CLR: Linking Events and Their Participants in Discourse Using a Comprehensive FrameNet Dictionary

Proceedings of the 5th International Workshop on Semantic Evaluation, ACL 2010, pages 300–303, Uppsala, Sweden, 15-16 July 2010. c⃝2010 Association for Computational Linguistics CLR: Linking Events and Their Participants in Discourse Using a Comprehensive FrameNet Dictionary Ken Litkowski CL Research Damascus, MD USA. ken@clres.com Abstract The CL Research system for SemEval-2 Task 10 for linking events and their participants in discourse is an exploration of the use of a spe- cially created FrameNet dictionary that cap- tures all FrameNet information about frames, lexical units, and frame-to-frame relations. This system is embedded in a specially de- signed interface, the Linguistic Task Analyzer. The implementation of this system was quite minimal at the time of submission, allowing only an initial completion of the role recogni- tion and labeling task, with recall of 0.112, precision of 0.670, and F-score of 0.192. We describe the design of the system and the con- tinuing efforts to determine how much of this task can be performed with the available lexi- cal resources. Changes since the official sub- mission have improved the F-score to 0.266. 1 Introduction The semantic role labeling (SRL) task has re- ceived considerable attention in recent years, with previous tasks in Senseval-2 (Litkowski, 2004), Semeval-1 (Baker et al., 2007), and CoNLL (Carreras & Marquez, 2004; Carreras & Marquez, 2005). The current task, Linking Events and their Participants in Discourse, con- tinues the evolution of SRL tasks with the intent of identifying Null Instantiations, i.e., frame elements that are absent from the local context, but potentially recoverable from the wider dis- course context. CL Research participated in one subtask, role recognition and labeling, unable to implement techniques for the null instantiation subtask. This paper describes our efforts thus far (clearly a work in progress), specifically the implementa- tion of a development interface (section 2), the use of a specially constructed FrameNet dictio- nary (section 3), techniques for performing the role recognition and labeling task (section 4), our results (section 5), and future developments (sec- tion 6). 2 The Linguistic Task Analyzer CL Research participated in the linking task by extending its Linguistic Task Analyzer (LTA), an interface also used for such tasks as word- sense disambiguation and recognizing textual entailment. LTA includes a wide array of mod- ules, including a full-scale parser, post-parsing semantic analysis routines, the use of XML func- tionality for creating and analyzing input and output, and access to several integrated dictiona- ries (used for semantic analysis). Modification of LTA for the linking task involves using existing functionality and implementing new functionali- ty specific to the task. We describe LTA in some detail to illustrate steps that might be relevant to a symbolic approach to the linking task. Each task in LTA consists of a set of items to be analyzed, in this case, an identifier for each sentence in the document being analyzed. LTA loads the appropriate XML files (usually the an- notation file and the gold file) and provides vari- ous data for each sentence, including the number of …

Content truncated to 500 words