Most text displays an internal coherence structure, which can be analyzed as a tree structure of relations that hold between short segments of text. We present a machinelearning governed approach to such an analysis in the framework of Rhetorical Structure Theory. Our rhetorical analyzer observes a variety of textual properties, such as cue phrases, part-of-speech information, rhetorical contex...

We are interested in the area of Dialogue Act (da) tagging. Identifying the dialogue acts of utterances is recognised as an important step towards understanding the content and nature of what speakers say. We have built a simple dialogue act classifier based on purely intrautterance features — principally word n-gram cue phrases. Although such a classifier performs surprisingly well, rivalling ...

In this work, we present a weakly supervised sentence extraction technique for identifying important sentences in scientific papers that are worthy of inclusion in the abstract. We propose a new attention based deep learning architecture that jointly learns to identify important content, as well as the cue phrases that are indicative of summary worthy sentences. We propose a new context embeddi...

For the task of recognizing dialogue acts, we are applying the Transformation-Based Learning (TBL) machine learning algorithm. To circumvent a sparse data problem, we extract values of well-motivated features of utterances, such as speaker direction, punctuation marks, and a new feature, called dialogue act cues, which we find to be more effective than cue phrases and word n-grams in practice. ...

The present study investigated whether preschool children could use the conventional “actions speak louder than words” principle (or the verbal-nonverbal consistency principle) to process information in situations where verbal cues contradict nonverbal cues. Three-, 4-, and 5-year-olds were shown a video in which an actor drank a beverage and made a verbal statement (e.g., “I like it”) that was...