570 Hits in 3.9 sec

Joint Apposition Extraction with Syntactic and Semantic Constraints

Will Radford, James R. Curran
2013 Annual Meeting of the Association for Computational Linguistics  
Appositions are adjacent NPs used to add information to a discourse. We propose systems exploiting syntactic and semantic constraints to extract appositions from OntoNotes.  ...  Our joint log-linear model outperforms the state-of-the-art Favre and Hakkani-Tür (2009) model by ∼10% on Broadcast News, and achieves 54.3% Fscore on multiple genres.  ...  Thanks must also go to Benoit Favre for his clear writing and help answering our questions as we replicated his dataset and system.  ... 
dblp:conf/acl/RadfordC13 fatcat:ntnklyobwbavjoyxbk662qxttm

Coreference Resolution for Structured Drug Product Labels

Halil Kilicoglu, Dina Demner-Fushman
2014 Proceedings of BioNLP 2014  
Enhancements include resolution of set/instance anaphora, recognition of appositive constructions and wider use of UMLS semantic knowledge.  ...  We obtained an improvement of 40% over the baseline with unweighted average F 1 -measure using B-CUBED, MUC, and CEAF metrics.  ...  The candidate antecedents are then recognized using syntactic (person, gender and number agreement, head word matching) and semantic (hypernym and UMLS semantic type matching) constraints.  ... 
doi:10.3115/v1/w14-3407 dblp:conf/bionlp/KilicogluD14 fatcat:5wl4qh27mjc73mccflpecbnfge

Joint Syntactic and Semantic Parsing with Combinatory Categorial Grammar

Jayant Krishnamurthy, Tom M. Mitchell
2014 Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)  
We present an approach to training a joint syntactic and semantic parser that combines syntactic training information from CCGbank with semantic training information from a knowledge base via distant supervision  ...  A semantic evaluation demonstrates that this parser produces logical forms better than both comparable prior work and a pipelined syntax-then-semantics approach.  ...  We additionally thank Jamie Callan and Chris Ré's Hazy group for collecting and processing the Wikipedia corpus.  ... 
doi:10.3115/v1/p14-1112 dblp:conf/acl/KrishnamurthyM14 fatcat:xgjozkgxxndy7pr55rpjchlodu

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  
Moreover, the inherent ambiguities caused by verbal coordination and relative clauses make semantic analysis of Chinese more difficult than the syntactic analysis of Chinese.  ...  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  ...  applied a joint model that performed syntactic parsing and semantic parsing at the same time.  ... 
dblp:conf/iwpt/YuMMWT11 fatcat:ljbapnrtgfejxaxevgizxvdhza

Bio-SCoRes: A Smorgasbord Architecture for Coreference Resolution in Biomedical Text

Halil Kilicoglu, Dina Demner-Fushman, Tudor Groza
2016 PLoS ONE  
One of the difficulties in coreference resolution stems from the fact that distinct types of coreference (e.g., anaphora, appositive) are expressed with a variety of lexical and syntactic means (e.g.,  ...  For development and evaluation, we used a corpus of structured drug labels annotated with fine-grained coreference information.  ...  Acknowledgments We thank Sonya Shooshan and Laritza Rodriguez for their contributions to the annotation study. This work was supported by the intramural research program at the U.S.  ... 
doi:10.1371/journal.pone.0148538 pmid:26934708 pmcid:PMC4774913 fatcat:eqtpgxqjivg2rgn4oqbpbiiqqq

Stanford's Multi-Pass Sieve Coreference Resolution System at the CoNLL-2011 Shared Task

Heeyoung Lee, Yves Peirsman, Angel X. Chang, Nathanael Chambers, Mihai Surdeanu, Dan Jurafsky
2011 Conference on Computational Natural Language Learning  
Our system is a collection of deterministic coreference resolution models that incorporate lexical, syntactic, semantic, and discourse information.  ...  Our system was ranked first in both tracks, with a score of 57.8 in the closed track and 58.3 in the open track.  ...  Any opinions, findings, and conclusion or recommendations expressed in this material are those of the authors and do not necessarily reflect the view of the Air Force Research Laboratory (AFRL). 5 See  ... 
dblp:conf/conll/LeePCCSJ11 fatcat:xsi2vr5lbjhrrb5ygghvyxwxxu

Inducing Terminology for Lexical Acquisition

Roberto Basili, Gianluca De Rossi, Maria Teresa Pazienza
1997 Conference on Empirical Methods in Natural Language Processing  
Terminology is seen as the acquisition of domain specific knowledge (i.e. semantic features, selectional restrictions) for complex terms and /or unknown words.  ...  This has useful implications on more complex text processing tasks (e.g. information extraction). An hybrid symbolic and probabilistic approach to terminology extraction has been defined.  ...  Lexical acquisition based on collocations between terms (and not simple lemmas) provides more granular information on lexical senses as well as (syntactic or semantic) selectional constraints.  ... 
dblp:conf/emnlp/BasiliRP97 fatcat:rtms7gvnfrcj5ltbtsmih7xrdu

