Hierarchical RNN with Static Sentence-Level Attention for Text-Based Speaker Change Detection
arXiv:1703.07713
Abstract
Speaker change detection (SCD) is an important task in dialog modeling. Our paper addresses the problem of text-based SCD, which differs from existing audio-based studies and is useful in various scenarios, for example, processing dialog transcripts where speaker identities are missing (e.g., OpenSubtitle), and enhancing audio SCD with textual information. We formulate text-based SCD as a matching problem of utterances before and after a certain decision point; we propose a hierarchical recurrent neural network (RNN) with static sentence-level attention. Experimental results show that neural networks consistently achieve better performance than feature-based approaches, and that our attention-based model significantly outperforms non-attention neural networks.
arXiv commentIn Proceedings of the ACM on Conference on Information and Knowledge Management (CIKM), 2017
References in corpus (11)
- Adam: A Method for Stochastic Optimization
- Bidirectional Attention Flow for Machine Comprehension
- A Neural Conversational Model
- Convolutional Neural Network Architectures for Matching Natural Language Sentences
- Effective Approaches to Attention-based Neural Machine Translation
- Reasoning about Entailment with Neural Attention
- A large annotated corpus for learning natural language inference
- A Hierarchical Neural Autoencoder for Paragraphs and Documents
- Natural Language Inference by Tree-Based Convolution and Heuristic Matching
- Neural Attention Models for Sequence Classification: Analysis and Application to Key Term Extraction and Dialogue Act Detection
- Dialogue Session Segmentation by Embedding-Enhanced TextTiling