Generating High-Quality and Informative Conversation Responses with Sequence-to-Sequence Models
Citations Over TimeTop 1% of 2017 papers
Abstract
Sequence-to-sequence models have been applied to the conversation response generation problem where the source sequence is the conversation history and the target sequence is the response. Unlike translation, conversation responding is inherently creative. The generation of long, informative, coherent, and diverse responses remains a hard task. In this work, we focus on the single turn setting. We add self-attention to the decoder to maintain coherence in longer responses, and we propose a practical approach, called the glimpse-model, for scaling to large datasets. We introduce a stochastic beam-search algorithm with segment-by-segment reranking which lets us inject diversity earlier in the generation process. We trained on a combined data set of over 2.3B conversation messages mined from the web. In human evaluation studies, our method produces longer responses overall, with a higher proportion rated as acceptable and excellent as length increases, compared to baseline sequenceto-sequence models with explicit lengthpromotion. A back-off strategy produces better responses overall, in the full spectrum of lengths.
Related Papers
- Conversational coherence : form, structure, and strategy(1983)
- → Social Media Conversation Monitoring: Visualize Information Contents of Twitter Messages Using Conversational Metrics(2016)6 cited
- → Focus-aware Response Generation in Inquiry Conversation(2023)8 cited
- → The Coherence of Incoherent Discourse(1985)28 cited
- → On Abstract Models and Conversation Policies(2000)10 cited