Context and knowledge aware conversational model and system combination for grounded response generation
| Autor: | Shugo Kato, Akinobu Lee, Akihide Ozeki, Ryota Tanaka |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
Response generation
Focus (computing) System combination Computer science 020206 networking & telecommunications Context (language use) 02 engineering and technology computer.software_genre 01 natural sciences Theoretical Computer Science Human-Computer Interaction Human–computer interaction 0103 physical sciences 0202 electrical engineering electronic engineering information engineering Dialog system Baseline (configuration management) 010301 acoustics computer Software |
| Zdroj: | Computer Speech & Language. 62:101070 |
| ISSN: | 0885-2308 |
| DOI: | 10.1016/j.csl.2020.101070 |
| Popis: | End-to-end neural-based dialogue systems can potentially generate tailored and coherent responses for user inputs. However, most of existing systems produce universal and non-informative responses, and they have not gone beyond chitchat yet. To tackle these problems, 7th Dialog System Technology Challenges (DSTC7-Track2) was developed to focus on building a dialogue system that produces informational responses that are grounded on external knowledge. In this study, we propose a Memory-augmented Hierarchical Recurrent Encoder-Decoder, called MHRED, that grounded on both multi-turn dialogue context and external knowledge. Furthermore, we apply a combination of multiple dialogue systems. Our final system is an ensemble that combines three modules: a generation-based module, a retrieval-based module, and a reranking module. First, responses are generated by MHRED, and retrieved from a pre-defined database focusing on informativeness. Next, the reranking module sorts these candidates using several hand-crafted features, and finally it selects a response with the highest score. Therefore, this system can return diverse and meaningful responses from various perspectives. Experimental results show that our proposed MHRED outperforms strong baseline models and combining multiple dialogue systems significantly improves the automatic evaluation and human evaluations. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full Text from ScienceDirect