334 Hits in 5.9 sec

Using WordNet to automatically deduce relations between words in noun-noun compounds

Fintan J. Costello, Tony Veale, Simon Dunne
2006 Proceedings of the COLING/ACL on Main conference poster sessions -   unpublished
We present an algorithm for automatically disambiguating noun-noun compounds by deducing the correct semantic relation between their constituent words.  ...  This algorithm uses a corpus of 2,500 compounds annotated with WordNet senses and covering 139 different semantic relations (we make this corpus available online for researchers interested in the semantics  ...  In this paper we describe a novel algorithm for disambiguating noun-noun compounds by automatically deducing the correct semantic relationship between their constituent words.  ... 
doi:10.3115/1273073.1273094 fatcat:6iolncgszbcxneyozuzqtihube

Identification of Adjective-Noun Neologisms using Pretrained Language Models

John Philip McCrae
2019 Proceedings of the Joint Workshop on Multiword Expressions and WordNet (MWE-WN 2019)  
In this paper, we show that we can effectively identify the distinction between compositional and non-compositional adjective-noun pairs by using pretrained language models and comparing this with individual  ...  word embeddings.  ...  Acknowledgments This publication has emanated from research supported in part by a research grant from Science Foundation Ireland (SFI) under Grant Number SFI/12/RC/2289, co-funded by the European Regional  ... 
doi:10.18653/v1/w19-5116 dblp:conf/mwe/McCrae19 fatcat:oyt66c2csnhjhcscocfh4dnt44

Automated Construction of a Large Semantic Network of Related Terms for Domain-Specific Modeling [chapter]

Henning Agt, Ralf-Detlef Kutsche
2013 Lecture Notes in Computer Science  
In order to support the domain modeling process in model-based software development, we automatically create large networks of semantically related terms from natural language.  ...  Using part-of-speech tagging, lexical patterns and co-occurrence analysis, and several semantic improvement algorithms, we construct SemNet, a network of approximately 2.7 million single and multi-word  ...  We deduce semantic relatedness between terms based on statistical semantics [22] using n-gram frequencies.  ... 
doi:10.1007/978-3-642-38709-8_39 fatcat:zmx5anofkzgoznnu22z3gntqbm

Towards a Workbench for Acquisition of Domain Knowledge from Natural Language [article]

Andrei Mikheev Steven Finch (Thomson Technical Labs, Rockville Maryland)
1996 arXiv   pre-print
of extracted data and a semi-automatic refinement of obtained hypotheses.  ...  In this paper we describe an architecture and functionality of main components of a workbench for an acquisition of domain knowledge from large text corpora.  ...  However, it is not necessarily the case that related adjectives are stated together in one WordNet entry. Sometimes there is an indirect link between adjectives.  ... 
arXiv:cmp-lg/9604026v1 fatcat:iuxiuvblt5eotcr44bp6e43imm

Introduction to the special issue: On wordnets and relations

Maciej Piasecki, Stan Szpakowicz, Christiane Fellbaum, Bolette Sandford Pedersen
2013 Language Resources and Evaluation  
in transferring the structure from the source to the target wordnet.  ...  The numerous uses of this lexical resource have motivated the building of wordnets 1 in several dozen languages, including even a "dead" language, Latin.  ...  Open Access This article is distributed under the terms of the Creative Commons Attribution License which permits any use, distribution, and reproduction in any medium, provided the original author(s)  ... 
doi:10.1007/s10579-013-9247-y fatcat:z5aqq4yazranpfpt36auysigde

Analysing debates on climate change with textual entailment and ontologies

Adrian Groza
2018 Figshare  
This work was supported by the by the Department of Computer Science from Technical University of Cluj-Napoca (TUCN), Romania through grant "WSN in precision agriculture: hybrid models for recommendation  ...  Broad-coverage knowledge needed to align words/phrases consists of i) align identical words; ii) align equivalent/related phrases -using paraphrase resources; and iii) align lexically related words: using  ...  The second, lexical aligner based on new noun lexical resource uses the lexical resource for NOUNS (A 6 ) generated automatically from a climate change domain ontology.  ... 
doi:10.6084/m9.figshare.5835600.v1 fatcat:chwykmdsijd35n77qwaqsqmydy

Syntagmatic and paradigmatic representations of term variation

Christian Jacquemin
1999 Proceedings of the 37th annual meeting of the Association for Computational Linguistics on Computational Linguistics -  
It is applied to term normalization of French and English corpora in the medical and agricultural domains.  ...  A two-tier model for the description of morphological, syntactic and semantic variations of multi-word terms is presented.  ...  We are also grateful to B6atrice Daille (IRIN) for running her termer ACABIT on the data and to Olivier Ferret (LIMSI) for the Word97 macrofunction used to extract the thesaurus.  ... 
doi:10.3115/1034678.1034733 dblp:conf/acl/Jacquemin99 fatcat:mpv2j26645d3vafl4zsp336mfa

