tailieunhanh - Báo cáo khoa học: "Head-driven Transition-based Parsing with Top-down Prediction"

This paper presents a novel top-down headdriven parsing algorithm for data-driven projective dependency analysis. This algorithm handles global structures, such as clause and coordination, better than shift-reduce or other bottom-up algorithms. Experiments on the English Penn Treebank data and the Chinese CoNLL-06 data show that the proposed algorithm achieves comparable results with other data-driven dependency parsing algorithms. | Head-driven Transition-based Parsing with Top-down Prediction Katsuhiko Hayashi Taro Watanabe Masayuki Asahara Yuji Matsumoto Nara Institute of Science and Technology Ikoma Nara 630-0192 Japan National Institute of Information and Communications Technology Sorakugun Kyoto 619-0289 Japan National Institute for Japanese Language and Linguistics Tachikawa Tokyo 190-8561 Japan katsuhiko-h@ masayu-a@ matsu@ Abstract This paper presents a novel top-down head-driven parsing algorithm for data-driven projective dependency analysis. This algorithm handles global structures such as clause and coordination better than shift-reduce or other bottom-up algorithms. Experiments on the English Penn Treebank data and the Chinese CoNLL-06 data show that the proposed algorithm achieves comparable results with other data-driven dependency parsing algorithms. 1 Introduction Transition-based parsing algorithms such as shift-reduce algorithms Nivre 2004 Zhang and Clark 2008 are widely used for dependency analysis because of the efficiency and comparatively good performance. However these parsers have one major problem that they can handle only local information. Isozaki et al. 2004 pointed out that the drawbacks of shift-reduce parser could be resolved by incorporating top-down information such as root finding. This work presents an O n2 top-down head-driven transition-based parsing algorithm which can parse complex structures that are not trivial for shift-reduce parsers. The deductive system is very similar to Earley parsing Earley 1970 . The Earley prediction is tied to a particular grammar rule but the proposed algorithm is data-driven following the current trends of dependency parsing Nivre 2006 McDonald and Pereira 2006 Koo et al. 2010 . To do the prediction without any grammar rules we introduce a weighted prediction that is to predict lower nodes from higher nodes with a statistical model. 657 To improve parsing .

TỪ KHÓA LIÊN QUAN
crossorigin="anonymous">
Đã phát hiện trình chặn quảng cáo AdBlock
Trang web này phụ thuộc vào doanh thu từ số lần hiển thị quảng cáo để tồn tại. Vui lòng tắt trình chặn quảng cáo của bạn hoặc tạm dừng tính năng chặn quảng cáo cho trang web này.