Arc-swift: A Novel Transition System for Dependency Parsing
نویسندگان
چکیده
Transition-based dependency parsers often need sequences of local shift and reduce operations to produce certain attachments. Correct individual decisions hence require global information about the sentence context and mistakes cause error propagation. This paper proposes a novel transition system, arc-swift, that enables direct attachments between tokens farther apart with a single transition. This allows the parser to leverage lexical information more directly in transition decisions. Hence, arc-swift can achieve significantly better performance with a very small beam size. Our parsers reduce error by 3.7–7.6% relative to those using existing transition systems on the Penn Treebank dependency parsing task and English Universal Dependencies.
منابع مشابه
Universal Dependency Parser: A Single Parser for Many Languages on Arc-Swift
Dependency parsing has been a longstanding task in NLP with a recent boost in performance thanks to neural network models. However, most dependency parsers are monolingual–a single parser is trained per language–and utilize transitionbased systems that are limited to local information. We utilize a novel transitionbased system, arc-swift, proposed in [1] that incorporates both local and global ...
متن کاملAn improved joint model: POS tagging and dependency parsing
Dependency parsing is a way of syntactic parsing and a natural language that automatically analyzes the dependency structure of sentences, and the input for each sentence creates a dependency graph. Part-Of-Speech (POS) tagging is a prerequisite for dependency parsing. Generally, dependency parsers do the POS tagging task along with dependency parsing in a pipeline mode. Unfortunately, in pipel...
متن کاملDynamic Programming Algorithms for Transition-Based Dependency Parsers
We develop a general dynamic programming technique for the tabulation of transition-based dependency parsers, and apply it to obtain novel, polynomial-time algorithms for parsing with the arc-standard and arc-eager models. We also show how to reverse our technique to obtain new transition-based dependency parsers from existing tabular methods. Additionally, we provide a detailed discussion of t...
متن کاملTransition-Based Parsing
Transition-based models for dependency parsing use a factorization defined in terms of a transition system, or abstract state machine. In this lecture, I will introduce the arc-eager and arcstandard transition systems for dependency parsing (§1) and discuss two different approaches to learning and decoding with these models: greedy classifier-based parsing (§2) and beam search and structured le...
متن کاملArc-Hybrid Non-Projective Dependency Parsing with a Static-Dynamic Oracle
We extend the arc-hybrid transition system for dependency parsing with a SWAP transition that enables reordering of the words and construction of non-projective trees. Although this extension potentially breaks the arc-decomposability of the transition system, we show that the existing dynamic oracle can be modified and combined with a static oracle for the SWAP transition. Experiments on five ...
متن کامل