SemEval-2010 Task 10: Linking Events and Their Participants in Discourse

Proceedings of the 5th International Workshop on Semantic Evaluation, ACL 2010, pages 45–50, Uppsala, Sweden, 15-16 July 2010. c⃝2010 Association for Computational Linguistics SemEval-2010 Task 10: Linking Events and Their Participants in Discourse Josef Ruppenhofer and Caroline Sporleder Computational Linguistics Saarland University {josefr,csporled}@coli.uni-sb.de Roser Morante CNTS University of Antwerp Roser.Morante@ua.ac.be Collin Baker ICSI Berkeley, CA 94704 collin@icsi.berkeley.edu Martha Palmer Department of Linguistics University of Colorado at Boulder martha.palmer@colorado.edu Abstract We describe the SemEval-2010 shared task on “Linking Events and Their Partic- ipants in Discourse”. This task is an ex- tension to the classical semantic role label- ing task. While semantic role labeling is traditionally viewed as a sentence-internal task, local semantic argument structures clearly interact with each other in a larger context, e.g., by sharing references to spe- cific discourse entities or events. In the shared task we looked at one particular as- pect of cross-sentence links between ar- gument structures, namely linking locally uninstantiated roles to their co-referents in the wider discourse context (if such co-referents exist). This task is poten- tially beneficial for a number of NLP ap- plications, such as information extraction, question answering or text summarization. 1 Introduction Semantic role labeling (SRL) has been defined as a sentence-level natural-language processing task in which semantic roles are assigned to the syntac- tic arguments of a predicate (Gildea and Jurafsky, 2002). Semantic roles describe the function of the participants in an event. Identifying the seman- tic roles of the predicates in a text allows knowing who did what to whom when where how, etc. However, semantic role labeling as it is cur- rently defined misses a lot of information due to the fact that it is viewed as a sentence-internal task. Hence, relations between different local se- mantic argument structures are disregarded. This view of SRL as a sentence-internal task is partly due to the fact that large-scale manual annotation projects such as FrameNet1 and PropBank2 typ- ically present their annotations lexicographically by lemma rather than by source text. It is clear that there is an interplay between lo- cal argument structure and the surrounding dis- course (Fillmore, 1977). In early work, Palmer et al. (1986) discussed filling null complements from context by using knowledge about individual pred- icates and tendencies of referential chaining across sentences. But so far there have been few attempts to find links between argument structures across clause and sentence boundaries explicitly on the basis of semantic relations between the predicates involved. Two notable exceptions are Fillmore and Baker (2001) and Burchardt et al. (2005). Fillmore and Baker (2001) analyse a short newspaper arti- cle and discuss how frame semantics could benefit discourse processing but without making concrete suggestions of how to model this. Burchardt et al. (2005) provide a detailed analysis of the links be- tween the local semantic argument structures in a short text; however their system is not fully imple- mented either. With the shared task, we aimed to make a first step towards taking SRL beyond the domain of individual …

Content truncated to 500 words