Filters








19,546 Hits in 2.5 sec

Minimally lexicalized dependency parsing

Daisuke Kawahara, Kiyotaka Uchimoto
2007 Proceedings of the 45th Annual Meeting of the ACL on Interactive Poster and Demonstration Sessions - ACL '07   unpublished
Experimental results indicate that minimal or low lexicalization is sufficient for parsing accuracy.  ...  This paper discusses our investigation into the effectiveness of lexicalization in dependency parsing.  ...  Minimally Lexicalized Dependency Parsing We present a simple method for changing the degree of lexicalization in dependency parsing.  ... 
doi:10.3115/1557769.1557829 fatcat:ldrcp3m2mnbj5kpu26fywdqkei

What is the minimal set of fragments that achieves maximal parse accuracy?

Rens Bod
2001 Proceedings of the 39th Annual Meeting on Association for Computational Linguistics - ACL '01  
We aim at finding the minimal set of fragments which achieves maximal parse accuracy in Data Oriented Parsing.  ...  We isolate some dependency relations which previous models neglect but which contribute to higher parse accuracy.  ...  While early head-lexicalized grammars restricted the fragments to the locality of headwords (e.g.  ... 
doi:10.3115/1073012.1073022 dblp:conf/acl/Bod01 fatcat:krtmuzxu4zhbxa2uivkqvee4xq

What is the minimal set of fragments that achieves maximal parse accuracy? [article]

Rens Bod
2001 arXiv   pre-print
We aim at finding the minimal set of fragments which achieves maximal parse accuracy in Data Oriented Parsing.  ...  We isolate some dependency relations which previous models neglect but which contribute to higher parse accuracy.  ...  While early head-lexicalized grammars restricted the fragments to the locality of headwords (e.g.  ... 
arXiv:cs/0110050v1 fatcat:3efifzmkgraopixzcjj2ekovma

Do All Fragments Count? [article]

Rens Bod
2000 arXiv   pre-print
We aim at finding the minimal set of fragments which achieves maximal parse accuracy in Data Oriented Parsing.  ...  We isolate a number of dependency relations which previous models neglect but which contribute to higher parse accuracy.  ...  Introduction One of the main goals in statistical natural language parsing is to find the minimal set of statistical dependencies (between words and syntactic structures) which achieves maximal parse accuracy  ... 
arXiv:cs/0011040v1 fatcat:jrhoel7sdzd5lksybupijiimte

Approximate Factoring for A* Search

Aria Haghighi, John DeNero, Dan Klein
2007 North American Chapter of the Association for Computational Linguistics  
We apply our approach to bitext parsing and lexicalized parsing, demonstrating its effectiveness in these domains.  ...  This work is supported by a DHS fellowship to the first 13 Since we cannot exhaustively parse with this model, we cannot compare our F1 to an exact search method. author and a Microsoft new faculty fellowship  ...  Lexicalized Parsing We next apply our technique to lexicalized parsing (Charniak, 1997; Collins, 1999).  ... 
dblp:conf/naacl/HaghighiDK07 fatcat:3nzv7a3w6bgqtfmfvqvivdajxa

Syntax-Based Translation With Bilingually Lexicalized Synchronous Tree Substitution Grammars

Jiajun Zhang, Feifei Zhai, Chengqing Zong
2013 IEEE Transactions on Audio, Speech, and Language Processing  
In this article, inspired by lexicalized PCFG, which is widely used in monolingual parsing, we propose to upgrade the STSG (synchronous tree substitution grammars)-based syntax translation model with bilingually  ...  lexicalized STSG.  ...  Depending on whether the input is a string or a parse tree, we divide these models into two categories: tree-based parsing models and string-based parsing models.  ... 
doi:10.1109/tasl.2013.2255283 fatcat:vhzwhxaghvf2nkrzyth3n2kfgq

Unlexicalized Transition-based Discontinuous Constituency Parsing [article]

Maximin Coavoux, Benoît Crabbé, Shay B. Cohen
2019 arXiv   pre-print
We compare it to lexicalized parsing models in order to address the question of lexicalization in the context of discontinuous constituency parsing.  ...  Lexicalized parsing models are based on the assumptions that (i) constituents are organized around a lexical head (ii) bilexical statistics are crucial to solve ambiguities.  ...  Lexicalized Transition System In order to assess the role of lexicalization in parsing, we introduce a second transition system, ML-GAP-LEX, which is designed (i) to be lexicalized (ii) to differ minimally  ... 
arXiv:1902.08912v1 fatcat:j43rpkvp35bk7lpmmpokularw4

Tree-gram Parsing: Lexical Dependencies and Structural Relations [article]

Khalil Sima'an
2000 arXiv   pre-print
It proposes that two widely used kinds of relations, lexical dependencies and structural relations, have complementary disambiguation capabilities.  ...  It presents a new model based on structural relations, the Tree-gram model, and reports experiments showing that structural relations should benefit from enrichment by lexical dependencies.  ...  Acknowledgements: I thank Remko Scha, Remko Bonnema, Walter Daelemans and Jakub Zavrel for illuminating discussions, Remko Bonnema for his pre-and post-parsing software, and the anonymous reviewers for  ... 
arXiv:cs/0011007v1 fatcat:veqvxpctb5db7o7pvr3b4uicgi

