Filters








135 Hits in 7.0 sec

Using automatically labelled examples to classify rhetorical relations: an assessment

CAROLINE SPORLEDER, ALEX LASCARIDES
2006 Natural Language Engineering  
Our results suggest that training on this type of data may not be such a good strategy, as models trained in this way do not seem to generalise very well to unmarked data.  ...  Being able to identify which rhetorical relations (e.g., contrast or explanation) hold between spans of text is important for many natural language processing applications.  ...  We would like to thank Vasilis Karaiskos and Max Leadley-Brown for doing the manual annotations and Mirella Lapata for helpful suggestions and discussions.  ... 
doi:10.1017/s1351324906004451 fatcat:tpoak2bdrrbl5j6fxrbeuszssm

An unsupervised approach to recognizing discourse relations

Daniel Marcu, Abdessamad Echihabi
2001 Proceedings of the 40th Annual Meeting on Association for Computational Linguistics - ACL '02  
We present an unsupervised approach to recognizing discourse relations of CON-  ...  s corpus could identify at most 61/238 of the CONTRAST relations correctly. Because Carlson et al.'s corpus is small, all unmarked relations will be likely labeled as ELABORATIONs.  ...  This result is consistent with the discourse model proposed by Knott et al. (2001) , who suggest that ELABORATION relations are too ill-defined to be part of any discourse theory.  ... 
doi:10.3115/1073083.1073145 dblp:conf/acl/MarcuE02 fatcat:bzsnz73vnrbhbdrllrhry6k5n4

The chicken-and-egg problem in wordnet design: synonymy, synsets and constitutive relations

Marek Maziarz, Maciej Piasecki, Stanisław Szpakowicz
2013 Language Resources and Evaluation  
We propose to make a wordnet a net of words or, to be more precise, lexical units. We discuss our assumptions and present their implementation in a steadily growing Polish wordnet.  ...  A small set of constitutive relations allows us to construct synsets automatically out of groups of lexical units with the same connectivity.  ...  LUs belonging to one synset form an equivalence class with respect to those relations.  ... 
doi:10.1007/s10579-012-9209-9 fatcat:p5czauanrzgcbngpo6v2desyxi

Automatic Extraction of Causal Relations from Text using Linguistically Informed Deep Neural Networks

Tirthankar Dasgupta, Rupsa Saha, Lipika Dey, Abir Naskar
2018 Proceedings of the 19th Annual SIGdial Meeting on Discourse and Dialogue  
We have evaluated the performance of the proposed extraction model with respect to two baseline systems,one a rule-based classifier, and the other a conditional random field (CRF) based supervised model  ...  The extracted events and their relations are used to build a causal-graph after clustering and appropriate generalization, which is then used for predictive purposes.  ...  for lexical patterns Seed New Term Wordnet Gloss of Term Example due to corrode cause to deteriorate due to agent The acid corroded the metal.  ... 
doi:10.18653/v1/w18-5035 dblp:conf/sigdial/DasguptaSDN18 fatcat:zxsscfmmh5hrnpyptwgzfx6drq

Mapping wordnets from the perspective of inter-lingual equivalence

Ewa Katarzyna Rudnicka, Maciej Tomasz Piasecki, Tadeusz Piotrowski, Łukasz Grabowski, Francis Bond
2017 Cognitive Studies | Études cognitives  
In this paper an analysis is carried out of a set of inter-wordnet relations used in the mapping of the plWordNet onto the Princeton WordNet, and an attempt is made to relate them to equivalence taxonomies  ...  The development of wordnets for different languages has given rise to many wordnet linking projects (e.g. EuroWordNet, Vossen, 2002).  ...  Resembling editors' comments, glosses were added to a large portion of lexical units (and to certain synsets too) in order to make the identified lexical meaning clearer to users, as well as to explain  ... 
doi:10.11649/cs.1373 fatcat:w3272ebi4bcotfufcm56pc2jpm

Semantic Relations and Deep Learning [article]

Vivi Nastase, Stan Szpakowicz
2021 arXiv   pre-print
A new Chapter 5 of the book, by Vivi Nastase and Stan Szpakowicz, discusses relation classification/extraction in the deep-learning paradigm which arose after the first edition appeared.  ...  The second edition of "Semantic Relations Between Nominals" by Vivi Nastase, Stan Szpakowicz, Preslav Nakov and Diarmuid \'O S\'eaghdha has been published in April 2021 by Morgan & Claypool (www.morganclaypoolpublishers.com  ...  Words/entities can also be represented by relational models: their meaning is identified by their relations with other words (as in a wordnet) or other entities (as in a knowledge graph).  ... 
arXiv:2009.05426v4 fatcat:rmzoalfwcza4nex7pd4u6w7kbe

A Figure in a Field: Semantic Field-Based Analysis of Antithesis

Beata Beigman Klebanov, David Kaufer, Hilary Elise Yokota Franklin
2010 Cognitive Semiotics  
We present an implemented model of what we call generalized lexical cohesion, which allows us to analyze a text in terms of the semantic domains that its language invokes.  ...  ad hoc and unsystematic flavor" about it, according to Oakley (2009) .  ...  Since WordNet is structured by hyponymy and has some links that are specified as antonyms, WordNet is largely responsible in our model for detecting classical relations.  ... 
doi:10.3726/81610_121 fatcat:fqpcew5hqfhuxpxs552gc3bi6y

