Topic-switch adapted Japanese Dialogue System based on PLATO-2
This work addresses the problem of building effective Japanese dialogue systems for users, but it is incremental as it adapts an existing method to a new language with a minor algorithmic addition.
The paper tackled the lack of large-scale open-domain dialogue systems for Japanese by creating a 1.656 million dialogue dataset and training PLATO-2 on it, resulting in PLATO-JDS achieving an average human evaluation score of 1.500 out of 2.000. They also introduced a topic-switch algorithm that improved the score by 0.267 to 1.767, enhancing user experience.
Large-scale open-domain dialogue systems such as PLATO-2 have achieved state-of-the-art scores in both English and Chinese. However, little work explores whether such dialogue systems also work well in the Japanese language. In this work, we create a large-scale Japanese dialogue dataset, Dialogue-Graph, which contains 1.656 million dialogue data in a tree structure from News, TV subtitles, and Wikipedia corpus. Then, we train PLATO-2 using Dialogue-Graph to build a large-scale Japanese dialogue system, PLATO-JDS. In addition, to improve the PLATO-JDS in the topic switch issue, we introduce a topic-switch algorithm composed of a topic discriminator to switch to a new topic when user input differs from the previous topic. We evaluate the user experience by using our model with respect to four metrics, namely, coherence, informativeness, engagingness, and humanness. As a result, our proposed PLATO-JDS achieves an average score of 1.500 for the human evaluation with human-bot chat strategy, which is close to the maximum score of 2.000 and suggests the high-quality dialogue generation capability of PLATO-2 in Japanese. Furthermore, our proposed topic-switch algorithm achieves an average score of 1.767 and outperforms PLATO-JDS by 0.267, indicating its effectiveness in improving the user experience of our system.