Learning to Plan and Realize Separately for Open-Ended Dialogue Systems
Autor: | Bryanna Hebenstreit, Brodie Mather, Bonnie J. Dorr, Alan Zemel, Tomek Strzalkowski, Samira Shaikh, Archna Bhatia, Adam Dalton, Sashank Santhanam, Zhuo Cheng |
---|---|
Jazyk: | angličtina |
Rok vydání: | 2020 |
Předmět: |
FOS: Computer and information sciences
Computer Science - Computation and Language Process (engineering) Computer science media_common.quotation_subject 05 social sciences Realization (linguistics) Natural language generation Plan (drawing) 010501 environmental sciences 01 natural sciences Phase (combat) Human–computer interaction Conversation 0509 other social sciences 050904 information & library sciences Computation and Language (cs.CL) 0105 earth and related environmental sciences media_common |
Zdroj: | EMNLP (Findings) |
Popis: | Achieving true human-like ability to conduct a conversation remains an elusive goal for open-ended dialogue systems. We posit this is because extant approaches towards natural language generation (NLG) are typically construed as end-to-end architectures that do not adequately model human generation processes. To investigate, we decouple generation into two separate phases: planning and realization. In the planning phase, we train two planners to generate plans for response utterances. The realization phase uses response plans to produce an appropriate response. Through rigorous evaluations, both automated and human, we demonstrate that decoupling the process into planning and realization performs better than an end-to-end approach. Accepted at EMNLP 2020 (Findings) |
Databáze: | OpenAIRE |
Externí odkaz: |