44 Hits in 6.6 sec

Semi-automatically Developing Chinese HPSG Grammar from the Penn Chinese Treebank for Deep Parsing

Kun Yu, Yusuke Miyao, Xiangli Wang, Takuya Matsuzaki, Jun'ichi Tsujii
2010 International Conference on Computational Linguistics  
In this paper, we introduce our recent work on Chinese HPSG grammar development through treebank conversion.  ...  Then, a large-scale lexicon is automatically extracted from the HPSG treebank.  ...  Conclusion and Future Work In this paper, we described the semi-automatic development of a Chinese HPSG grammar from the CTB. Grammatical constraints are first designed by hand.  ... 
dblp:conf/coling/YuMWMT10 fatcat:2jmggylnuba7leu4j5tfxiqw3a

Analysis of the Difficulties in Chinese Deep Parsing

Kun Yu, Yusuke Miyao, Takuya Matsuzaki, Xiangli Wang, Jun'ichi Tsujii
2011 International Workshop/Conference on Parsing Technologies  
This paper discusses the difficulties in Chinese deep parsing, by comparing the accuracy of a Chinese HPSG parser to the accuracy of an English HPSG parser and the commonly used Chinese syntactic parsers  ...  Analysis reveals that deep parsing for Chinese is more challenging than for English, due to the shortage of syntactic constraints of Chinese verbs, the widespread pro-drop, and the large distribution of  ...  With the hand-crafted conversion rules, Yu et al. (2010) built a Chinese HPSG Treebank semi-automatically from the Penn Chinese Treebank.  ... 
dblp:conf/iwpt/YuMMWT11 fatcat:ljbapnrtgfejxaxevgizxvdhza

A Survey of Syntactic-Semantic Parsing Based on Constituent and Dependency Structures [article]

Meishan Zhang
2020 arXiv   pre-print
Besides, we also review the closely-related topics such as cross-domain, cross-lingual and joint parsing models, parser application as well as corpus development of parsing in the article.  ...  Syntactic and semantic parsing has been investigated for decades, which is one primary topic in the natural language processing community. This article aims for a brief survey on this topic.  ...  There are several classical treebanks such as the Penn Treebanks of English and Chinese languages, which greatly promote the development of the parsing community.  ... 
arXiv:2006.11056v1 fatcat:pd22rciuxzdc5kvghaapjjyg3u

High-level methodologies for grammar engineering, introduction to the special issue

Denys Duchier, Yannick Parmentier
2015 Journal of Language Modelling  
Advances in the field have led to the development of environments for semi-automatic grammar engineering, borrowing ideas from compilation (grammar engineering is compared with software development) and  ...  This special issue reports on new trends in the field, where grammar engineering benefits from elaborate high-level methodologies and techniques, dealing with various issues (both theoretical and practical  ...  The authors first show how to semi-automatically extract such a grammar from a treebank of Vietnamese. In a second step, they use this grammar for deep parsing.  ... 
doi:10.15398/jlm.v3i1.117 fatcat:c2bo6drgmrg4pasyvgb5x7bmpq

Deep Dependency Graph Conversion in English

Jinho Choi
2017 International Workshop on Treebanks and Linguistic Theories  
This paper presents a method for the automatic conversion of constituency trees into deep dependency graphs consisting of primary, secondary, and semantic relations.  ...  , which can reduce the bundle of developing another layer of annotation dedicated for predicate argument structures.  ...  A special thank is due to professor Martha Palmer at the University of Colorado Boulder, who had encouraged the author to develop this representation during his Ph.D. program.  ... 
dblp:conf/tlt/Choi17 fatcat:zgripxhr2jdmdjhakiba7s4ysa

Computational linguistics and grammar engineering [article]

Emily M. Bender, Guy Emerson
2021 Zenodo  
We discuss the relevance of HPSG for computational linguistics, and the relevance of computational linguistics for HPSG, including: the theoretical and computational infrastructure required to carry out  ...  computational studies with HPSG; computational resources developed within HPSG; how those resources are deployed, for both practical applications and linguistic research; and finally, a sampling of linguistic  ...  Acknowledgments We would like to thank Stephan Oepen for helpful comments on an early draft of this chapter, Stefan Müller for detailed comments as volume editor and Elizabeth Pankratz for careful copy  ... 
doi:10.5281/zenodo.5599867 fatcat:qfrfqb5fnngdtbbqhhm3dkmmua

Statistical Deep Parsing for Spanish: Abridged Version

Luis Chiruzzo
2022 CLEI Electronic Journal  
This document presents the development of a statistical HPSG parser for Spanish.  ...  We describe the HPSG grammar adapted to Spanish we designed and the construction of our corpus.  ...  The rules were developed manually and they used manual and semi-automatic processes to build the lexicon [9] .  ... 
doi:10.19153/cleiej.25.1.2 fatcat:k5jdrcbqcjc5vccmw5x4egckke

Valency-Augmented Dependency Parsing

Tianze Shi, Lillian Lee
2018 Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing  
We further show that our approach can be applied to an ostensibly different formalism and dataset, Tree Adjoining Grammar as extracted from the Penn Treebank; there, we outperform the previous stateof-the-art  ...  We present a complete, automated, and efficient approach for utilizing valency analysis in making dependency parsing decisions.  ...  Acknowledgments We thank the three anonymous reviewers for their insightful comments, Jungo Kasai for assistance in setting up the TAG parsing experiments, and Xilun Chen, Jason Eisner, Jungo Kasai and  ... 
doi:10.18653/v1/d18-1159 dblp:conf/emnlp/ShiL18 fatcat:p33x22qewzdqrkryzwlarlyebm

Sentence Meaning Representations across Languages: What Can We Learn from Existing Frameworks?

