A Transition-Based System for Joint Lexical and Syntactic Analysis

Abstract

We present a transition-based system that jointly predicts the syntactic structure and lexical units of a sentence by building two structures over the input words: a syntactic dependency tree and a forest of lexical units including multiword expressions (MWEs). This combined representation allows us to capture both the syntactic and semantic structure of MWEs, which in turn enables deeper downstream semantic analysis, especially for semicompositional MWEs. The proposed system extends the arc-standard transition system for dependency parsing with transitions for building complex lexical units. Experiments on two different data sets show that the approach significantly improves MWE identification accuracy (and sometimes syntactic accuracy) compared to existing joint approaches.

USzeged: Identifying Verbal Multiword Expressions with POS Tagging and Parsing Techniques

“…Our system works through the connection of MWEs and parsing, an approach described by many sources (Constant and Nivre, 2016;Nasr et al, 2015;Candito and Constant, 2014;Green et al, 2011;Waszczuk et al, 2016;Wehrli et al, 2010;Green et al, 2013) and is one the basic ideas behind the work done by the PARSEME group 2 .…”

The ATILF-LLF System for Parseme Shared Task: a Transition-based Verbal Multiword Expression Tagger

“…Constant and Nivre (2016) proposed a parsing algorithm that jointly predicts a syntactic dependency tree and a forest of lexical units including MWEs. In particular, in line with Nivre (2014), this system integrates special parsing mechanisms to deal with lexical analysis.…”

Automatic Annotation of Verbal Collocations in Modern Greek

“…Additionally, Nasr et al [8] have developed a joint parsing and MWE identification model for the detection and representation of ambiguous complex function words. Constant and Nivre [9] developed a transition-based parser which combines two factorized substructures: a standard tree representing the syntactic dependencies between the lexical elements of a sentence and a forest of lexical trees including MWE identified in the sentence. Many studies have focused on the automatic identification of Modern Greek collocations.…”