A Figure in a Field: Semantic Field-Based Analysis of Antithesis

Beata Beigman Klebanov, David Kaufer, Hilary Elise Yokota Franklin
2010 Cognitive Semiotics  
We present an implemented model of what we call generalized lexical cohesion, which allows us to analyze a text in terms of the semantic domains that its language invokes.  ...  ad hoc and unsystematic flavor" about it, according to Oakley (2009) .  ...  Since WordNet is structured by hyponymy and has some links that are specified as antonyms, WordNet is largely responsible in our model for detecting classical relations.  ... 
doi:10.1515/cogsem.2010.6.spring2010.121 fatcat:pjjipvsx6fh2vjm2ec4oet6wty

Broadcast News Gisting Using Lexical Cohesion Analysis [chapter]

Nicola Stokes, Eamonn Newman, Joe Carthy, Alan F. Smeaton
2004 Lecture Notes in Computer Science  
Our results show that our novel lexical chaining approach to this problem outperforms standard extractive gisting methods.  ...  We automatically evaluate the performance of our lexical chaining-based gister with respect to four baseline extractive gisting methods on a collection of closed caption material taken from a series of  ...  The authors are also grateful to the anonymous reviewers for their helpful comments.  ... 
doi:10.1007/978-3-540-24752-4_16 fatcat:owih6mdorvg7tcjkc2kgr3jv4q

Concept Relation Discovery and Innovation Enabling Technology (Cordiet)

Jonas Poelmans, Paul Elzinga, Stijn Viaene, Guido Dedene
2010 Social Science Research Network  
Lexical cohesion is modeled on the basis of lexical chains [11] .  ...  With the help of discriminant, pronouns which may be not resolved (for the purpose of rising the precision rate) were identified.  ... 
doi:10.2139/ssrn.1713124 fatcat:f27e6pnel5awtkziz2qxmpqrzq

Introduction to WordNet: An On-line Lexical Database*

George A. Miller, Richard Beckwith, Christiane Fellbaum, Derek Gross, Katherine J. Miller
1990 International Journal of Lexicography  
In its initial conception, WordNet was concerned solely with the pattern of semantic relations between lexicalized concepts; that is to say, it was to be a theory of the Word Meaning box.  ...  At present, WordNet distinguishes between semantic relations and lexical relations; the emphasis is still on semantic relations between meanings, but relations between words are also included.  ...  In an attempt to model the lexical knowledge of a native speaker of English, WordNet has been given detailed information about relations between word forms and synonym sets.  ... 
doi:10.1093/ijl/3.4.235 fatcat:hert5mzpv5dnfkrvrrh26dcure

Exploiting aspectual features and connecting words for summarization-inspired temporal-relation extraction

Bonnie J. Dorr, Terry Gaasterland
2007 Information Processing & Management  
This paper presents a model that incorporates contemporary theories of tense and aspect and develops a new framework for extracting temporal relations between two sentence-internal events, given their  ...  tense, aspect, and a temporal connecting word relating the two events.  ...  Acknowledgments We are indebted to three anonymous reviewers for their helpful comments and to Nitin Madnani and Waiyian (Yuan) Chong for their assistance in implementing supplemental portions of the code  ... 
doi:10.1016/j.ipm.2007.01.008 fatcat:zcmonmbbirawjer3k5woj664na

Introducing Idioms in the Galician WordNet: Methods, Problems and Results

María Álvarez de la Granja, Xosé María Gómez Clemente, Xavier Gómez Guinovart
2016 Open Linguistics  
AbstractThis study describes the introduction of verbal idioms in the Galician language version (Galnet) of the semantic network WordNet; a network that does not traditionally include many phraseological  ...  In this study, we present the working methodology for the experiment and an analysis of the results, to help understand the most important problems found when trying to introduce idioms in Galnet.  ...  In the WordNet model of lexical representation, synsets are linked by means of lexical-semantic relations.  ... 
doi:10.1515/opli-2016-0012 fatcat:pqmizqll5rh5njnf5avgonehku

Causality Mining in Natural Languages Using Machine and Deep Learning Techniques: A Survey

Wajid Ali, Wanli Zuo, Rahman Ali, Xianglin Zuo, Gohar Rahman
2021 Applied Sciences  
Causality (cause-effect relations) serves as an essential category of relationships, which plays a significant role in question answering, future events predication, discourse comprehension, decision making  ...  In this survey, an effort has been made to address a comprehensive review of some state-of-the-art shallow ML and DL approaches in CM.  ...  They used explicit discourse connectives for mining alternative lexicalizations (Altlexes) of causal discourse relations.  ... 
doi:10.3390/app112110064 fatcat:btv66da5x5a73auogv5d3lp2bi

Mining opinion components from unstructured reviews: A review

Khairullah Khan, Baharum Baharudin, Aurnagzeb Khan, Ashraf Ullah
2014 Journal of King Saud University: Computer and Information Sciences  
The opinions of users are helpful for the public and for stakeholders when making certain decisions.  ...  Opinion mining is a way to retrieve information through search engines, Web blogs and social networks.  ...  , is related to OM.  ... 
doi:10.1016/j.jksuci.2014.03.009 fatcat:oma2lylgpzc7noalvewtsbtdqa
« Previous Showing results 1 — 15 out of 135 results