Báo cáo khoa học: Semantic Role Labeling: Past, Present and Future

Semantic Role Labeling (SRL) consists of, given a sentence, detecting basic event structures such as “who” did “what” to “whom”, “when” and “where”. From a linguistic point of view, a key component of the task corresponds to identifying the semantic arguments filling the roles of the sentence predicates. Typical predicate semantic arguments include Agent, Patient, and Instrument, but semantic roles may also be found as adjuncts (e.g., Locative, Temporal, Manner, and Cause). The identification of such event frames holds potential for significant impact in many NLP applications, such as Information Extraction, Question Answering, Summarization and Machine Translation. Recently, the...
Nội dung trích xuất từ tài liệu:
Báo cáo khoa học: "Semantic Role Labeling: Past, Present and Future" Semantic Role Labeling: Past, Present and Future Llu´s M` rquez ı a TALP Research Center Software Department Technical University of Catalonia lluism@lsi.upc.edu1 Introduction 2 Content Overview and Outline This tutorial has two differentiated parts. InSemantic Role Labeling (SRL) consists of, given the first one, the state-of-the-art on SRL will bea sentence, detecting basic event structures such overviewed, including: main techniques applied,as “who” did “what” to “whom”, “when” and existing systems, and lessons learned from the“where”. From a linguistic point of view, a key CoNLL and SemEval evaluation exercises. Thiscomponent of the task corresponds to identifying part will include a critical review of current prob-the semantic arguments filling the roles of the sen- lems and the identification of the main challengestence predicates. Typical predicate semantic argu- for the future. The second part is devoted to thements include Agent, Patient, and Instrument, but lines of research oriented to overcome current lim-semantic roles may also be found as adjuncts (e.g., itations. This part will include an analysis ofLocative, Temporal, Manner, and Cause). The the relation between syntax and SRL, the devel-identification of such event frames holds potential opment of joint systems for integrated syntactic-for significant impact in many NLP applications, semantic analysis, generalization across corpora,such as Information Extraction, Question Answer- and engineering of truly semantic features. Seeing, Summarization and Machine Translation. the outline below. Recently, the compilation and manual annota- 1. Introductiontion with semantic roles of several corpora has • Problem definition and propertiesenabled the development of supervised statistical • Importance of SRLapproaches to SRL, which has become a well- • Main computational resources and systems avail-defined task with a substantial body of work and able for SRLcomparative evaluation. Significant advances in 2. State-of-the-art SRL systemsmany directions have been reported over the last • Architectureseveral years, including but not limited to: ma- • Training of different componentschine learning algorithms and architectures spe- • Feature engineeringcialized for the task, feature engineering, inference 3. Empirical evaluation of SRL systemsto force coherent solutions, and system combina-tions. • Evaluation exercises at SemEval and CoNLL conferences However, despite all the efforts and the con- • Main lessons learnedsiderable degree of maturity of the SRL technol- 4. Current problems and challengesogy, the use of SRL systems in real-world ap-plications has so far been limited and, certainly, 5. Keys for future progressbelow the initial expectations. This fact has to • Relation to syntax: joint learning of syntactic anddo with the weaknesses and limitations of current semantic dependenciessystems, which have been highlighted by many • Generalization across domains and text genres • Use of semantic knowledgeof the evaluation exercises and keep unresolved • SRL systems in applicationsfor a few years (e.g., poor generalization acrosscorpora, low scalability and efficiency, knowledge 6. Conclusionspoor features, too high complexity, absolute per-formance below 90%, etc.). 3 Tutorial Abstracts of ACL-IJCNLP 2009, page 3, Suntec, Singapore, 2 August 2009. c 2009 ACL and AFNLP ...