The relationship between working memory capacity and writing ability was examined via a linguistic analysis of student essays. Undergraduate students (n = 108) wrote timed, prompt-based essays and completed a battery of cognitive assessments. The surfaceand discourse-level linguistic features of students’ essays were then analyzed using natural language processing tools. The results indicated t...

This paper reports on the beginnings of some work whose aim is to investigate the role of punctuation in signalling discourse structure. This is part of a larger enterprise motivated by the view that natural language processing systems, whether generating or understanding language, should take account of the physical manifestation of language: in the context of written language, this means taki...

Handling of human language by computer is a very intricate and complex task. In natural languages, sentences are usually part of discourse units just as words are part of sentences. Anaphora resolution plays a significant role in discourse analysis for chopping larger discourse units into smaller ones. This process is done for the purpose of better understanding and making easier the further pr...

Chinese discourse coherence modeling remains a challenge taskin Natural Language Processing field.Existing approaches mostlyfocus on the need for feature engineering, whichadoptthe sophisticated features to capture the logic or syntactic or semantic relationships acrosssentences within a text.In this paper, we present an entity-drivenrecursive deep modelfor the Chinese discourse coherence evalu...

In this paper we address the problem of skewed class distribution in implicit discourse relation recognition. We examine the performance of classifiers for both binary classification predicting if a particular relation holds or not and for multi-class prediction. We review prior work to point out that the problem has been addressed differently for the binary and multi-class problems. We demonst...

While the global discourse structure that describes how utterances are grouped into larger units of discourse has received much attention both in oral and in computermediated dialogues, the local structure (i. e. the structure of individual utterances) of chat conversations has not been previously studied in a psycholinguistic perspective. In this paper we explore some evidence of cognitive pro...

A study is presented on the effects of discourse-semantic and lexical-syntactic information during spoken sentence processing. Event-related brain potentials (ERPs) were registered while subjects listened to discourses that ended in a sentence with a temporary syntactic ambiguity. The prior discourse-semantic information biased toward one analysis of the temporary ambiguity, whereas the lexical...

Human engagement in narrative is partially driven by reasoning about discourse relations between narrative events, and the expectations about what is likely to happen next that results from such reasoning. Researchers in NLP have tackled modeling such expectations from a range of perspectives, including treating it as the inference of the CONTINGENT discourse relation, or as a type of common-se...

We present an implemented system for processing definite descriptions. The system is based on the results of a corpus analysis previously reported, which showed how common discourse-new descriptions are in newspaper corpora, and identified several problems to be dealt with when developing computational methods for interpreting bridging descriptions. The annotated corpus produced in this earlier...

It is increasingly recognized in Natural Language Processing that intonation makes a significant contribution to the communication of discourse structure. However, the correspondence between particular intonational features and specific aspects of discourse structure is only beginning to be understood. In this paper, we show how tune, phrasing, accent, and pitch range can combine to convey info...