existing models that mainly rely on context-independent embedding-based similarity measures fail to detect slot values in unseen domains or do so only partially. We propose a new zero-shot slot filling neural model, LEONA, which works in three steps. Step one acquires domain-oblivious, context-aware representations of the utterance word by exploiting (a) linguistic features; (b) named entity recognition cues; (c) contextual embeddings from pre-trained language models. Step two fine-tunes these rich representations and produces slot-independent tags for each word. Step three exploits generalizable context-aware utterance-slot similarity features at the word level, uses slot-independent tags, and contextualizes them to produce slot-specific predictions for each word. Our thorough evaluation on four diverse public datasets demonstrates that our approach consistently outperforms the SOTA models by 17.52%, 22.15%, 17.42%, and 17.95% on average for unseen domains on SNIPS, ATIS, MultiWOZ, and SGD datasets, respectively.

References in corpus (20)

• Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
• Prototypical Networks for Few-shot Learning
• SQuAD: 100,000+ Questions for Machine Comprehension of Text
• A large annotated corpus for learning natural language inference
• Snips Voice Platform: an embedded Spoken Language Understanding system for private-by-design voice interfaces
• Optimal Hyperparameters for Deep LSTM-Networks for Sequence Labeling Tasks
• Few-shot classification in Named Entity Recognition Task
• DiSAN: Directional Self-Attention Network for RNN/CNN-Free Language Understanding
• Benchmarking Natural Language Understanding Services for building Conversational Agents
• A Joint Many-Task Model: Growing a Neural Network for Multiple NLP Tasks
• Joint Slot Filling and Intent Detection via Capsule Neural Networks
• Few-shot Autoregressive Density Estimation: Towards Learning to Learn Distributions
• Adapting Meta Knowledge Graph Information for Multi-Hop Reasoning over Few-Shot Relations
• Leveraging Sentence-level Information with Encoder LSTM for Semantic Slot Filling
• Induction Networks for Few-Shot Text Classification
• Deep Semantic Role Labeling with Self-Attention
• Coach: A Coarse-to-Fine Approach for Cross-domain Slot Filling
• Goal-Oriented Multi-Task BERT-Based Dialogue State Tracker
• The SPPD System for Schema Guided Dialogue State Tracking Challenge
• Few-shot Slot Tagging with Collapsed Dependency Transfer and Label-enhanced Task-adaptive Projection Network