An Incremental Algorithm for Transition-based CCG Parsing

Abstract

Incremental parsers have potential advantages for applications like language modeling for machine translation and speech recognition. We describe a new algorithm for incremental transition-based Combinatory Categorial Grammar parsing. As English CCGbank derivations are mostly right branching and non-incremental, we design our algorithm based on the dependencies resolved rather than the derivation. We introduce two new actions in the shift-reduce paradigm based on the idea of 'revealing' (Pareschi and Steedman, 1987) the required information during parsing. On the standard CCGbank test data, our algorithm achieved improvements of 0.88% in labeled and 2.0% in unlabeled F-score over a greedy non-incremental shift-reduce parser.

A Transition-Based Directed Acyclic Graph Parser for UCCA

“…Transition-based techniques are a natural starting point for UCCA parsing, given the conceptual similarity of UCCA's distinctions, centered around predicate-argument structures, to distinctions expressed by dependency schemes, and the achievements of transition-based methods in dependency parsing (Dyer et al, 2015;Andor et al, 2016;Kiperwasser and Goldberg, 2016). We are further motivated by the strength of transition-based methods in related tasks, including dependency graph parsing (Sagae and Tsujii, 2008;Ribeyre et al, 2014;Tokgöz and Eryigit, 2015), constituency parsing (Sagae and Lavie, 2005;Zhang and Clark, 2009;Zhu et al, 2013;Maier, 2015;Maier and Lichte, 2016), AMR parsing (Wang et al, 2015a(Wang et al, ,b, 2016Misra and Artzi, 2016;Goodman et al, 2016;Zhou et al, 2016;Damonte et al, 2017) and CCG parsing (Zhang and Clark, 2011;Ambati et al, 2015Ambati et al, , 2016.…”

Shift-Reduce CCG Parsing using Neural Network Models

“…While the majority of CCG parsers are chart-based (Clark and Curran, 2007;Lewis and Steedman, 2014a), there has been some work on shift-reduce CCG parsing (Zhang and Clark, 2011;Xu et al, 2014;Ambati et al, 2015). Zhang and Clark (2011) used a global linear model trained discriminatively with the averaged perceptron (Collins, 2002) and beam search for their shift-reduce CCG parser.…”

“…A dependency model for shift-reduce CCG parsing using a dynamic oracle technique (Goldberg and Nivre, 2012) was developed by Xu et al (2014). Ambati et al (2015) presented an incremental algorithm for transition based CCG parsing which introduced two novel revealing actions to overcome the consequences of the greedy nature of the previous parsers.…”

“…There is an improvement of 2.14% in UF and 2.4% in LF, when both the parsers used maximum-entropy (C&C) taggers. We also experimented with the revealing based incremental algorithm of Ambati et al (2015). Neural network parser gave better results than the perceptron parser for the incremental algorithm as well.…”

LSTM CCG Parsing

“…Most work on CCG parsing has either used CKY chart parsing (Hockenmaier, 2003;Clark and Curran, 2007;Fowler and Penn, 2010;Auli and Lopez, 2011a) or shift-reduce algorithms (Zhang and Clark, 2011;Xu et al, 2014;Ambati et al, 2015). These methods rely on beam-search to cope with the huge space of possible CCG parses.…”