Fine-Grained Sentence Functions for Short-Text Conversation
This work addresses the problem of enhancing conversation models for short-text interactions by providing annotated data, but it is incremental as it builds on existing methods with new annotations.
The authors tackled the lack of a large conversation dataset annotated with sentence functions by collecting STC-Sefun, a new dataset for short-text conversations, and used it to train classification and conversation models, resulting in improved response quality.
Sentence function is an important linguistic feature referring to a user's purpose in uttering a specific sentence. The use of sentence function has shown promising results to improve the performance of conversation models. However, there is no large conversation dataset annotated with sentence functions. In this work, we collect a new Short-Text Conversation dataset with manually annotated SEntence FUNctions (STC-Sefun). Classification models are trained on this dataset to (i) recognize the sentence function of new data in a large corpus of short-text conversations; (ii) estimate a proper sentence function of the response given a test query. We later train conversation models conditioned on the sentence functions, including information retrieval-based and neural generative models. Experimental results demonstrate that the use of sentence functions can help improve the quality of the returned responses.