Automatic Prediction of Discourse Connectives
This work addresses the challenge of generating fluent discourses for applications like dialog systems, though it is incremental as it applies an existing method to a new dataset.
The paper tackles the problem of predicting suitable discourse connectives to build coherent discourses, and finds that an automatic predictor using a decomposable attention model achieves an F1 score of 32, outperforming human raters who score 30.
Accurate prediction of suitable discourse connectives (however, furthermore, etc.) is a key component of any system aimed at building coherent and fluent discourses from shorter sentences and passages. As an example, a dialog system might assemble a long and informative answer by sampling passages extracted from different documents retrieved from the Web. We formulate the task of discourse connective prediction and release a dataset of 2.9M sentence pairs separated by discourse connectives for this task. Then, we evaluate the hardness of the task for human raters, apply a recently proposed decomposable attention (DA) model to this task and observe that the automatic predictor has a higher F1 than human raters (32 vs. 30). Nevertheless, under specific conditions the raters still outperform the DA model, suggesting that there is headroom for future improvements.