Файл:A Neural Conversational Model 1506.05869.pdf
Oriol Vinyals VINYALS@GOOGLE.COM Google Quoc V. Le QVL@GOOGLE.COM Google
Conversational modeling is an important task in natural language understanding and machine intelligence. Although previous approaches exist, they are often restricted to speciﬁc domains (e.g., booking an airline ticket) and require handcrafted rules. In this paper, we present a simple approach for this task which uses the recently proposed sequence to sequence framework. Our model converses by predicting the next sentence given the previous sentence or sentences in a conversation. The strength of our model is that it can be trained end-to-end and thus requires much fewer hand-crafted rules. We ﬁnd that this straightforward model can generate simple conversations given a large conversational training dataset. Our preliminary results suggest that, despite optimizing the wrong objective function, the model is able to converse well. It is able extract knowledge from both a domain speciﬁc dataset, and from a large, noisy, and general domain dataset of movie subtitles. On a domainspeciﬁc IT helpdesk dataset, the model can ﬁnd a solution to a technical problem via conversations. On a noisy open-domain movie transcript dataset, the model can perform simple forms of common sense reasoning. As expected, we also ﬁnd that the lack of consistency is a commonfailure mode of our model.
Нажмите на дату/время, чтобы просмотреть, как тогда выглядел файл.
|текущий||12:08, 22 декабря 2016||0 × 0 (87 КБ)||Slikos|
- Вы не можете перезаписать этот файл.