HPSG Parsing with Shallow Dependency Constraints

Kenji Sagae, Yusuke Miyao, Jun'ichi Tsujii
2007 Annual Meeting of the Association for Computational Linguistics  
We show that by using surface dependencies to constrain the application of wide-coverage HPSG rules, we can benefit from a number of parsing techniques designed for highaccuracy dependency parsing, while  ...  We present a novel framework that combines strengths from surface syntactic parsing and deep syntactic parsing to increase deep parsing accuracy, specifically by combining dependency and HPSG parsing.  ...  Typically, shallow parsing is used to create robust minimal recursion semantics, which are used as constraints to limit ambiguity during parsing.  ... 
dblp:conf/acl/SagaeMT07 fatcat:hn6cqldrujfi3bbnwfepvgwrui

A Distributed Representation-Based Framework for Cross-Lingual Transfer Parsing

Jiang Guo, Wanxiang Che, David Yarowsky, Haifeng Wang, Ting Liu
2016 The Journal of Artificial Intelligence Research  
This paper investigates the problem of cross-lingual transfer parsing, aiming at inducing dependency parsers for low-resource languages while using only training data from a resource-rich language (e.g  ...  Consequently, both lexical features and non-lexical features can be used in our model for cross-lingual transfer.  ...  Thus, this approach partially fills the gap of lexical features in cross-lingual learning of dependency parsing.  ... 
doi:10.1613/jair.4955 fatcat:mpkzaf774nabrbxq6u5n3lpxdu

Extracting Stochastic Grammars from Treebanks [chapter]

Rens Bod
2003 Text, Speech and Language Technology  
That is, the parse accuracy decreases (1) if the maximum size of the subtrees decreases, (2) if the maximum lexicalization of the subtrees decreases, (3) if the minimal frequency of the subtrees increases  ...  By a lexicalized subtree we mean a subtree whose yield or frontier contains one or more words. The more words a subtree contains, the more lexical dependencies are taken into account.  ... 
doi:10.1007/978-94-010-0201-1_19 fatcat:hrfhpnvvfvf6hoaka666awy2rm

Unlexicalized Transition-based Discontinuous Constituency Parsing

Maximin Coavoux, Benoît Crabbé, Shay B. Cohen
2019 Transactions of the Association for Computational Linguistics  
We compare it with lexicalized parsing models in order to address the question of lexicalization in the context of discontinuous constituency parsing.  ...  Lexicalized parsing models are based on the assumptions that (i) constituents are organized around a lexical head and (ii) bilexical statistics are crucial to solve ambiguities.  ...  Lexicalized Transition System In order to assess the role of lexicalization in parsing, we introduce a second transition system, ML-GAP-LEX, which is designed (i) to be lexicalized and (ii) to differ minimally  ... 
doi:10.1162/tacl_a_00255 fatcat:2uvdbibx7vesde2bzxdnqkkvda

Lexicalized Stochastic Modeling of Constraint-Based Grammars using Log-Linear Measures and EM Training [article]

Stefan Riezler, Detlef Prescher, Jonas Kuhn, Mark Johnson
2000 arXiv   pre-print
Also, a new class-based grammar lexicalization is presented, showing a 10% gain over unlexicalized models.  ...  Introduction Stochastic parsing models capturing contextual constraints beyond the dependencies of probabilistic context-free grammars (PCFGs) are currently the subject of intensive research.  ...  pure frequency statistics or classbased probabilities of head word dependencies.  ... 
arXiv:cs/0008034v1 fatcat:ty2zl26xxzcbppk35hzomb5pva

Explanation-based learning and finite state transducers: applications to parsing lexicalized tree adjoining grammars

B. SRINIVAS
1996 Natural Language Engineering  
In 7], we showed that combining the LTAG representation with the EBL technique provides a novel method for parsing based on a FST mechanism and demonstrated a speedup in parsing times on the ATIS corpus  ...  Explanation-based Learning techniques have been applied in NLP for speeding up parsing in limited domains.  ...  However, it must be noted that depending on the degree of abstraction from the lexical items, the generalized parse may be stored under di erent indices containing varying amounts of lexical speci c information  ... 
doi:10.1017/s1351324997001642 fatcat:4yucashhbvgj5h4owfapehpcbi

Semi-supervised Dependency Parsing using Lexical Affinities

Seyed Abolghasem Mirroshandel, Alexis Nasr, Joseph Le Roux
2012 Annual Meeting of the Association for Computational Linguistics  
Experiments on the French Treebank showed a relative decrease of the error rate of 7.1% Labeled Accuracy Score yielding the best parsing results on this treebank.  ...  Treebanks are not large enough to reliably model precise lexical phenomena. This deficiency provokes attachment errors in the parsers trained on such data.  ...  lexical dependencies between open POS, such as nouns, verbs and adjectives.  ... 
dblp:conf/acl/MirroshandelNR12 fatcat:tlb4l4uaazh6nbtsdxqbt33zne
« Previous Showing results 1 — 15 out of 19,546 results