Determiner-Established Deixis to Communicative Artifacts in Pedagogical Text

Abstract

Pedagogical materials frequently contain deixis to communicative artifacts such as textual structures (e.g., sections and lists), discourse entities, and illustrations. By relating such artifacts to the prose, deixis plays an essential role in structuring the flow of information in informative writing. However, existing language technologies have largely overlooked this mechanism. We examine properties of deixis to communicative artifacts using a corpus rich in determiner-established instances of the phenomenon (e.g., "this section", "these equations", "those reasons") from Wikibooks, a collection of learning texts. We use this corpus in combination with WordNet to determine a set of word senses that are characteristic of the phenomenon, showing its diversity and validating intuitions about its qualities. The results motivate further research to extract the connections encoded by such deixis, with the goals of enhancing tools to present pedagogical e-texts to readers and, more broadly, improving language technologies that rely on deictic phenomena.

Supervised and Unsupervised Methods for Robust Separation of Section Titles and Prose Text in Web Documents

“…Deixis present in a text can also be considered metadata and detection of deixis helps in structuring the flow of information. Wilson and Oberlander (2014) attempted to capture word senses related to deixis.…”

“…Deixis present in a text can also be considered metadata and detection of deixis helps in structuring the flow of information. Wilson and Oberlander (2014) attempted to capture word senses related to deixis. Topic classification is the problem of segregating a document into different topics, and argumentative zoning (Teufel et al, 1999) was an early effort that shares some goals with the present work, as it addressed the detection of the main thematic areas in research articles.…”