tailieunhanh - Báo cáo khoa học: "Finding non-local dependencies: beyond pattern matching"

We describe an algorithm for recovering non-local dependencies in syntactic dependency structures. The patternmatching approach proposed by Johnson (2002) for a similar task for phrase structure trees is extended with machine learning techniques. The algorithm is essentially a classifier that predicts a nonlocal dependency given a connected fragment of a dependency structure and a set of structural features for this fragment. | Finding non-local dependencies beyond pattern matching Valentin Jijkoun Language and Inference Technology Group ILLC University of Amsterdam jijkoun@ Abstract We describe an algorithm for recovering non-local dependencies in syntactic dependency structures. The patternmatching approach proposed by Johnson 2002 for a similar task for phrase structure trees is extended with machine learning techniques. The algorithm is essentially a classifier that predicts a nonlocal dependency given a connected fragment of a dependency structure and a set of structural features for this fragment. Evaluating the algorithm on the Penn Treebank shows an improvement of both precision and recall compared to the results presented in Johnson 2002 . 1 Introduction Non-local dependencies also called long-distance long-range or unbounded appear in many frequent linguistic phenomena such as passive WH-movement control and raising etc. Although much current research in natural language parsing focuses on extracting local syntactic relations from text nonlocal dependencies have recently started to attract more attention. In Clark et al. 2002 long-range dependencies are included in parser s probabilistic model while Johnson 2002 presents a method for recovering non-local dependencies after parsing has been performed. More specifically Johnson 2002 describes a pattern-matching algorithm for inserting empty nodes and identifying their antecedents in phrase structure trees or to put it differently for recovering non-local dependencies. From a training corpus with annotated empty nodes Johnson s algorithm first extracts those local fragments of phrase trees which connect empty nodes with their antecedents thus licensing corresponding non-local dependencies. Next the extracted tree fragments are used as patterns to match against previously unseen phrase structure trees when a pattern is matched the algorithm introduces a corresponding non-local dependency inserting an empty node and .

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.