A Full Non-Monotonic Transition System for Unrestricted Non-Projective Parsing
نویسندگان
چکیده
Restricted non-monotonicity has been shown beneficial for the projective arceager dependency parser in previous research, as posterior decisions can repair mistakes made in previous states due to the lack of information. In this paper, we propose a novel, fully non-monotonic transition system based on the non-projective Covington algorithm. As a non-monotonic system requires exploration of erroneous actions during the training process, we develop several non-monotonic variants of the recently defined dynamic oracle for the Covington parser, based on tight approximations of the loss. Experiments on datasets from the CoNLL-X and CoNLL-XI shared tasks show that a non-monotonic dynamic oracle outperforms the monotonic version in the majority of languages.
منابع مشابه
Non-Deterministic Oracles for Unrestricted Non-Projective Transition-Based Dependency Parsing
We study non-deterministic oracles for training non-projective beam search parsers with swap transitions. We map out the spurious ambiguities of the transition system and present two non-deterministic oracles as well as a static oracle that minimizes the number of swaps. An evaluation on 10 treebanks reveals that the difference between static and non-deterministic oracles is generally insignifi...
متن کاملEffective Online Reordering with Arc-Eager Transitions
We present a new transition system with word reordering for unrestricted nonprojective dependency parsing. Our system is based on decomposed arc-eager rather than arc-standard, which allows more flexible ambiguity resolution between a local projective and non-local crossing attachment. In our experiment on Universal Dependencies 2.0, we find our parser outperforms the ordinary swapbased parser ...
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 کاملIncremental Non-Projective Dependency Parsing
An open issue in data-driven dependency parsing is how to handle non-projective dependencies, which seem to be required by linguistically adequate representations, but which pose problems in parsing with respect to both accuracy and efficiency. Using data from five different languages, we evaluate an incremental deterministic parser that derives non-projective dependency structures in O(n2) tim...
متن کاملAn Improved Non-monotonic Transition System for Dependency Parsing
Transition-based dependency parsers usually use transition systems that monotonically extend partial parse states until they identify a complete parse tree. Honnibal et al. (2013) showed that greedy onebest parsing accuracy can be improved by adding additional non-monotonic transitions that permit the parser to “repair” earlier parsing mistakes by “over-writing” earlier parsing decisions. This ...
متن کامل