Transition-Based Left-Corner Parsing for Identifying PTB-Style Nonlocal Dependencies
نویسندگان
چکیده
This paper proposes a left-corner parser which can identify nonlocal dependencies. Our parser integrates nonlocal dependency identification into a transition-based system. We use a structured perceptron which enables our parser to utilize global features captured by nonlocal dependencies. An experimental result demonstrates that our parser achieves a good balance between constituent parsing and nonlocal dependency identification.
منابع مشابه
Incremental LTAG Parsing
We present a very efficient statistical incremental parser for LTAG-spinal, a variant of LTAG. The parser supports the full adjoining operation, dynamic predicate coordination, and non-projective dependencies, with a formalism of provably stronger generative capacity as compared to CFG. Using gold standard POS tags as input, on section 23 of the PTB, the parser achieves an f-score of 89.3% for ...
متن کاملA Three-Step Transition-Based System for Non-Projective Dependency Parsing
This paper presents a non-projective dependency parsing system that is transition-based and operates in three steps. The three steps include one classical method for projective dependency parsing and two inverse methods predicting separately the right and left non-projective dependencies. Splitting the parsing allows to increase the scores on both projective and non-projective dependencies comp...
متن کاملHierarchical Word Structure-based Parsing: A Feasibility Study on UD-style Dependency Parsing in Japanese
In applying word-based dependency parsing such as Universal Dependencies (UD) to Japanese, the uncertainty of word segmentation emerges for defining a word unit of the dependencies. We introduce the following hierarchical word structures to dependency parsing in Japanese: morphological units (a short unit word, SUW) and syntactic units (a long unit word, LUW). This paper describes the results o...
متن کاملLeft-corner Transitions on Dependency Parsing
We propose a transition system for dependency parsing with a left-corner parsing strategy. Unlike parsers with conventional transition systems, such as arc-standard or arc-eager, a parser with our system correctly predicts the processing difficulties people have, such as of center-embedding. We characterize our transition system by comparing its oracle behaviors with those of other transition s...
متن کاملImproving Graph-based Dependency Parsing with Decision History
This paper proposes an approach to improve graph-based dependency parsing by using decision history. We introduce a mechanism that considers short dependencies computed in the earlier stages of parsing to improve the accuracy of long dependencies in the later stages. This relies on the fact that short dependencies are generally more accurate than long dependencies in graph-based models and may ...
متن کامل