Knowledge-Grounded Response Generation with Deep Attentional Latent-Variable Model
| Autor: | Hao-Tong Ye, Shang-Yu Su, Yun-Nung Chen, Kai-Ling Lo |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2019 |
| Předmět: |
FOS: Computer and information sciences
Response generation Joint attention Computer science 02 engineering and technology computer.software_genre 01 natural sciences Theoretical Computer Science Task (project management) 0103 physical sciences 0202 electrical engineering electronic engineering information engineering Latent variable model 010301 acoustics Computer Science - Computation and Language Mechanism (biology) business.industry 020206 networking & telecommunications Human-Computer Interaction Benchmark (computing) Artificial intelligence business Computation and Language (cs.CL) computer Software Natural language processing Diversity (business) |
| Popis: | End-to-end dialogue generation has achieved promising results without using handcrafted features and attributes specific for each task and corpus. However, one of the fatal drawbacks in such approaches is that they are unable to generate informative utterances, so it limits their usage from some real-world conversational applications. This paper attempts at generating diverse and informative responses with a variational generation model, which contains a joint attention mechanism conditioning on the information from both dialogue contexts and extra knowledge. Published in DSTC7 workshop at AAAI 2019 |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|