Empirical Methods in Information Extraction

Claire Cardie
1997 The AI Magazine  
Generally, an information-extraction system takes as input an unrestricted text and "summarizes" the text with respect to a prespecified topic or domain of interest: It finds useful information about the  ...  The author presents a generic architecture for information-extraction systems and then surveys the learning algorithms that have been developed to address the problems of accuracy, portability, and knowledge  ...  , and (3) a discourse-level analysis of the syntactic and semantic representations.  ... 
doi:10.1609/aimag.v18i4.1322 dblp:journals/aim/Cardie97 fatcat:acl2jzvlvzhalaqyipekztjyem


W. Lehnert, J. McCarthy, S. Soderland, E. Riloff, C. Cardie, J. Peterson, F. Feng, C. Dolan, S. Goldman
1993 Proceedings of a workshop on held at Fredericksburg, Virginia September 19-23, 1993 -  
The views expressed in this paper are those of the authors and should not be interpreted to represent opinions or policies of the United States Government.  ...  These CNs extract a number of key noun phrases, and assign semantic features to these noun phrases based on soft constraints in the CN definition.  ...  We isolate compound noun phrases that are syntactically consistent with appositive constructions and pass these NP pairs on to a coreference classifier.  ... 
doi:10.3115/1119149.1119174 dblp:conf/tipster/LehnertMSRCPF93 fatcat:ltogt5x62bcsth5prudfnm2on4

Context-Preserving Text Simplification [article]

Christina Niklaus, Matthias Cetto, André Freitas, Siegfried Handschuh
2021 arXiv   pre-print
A comparative analysis with the annotations contained in the RST-DT shows that we are able to capture the contextual hierarchy between the split sentences with a precision of 89% and reach an average precision  ...  We present a context-preserving text simplification (TS) approach that recursively splits and rephrases complex English sentences into a semantic hierarchy of simplified sentences.  ...  Vanessa Wei Feng and Graeme Hirst. 2014. A linear- time bottom-up discourse parser with constraints and post-editing.  ... 
arXiv:2105.11178v1 fatcat:c4feprhparfwhlr7pgptld5u54

An Algorithm for Anaphora Resolution in Spanish Texts

Manuel Palomar, Antonio Ferrández, Lidia Moreno, Patricio Martínez-Barco, Jesús Peral, Maximiliano Saiz-Noeda, Rafael Muñoz
2001 Computational Linguistics  
We define a list of constraints and preferences for different types of pronominal expressions, and we document in detail the importance of each kind of knowledge (lexical, morphological, syntactic, and  ...  The paper also provides a definition for syntactic conditions on Spanish NP-pronoun noncoreference using partial parsing.  ...  Our work has been supported by the Spanish government (CICYT) with Grant TIC97-0671-C02-01/02.  ... 
doi:10.1162/089120101753342662 fatcat:or6ukih3bjhynbmxjgxxxvhl7u


W. Lehnert, J. McCarthy, S. Soderland, E. Riloff, C. Cardie, J. Peterson, F. Feng, C. Dolan, S. Goldman
1993 Proceedings of the 5th conference on Message understanding - MUC5 '93  
Notice that different CNs picked up "BRIDGESTONE SPORTS CO." with incompatible semantic features (it was associated with both a joint venture and a joint venture parent feature). extracted NPs rejected  ...  These CNs extract a number of key noun phrases, and assign semantic features to these noun phrases based on soft constraints in the CN definition.  ... 
doi:10.3115/1072017.1072043 dblp:conf/muc/LehnertMSRCPFDG93 fatcat:4puekaynhngspjcfp3torlhz2u

Scalable Semantic Parsing with Partial Ontologies

Eunsol Choi, Tom Kwiatkowski, Luke Zettlemoyer
2015 Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)  
We study this problem on two newly introduced large-scale noun phrase datasets, and present a new semantic parsing model and semi-supervised learning approach for reasoning with partial ontological support  ...  Experiments demonstrate strong performance on two tasks: referring expression resolution and entity attribute extraction.  ...  The authors thank Xiao Ling for providing the apposition data, and Yoav Artzi, Nicholas FitzGerald, Mike Lewis, Sameer Singh and Mark Yatskar for discussion and comments.  ... 
doi:10.3115/v1/p15-1127 dblp:conf/acl/ChoiKZ15 fatcat:xbev4zqhxzg23ja5ssiabdusqi

Decomposing Semantic Inferences

Elena Cabrio, Bernardo Magnini
2014 Linguistic Issues in Language Technology  
between the linguistic and the logical dimensions of semantic inferences emerges and can be empirically observed.  ...  Beside formal approaches to semantic inference that rely on logical representation of meaning, the notion of Textual Entailment (TE) has been proposed as an applied framework to capture major semantic  ...  Sara Tonelli for her help and availability in the annotation phase.  ... 
doi:10.33011/lilt.v9i.1319 fatcat:bhmnv2kfozd2pj6dprwtn5base

The generic information extraction system

Jerry R. Hobbs
1993 Proceedings of the 5th conference on Message understanding - MUC5 '93  
Appositives can be attached to their head nouns with high reliability, as can genitives, "of" prepositional phrases, and perhaps some other prepositional phrases.  ...  Sentence are parsed bottom-up, with top-down constraints being applied. As fragmentary parsing becomes more prevalent, the top-down constraints cannot be used as much.  ... 
doi:10.3115/1072017.1072029 dblp:conf/muc/Hobbs93 fatcat:6nrq73rhs5cdpev4znsbi4wsym
« Previous Showing results 1 — 15 out of 570 results