Results 21 to 30 of about 148 (104)

Combining constituent parsers [PDF]

open access: yesProceedings of Human Language Technologies: The 2009 Annual Conference of the North American Chapter of the Association for Computational Linguistics, Companion Volume: Short Papers on - NAACL '09, 2009
Combining the 1-best output of multiple parsers via parse selection or parse hybridization improves f-score over the best individual parser (Henderson and Brill, 1999; Sagae and Lavie, 2006). We propose three ways to improve upon existing methods for parser combination.
Victoria Fossum, Kevin Knight
openaire   +1 more source

Modeling Structure‐Building in the Brain With CCG Parsing and Large Language Models

open access: yesCognitive Science, Volume 47, Issue 7, July 2023., 2023
Abstract To model behavioral and neural correlates of language comprehension in naturalistic environments, researchers have turned to broad‐coverage tools from natural‐language processing and machine learning. Where syntactic structure is explicitly modeled, prior work has relied predominantly on context‐free grammars (CFGs), yet such formalisms are ...
Miloš Stanojević   +4 more
wiley   +1 more source

Parsing Chinese with Combinatory Categorial Grammar: A Linguistic and Computational Study

open access: yesComplexity, Volume 2022, Issue 1, 2022., 2022
Parsing Chinese language with CCG is very difficult because the architecture and assumptions of CCG do not fit well with facts from Chinese. Based on the concept of “realization” proposed by Zhu Dexi (1920–1992), this study sheds light on the discrepancy between CCG and Chinese syntax and puts forward a refined schema for Chinese compositionality.
Haixia Man   +4 more
wiley   +1 more source

Parser combination by reparsing [PDF]

open access: yesProceedings of the Human Language Technology Conference of the NAACL, Companion Volume: Short Papers on XX - NAACL '06, 2006
We present a novel parser combination scheme that works by reparsing input sentences once they have already been parsed by several different parsers. We apply this idea to dependency and constituent parsing, generating results that surpass state-of-the-art accuracy levels for individual parsers.
Kenji Sagae, Alon Lavie
openaire   +1 more source

K-best combination of syntactic parsers [PDF]

open access: yesProceedings of the 2009 Conference on Empirical Methods in Natural Language Processing Volume 3 - EMNLP '09, 2009
In this paper, we propose a linear model-based general framework to combine k-best parse outputs from multiple parsers. The proposed framework leverages on the strengths of previous system combination and re-ranking techniques in parsing by integrating them into a linear model.
Hui Zhang   +3 more
openaire   +1 more source

Parser combinators for Tigrinya and Oromo morphology

open access: closed, 2018
We present rule-based morphological parsers in the Tigrinya and Oromo languages, based on a parser-combinator rather than finite-state paradigm. This paradigm allows rapid development and ease of integration with other systems, although at the cost of non-optimal theoretical efficiency.
Littell, Patrick   +7 more
openaire   +2 more sources

Combining Czech Dependency Parsers [PDF]

open access: yes, 2006
In this paper we describe in detail two dependency parsing techniques developed and evaluated using the Prague Dependency Treebank 2.0 Then we propose two approaches for combining various existing parsers in order to obtain better accuracy The highest parsing accuracy reported in this paper is 85.84 %, which represents 1.86 % improvement compared to ...
Tomáš Holan, Zdeněk Žabokrtský
openaire   +1 more source

Parsley: optimising and improving parser combinators

open access: yes, 2023
Parser combinators are a functional abstraction for parsing that abstracts hand-written recursive-descent parsers behind a high-level set of combinators. While these kinds of parsers are popular in the functional programming community, they have been historically criticised: * Parser combinator performance is sub-par compared with handwritten parsers. *
openaire   +2 more sources

Home - About - Disclaimer - Privacy