Zdeněk Žabokrtský, Magda Ševčíková, Daniel Zeman
2020 Computational Linguistics  
This article gives an overview of how sentence meaning is represented in eleven deep-syntactic frameworks, ranging from those based on linguistic theories elaborated for decades to rather lightweight NLP-motivated  ...  GX20-16819X of the Czech Science Foundation. We would like to thank the three anonymous reviewers for their detailed comments and insightful suggestions.  ...  We also thank Eva Hajičová, Jarmila Panevová, and Markéta Lopatková for numerous valuable comments on the manuscript. All remaining errors are of course our own.  ... 
doi:10.1162/coli_a_00385 fatcat:kku2zljemfhfpprixiv2lczjme

Message from the general chair

Benjamin C. Lee
2015 2015 IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS)  
To maximize the utility of the injected knowledge, we deploy a learning-based multi-sieve approach and develop novel entity-based features.  ...  Our system gives a better performance than all the learning-based systems from the CoNLL-2011 shared task on the same dataset.  ...  Our approach can significantly advance the state-of-the-art parsing accuracy on two widely used target treebanks (Penn Chinese Treebank 5.1 and 6.0) using the Chinese Dependency Treebank as the source  ... 
doi:10.1109/ispass.2015.7095776 dblp:conf/ispass/Lee15 fatcat:ehbed6nl6barfgs6pzwcvwxria

Abstract Syntax as Interlingua: Scaling Up the Grammatical Framework from Controlled Languages to Robust Pipelines

Aarne Ranta, Krasimir Angelov, Normunds Gruzitis, Prasanth Kolachina
2020 Computational Linguistics  
This makes it possible for GF to utilize data from the other approaches and to build robust pipelines.  ...  The development of GF started in 1998, first as a tool for controlled language implementations, where it has gained an established position in both academic and commercial projects.  ...  Acknowledgments The authors want to thank the anonymous referees for their substantial and insightful comments.  ... 
doi:10.1162/coli_a_00378 fatcat:pgydeto4sncmngs2oonpm7s2gm

Syntax and Parsing of Semitic Languages [chapter]

Reut Tsarfaty
2014 Natural Language Processing of Semitic Languages  
The grammar of Semitic languages is different from that of English and many other languages.  ...  While parsing Semitic languages can already be made quite accurate using the present techniques, remaining challenges leave ample space for future research.  ...  The writing of this chapter was partially funded by the Swedish research council, for which we are grateful.  ... 
doi:10.1007/978-3-642-45358-8_3 dblp:series/tanlp/Tsarfaty14 fatcat:ntl4l44okvft5c2i72iz4tcyva

An HPSG-based Shared-Grammar for the Chinese Languages: ZHONG [|]

Zhenzhen Fan, Sanghoun Song, Francis Bond
2015 Proceedings of the Grammar Engineering Across Frameworks (GEAF) 2015 Workshop   unpublished
The grammars also have facilities for robust parsing, sentence generation, and unknown word handling.  ...  This paper introduces our attempts to model the Chinese language using HPSG and MRS. Chinese refers to a family of various languages including Mandarin Chinese, Cantonese, Min, etc.  ...  Acknowledgments We would like to express special thanks to Justin Chunlei Yang and Dan Flickinger for their enormous work on ManGO, which our current grammar is based on.  ... 
doi:10.18653/v1/w15-3303 fatcat:mbzw2ucilnbgzfc2ufhileyffm

Multiword Expression Processing: A Survey

Mathieu Constant, Gülşen Eryiğit, Johanna Monti, Lonneke van der Plas, Carlos Ramisch, Michael Rosner, Amalia Todirascu
2017 Computational Linguistics  
For each of the two MWE processing subtasks and for each of the two use cases, we conclude on open issues and research perspectives.  ...  It also elucidates the interactions between MWE processing and two use cases: Parsing and machine translation.  ...  This work has been partially funded by the French National Research Agency (ANR) through the PARSEME-FR project (ANR-14-CERA-0001) and by a TUBITAK 1001 grant (no: 112E276).  ... 
doi:10.1162/coli_a_00302 fatcat:rjrfyfbfpfblfbtwpbdqnpgsiu

Left-corner Methods for Syntactic Modeling with Universal Structural Constraints [article]

Hiroshi Noji
2016 arXiv   pre-print
In this task, the input to the algorithm is a collection of sentences, from which the model tries to extract the salient patterns on them as a grammar.  ...  We examine the effectiveness of our approach on many treebanks, and demonstrate that often our constraint leads to better parsing performance.  ...  Most treebanks are created by hand in this project except the following two languages: English: Automatically convert from the Wall Street Journal portion of the Penn Treebank (Marcus et al., 1993) (  ... 
arXiv:1608.00293v1 fatcat:7uf3c3zrtrdpzokqq6ilgx5bb4
« Previous Showing results 1 — 15 out of 44 results