Towards Automatic Identification of Discourse Markers in Dialogs: the Case of 'Like'

This article discusses the detection of discourse markers (DM) in dialog transcriptions, by human annotators and by automated means. After a theoretical discussion of the definition of DMs and their relevance to natural language processing, we focus on the role of like as a DM. Results from experiments with human annotators show that detection of DMs is a difficult but reliable task, which requires prosodic information from soundtracks. Then, several types of features are defined for automatic disambiguation of like: collocations, part-of-speech tags and duration-based features. Decision-tree learning shows that for like, nearly 70% precision can be reached, with near 100% recall, mainly using collocation filters. Similar results hold for well, with about 91% precision at 100% recall.

Tackling Copyright in the Digital Age: An Initiative of the University of Connecticut Libraries

From 2005 to 2007, the University of Connecticut Libraries Copyright Project Team engaged in a wide range of activities to fulfill its charge and to raise awareness of copyright issues in the library and across the university. This article highlights some of the primary activities and tools used by the team to involve stakeholders, to provide educational opportunities, and to stay current on copyright issues in higher education. Among other activities, the team developed a new copyright web site for use by library staff and the broader university community.