Shallow Discourse Parsing

Course organization

Instructors:	Tatjana Scheffler Manfred Stede
Time:	Mondays, 10-12 a.m. winter semester 2016/17
Place:	Golm, building 14, room 035
Modules:	CSAM11 or CSAM12 (M.Sc.) AM4 (B.Sc.)
Moodle:	Please register on the course's Moodle site.

Requirements

regular readings
active participation
presentation
project work + documentation (final paper)
grade: final project + presentation

Course description

A central factor of text coherence is the speaker’s/author’s establishing discourse relations between adjacent portions of text, e.g., temporal or causal ones. In this class, we will work on the specific task of shallow discourse parsing, which have received increased attention in the recent years. Shallow discourse parsing aims at identifying (explicit or implicit) discourse connectives and their arguments, as well as the semantic relations they express, in free text.

We will first study previous systems and approaches (as published in the CONLL Shared Tasks, and others). At the last Shared Task, we have participated with a shallow discourse parser for English: OPT (Oepen et al., 2016). The second part of the class will be spent on group projects aimed at improving individual modules or the general architecture of the parser, based on the preferences of the course participants.

Literature

• CONLL 2015 Shared Task
• CONLL 2016 Shared Task


• Lin, Z., Ng, H. T., & Kan, M. Y. (2014). A PDTB-styled end-to-end discourse parser. Natural Language Engineering, 20(02), 151-184.
• William Mann and Sandra Thompson. 1988. Rhetorical Structure Theory: Towards a Functional Theory of Text Organization. TEXT, 8:243–281.
• S. Oepen, J. Read, T. Scheffler, U. Sidarenka, M. Stede, E. Velldal, and L. Øvrelid. OPT: Oslo–Potsdam–Teesside---Pipelining Rules, Rankers, and Classifier Ensembles for Shallow Discourse Parsing. In Proceedings of the CONLL 2016 Shared Task. Berlin, 2016.
• R. Prasad, N. Dinesh, A. Lee, E. Miltsakaki, L. Robaldo, A. Joshi and B. Webber. 2008. The Penn Discourse Treebank 2.0. In Proc. of the 6th International Confer- ence on Language Resources and Evaluation (LREC). Marrakech, Morocco.
• Wang, J., & Lan, M. (2015). A refined end-to-end discourse parser. CoNLL 2015, 17.