UTD-SRL: A Pipeline Architecture for Extracting Frame Semantic Structures

Proceedings of the 4th International Workshop on Semantic Evaluations (SemEval-2007), pages 460–463, Prague, June 2007. c⃝2007 Association for Computational Linguistics UTD-SRL: A Pipeline Architecture for Extracting Frame Semantic Structures Cosmin Adrian Bejan and Chris Hathaway Human Language Technology Research Institute The University of Texas at Dallas Richardson, TX 75083-0688, USA {ady,chris}@hlt.utdallas.edu Abstract This paper describes our system for the task of extracting frame semantic structures in SemEval–2007. The system architecture uses two types of learning models in each part of the task: Support Vector Machines (SVM) and Maximum Entropy (ME). De- signed as a pipeline of classifiers, the seman- tic parsing system obtained competitive pre- cision scores on the test data. 1 Introduction The SemEval–2007 task for extracting frame se- mantic structures relies on the human annotated data available in the FrameNet (FN) database. The Berkeley FrameNet project (Baker et al., 1998) is an ongoing effort of building a semantic lexicon for English based on the theory of frame semantics. In frame semantics, the meaning of words or word ex- pressions, also called target words (TW), comprises aspects of conceptual structures, or frames, that de- scribe specific situations. The semantic roles, or frame elements (FE), associated with a target word are locally defined in the frame evoked by the tar- get word. Currently, the FN lexicon includes more than 135,000 sentences extracted from the British National Corpus containing more than 6,100 target words that evoke more than 825 semantic frames. For this task, we extended our previous work at Senseval-3 (Bejan et al., 2004) by (1) experiment- ing with additional features, (2) adding new classifi- cation sub-tasks to accomplish all the requirements, and (3) integrating these sub-tasks into a pipeline ar- chitecture. 2 System Description Given a sentence, the frame semantic structure ex- traction task consists of recognizing the word ex- pressions that evoke semantic frames, assigning the correct frame to them and, for each target word, detecting and labeling the corresponding frame el- ements properly. The task also requires the de- termination of syntactic realizations associated to a frame element, such as grammatical function (GF) and phrase type (PT). The following illustrates a sentence example annotated with frame elements to- gether with their corresponding grammatical func- tions and phrase types for the target word “tie”: FE = Content2 GF = Dep PT = PP FE = Content1 GF = Ext PT = NP AEOI’s activities and facilities have been tied to several universities . Frame = Make_Cognitive_Connection evokes To extract semantic structures similar to those il- lustrated in the example we divide the SemEval– 2007 task into four sub-tasks: (1) target word frame disambiguation (TWFD); (2) FE boundary detection (FEBD); (3) GF label classification (GFLC) and (4) FE label classification (FELC). The sub-tasks TWFD and GFLC are natural extensions of the approach de- scribed in (Bejan et al., 2004) for the task of se- mantic role labeling at Senseval-03. We design ma- chine learning classifiers specific for each of the four sub-tasks and arrange them in a pipeline architecture …

Content truncated to 500 words