This paper reports the submitted discourse relation classification systems of the language information processing group of Beijing Institute of Technology (BIT) to the CoNLL-2016 shared task. In this work, discriminative methods were employed according to the different characteristics of English and Chinese discourse structures. Additionally, distributed representations were introduced to catch...

Scientific papers revolve around citations, and for many discourse level tasks one needs to know whose work is being talked about at any point in the discourse. In this paper, we introduce the scientific attribution task, which links different linguistic expressions to citations. We discuss the suitability of different evaluation metrics and evaluate our classification approach to deciding attr...

We describe the use of the Apple-Psych system to conduct language comprehension experiments. Using this system, we have implemented several tasks commonly used to assess the cognitive processes involved in language comprehension. These include segment-by-segment reading tasks in which the stimuli are presented visually, and divided-attention and crossmodal tasks in which the stimuli are present...

We show that comprehenders' expectations about upcoming discourse coherence relations influence the resolution of local structural ambiguity. We employ cases in which two clauses share both a syntactic relationship and a discourse relationship, and hence in which syntactic and discourse processing might be expected to interact. An off-line sentence-completion study and an on-line self-paced rea...

Discourse connectives are words or phrases such as once, since, and on the contrary that explicitly signal the presence of a discourse relation. There are two types of ambiguity that need to be resolved during discourse processing. First, a word can be ambiguous between discourse or non-discourse usage. For example, once can be either a temporal discourse connective or a simply a word meaning “...

Reports on the effects of dividing attention at study on subsequent perceptual priming suggest that perceptual priming is generally unaffected by attentional manipulations as long as word identity is processed. We tested this hypothesis in three experiments by using the implicit word fragment completion and word stem completion tasks. Division of attention was instantiated with the Stroop task ...