tailieunhanh - Báo cáo khoa học: "Language-Independent Parsing with Empty Elements"

We present a simple, language-independent method for integrating recovery of empty elements into syntactic parsing. This method outperforms the best published method we are aware of on English and a recently published method on Chinese. | Language-Independent Parsing with Empty Elements Shu Cai and David Chiang USC Information Sciences Institute 4676 Admiralty Way Suite 1001 Marina del Rey Ca 90292 shucai chiang @ Yoav Goldberg Ben Gurion University of the Negev Department of Computer Science POB 653 Be er Shevi 84105 Israel yoavg@ Abstract We present a simple language-independent method for integrating recovery of empty elements into syntactic parsing. This method outperforms the best published method we are aware of on English and a recently published method on Chinese. 1 Introduction Empty elements in the syntactic analysis of a sentence are markers that show where a word or phrase might otherwise be expected to appear but does not. They play an important role in understanding the grammatical relations in the sentence. For example in the tree of Figure 2a the first empty element marks where John would be if believed were in the active voice someone believed. and the second empty element T marks where the man would be if who were not fronted John was believed to admire who . Empty elements exist in many languages and serve different purposes. In languages such as Chinese and Korean where subjects and objects can be dropped to avoid duplication empty elements are particularly important as they indicate the position of dropped arguments. Figure 1 gives an example of a Chinese parse tree with empty elements. The first empty element pro marks the subject of the whole sentence a pronoun inferable from context. The second empty element PRO marks the subject of the dependent VP shíshĩ falu tiáowén . The Penn Treebanks Marcus et al. 1993 Xue et al. 2005 contain detailed annotations of empty elements. Yet most parsing work based on these resources has ignored empty elements with some 212 NP 1 VP 1 -NONE- 1 ADVP 1 VP 1 pro 1 AD VV IP w NP VP zànshí zhongzhi for now suspend -NONE- VV NP PRO Affi NN NN shíshi 1 implement x falu tiáowén law clause Figure 1 Chinese parse tree with empty .

TÀI LIỆU LIÊN QUAN
TỪ KHÓA LIÊN QUAN