Natural Language Processing and Information Retrieval [chapter]

Ellen M. Voorhees
1999 Lecture Notes in Computer Science  
for compound index terms; and the implicit linguistic processing inherent in the statistical methods.  ...  Natural language processing techniques may be more important for related tasks such as question answering or document summarization.  ...  Acknowledgements My thanks to Donna Harman and Chris Buckley for improving this paper through their comments.  ... 
doi:10.1007/3-540-48089-7_3 fatcat:bgh5hwznava75gmiuuzy4jnphy

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  
be used to designate the relation between individual word forms belonging to those synsets.  ...  In other words, the use of synsets to represent word meanings is consistent with psycholinguistic evidence that nouns, verbs, and modifiers are organized independently in semantic memory.  ...  In order to spare users the trouble of affix stripping, and to assist with the creation of programs that use WordNet to automatically process natural language texts, the WordNet software suite includes  ... 
doi:10.1093/ijl/3.4.235 fatcat:hert5mzpv5dnfkrvrrh26dcure

Enhancing a Dictionary for Transfer Rule Acquisition

Francis Bond, Jim Breen, Eric Nichols
2007 Linguistic Research  
It is widely used as a source of lexical material in dictionary systems and text-processing projects.  ...  We then propose and apply semi-automatic methods to refine existing entries. The resulting dictionary is shown to be more suitable for the construction of machine translation rules.  ...  Acknowledgments This paper is largely based on Semi-automatic Refinement of the JMdict/EDICT Japanese-English Dictionary (Bond and Breen, 2007) , the section on building transfer rules comes from Nichols  ... 
doi:10.17250/khisli.24.2.200712.006 fatcat:bvf4bilhpzeq3cbpy2tws4koqu

Sentence Object Notation: Multilingual sentence notation based on Wordnet [article]

Abdelkrime Aries, Djamel Eddine Zegour, Walid Khaled Hidouci
2018 arXiv   pre-print
This can be done using a lexicon like wordnet, instead of words we use their synsets. As for syntactic relations, they have to be universal as much as possible.  ...  To avoid language-dependent notations, we have to come up with a new representation which don't use words, but their meanings.  ...  Acknowledgement Special thanks to Hisham Omar for his valuable feedback concerning Japanese examples.  ... 
arXiv:1801.00984v2 fatcat:p7num6fo4va7znjekacjzq6kba

A Framework for Interpreting Bridging Anaphora [chapter]

Parma Nand, Wai Yeap
2013 Communications in Computer and Information Science  
The annotators were asked to classify the relations between anaphor-antecedent pairs into relation types that have been previously used to describe the relations between a modifier and the head noun of  ...  In this paper we present a novel framework for resolving bridging anaphora. We argue that anaphora, particularly bridging anaphora, is used as a shortcut device similar to the use of compound nouns.  ...  The proposed framework enables us to use relations from the same set to describe the relations between car and tyres in the compound noun faulty car tyres and the anaphoric relations between faulty car  ... 
doi:10.1007/978-3-642-36907-0_9 fatcat:p2p2uqohbfbdtp7v46ofs35i2i

An automatic method for reporting the quality of thesauri

Javier Lacasta, Gilles Falquet, F. Javier Zarazaga-Soria, Javier Nogueras-Iso
2016 Data & Knowledge Engineering  
This paper describes a process that automatically analyses the thesaurus properties and relations with respect to ISO 25964 specification, and suggests the correction of potential problems.  ...  Thesauri are knowledge models commonly used for information classification and retrieval whose structure is defined by standards such as the ISO 25964.  ...  This approach is specially useful to align noun-based labels, such as those in a thematic thesaurus, and WordNet nouns.  ... 
doi:10.1016/j.datak.2016.05.002 fatcat:3wfbaygcx5haffk3gv6pg67yuy

Exploiting Sublanguage and Domain Characteristics in a Bootstrapping Approach to Lexicon and Ontology Creation [article]

Dietmar Roesner, Manuela Kunze
2003 arXiv   pre-print
It is very costly to build up lexical resources and domain ontologies.  ...  In this paper we report about ongoing experiments with 'bootstrapping techniques' for lexicon and ontology creation.  ...  In local contexts we both find part-of relations between anatomic structures as well as neighbourhood relations. The analysis of noun phrases needs to be more fine grained.  ... 
arXiv:cs/0304035v1 fatcat:metc5ncvwzacpbmiqogg3tx4ky

Knowledge Extraction from Classification Schemas [chapter]

Steffen Lamparter, Marc Ehrig, Christoph Tempich
2004 Lecture Notes in Computer Science  
Explicit as well as implicit semantics contained in the classification schema have to be considered to create a formal ontology.  ...  The extraction process is composed of five main steps: Identification of concepts and instances, word sense disambiguation, taxonomy construction, identification of non-taxonomic relations, and ontology  ...  [17] uses such a method for natural language processing and defines regular expressions that can be used to find relations between words.  ... 
doi:10.1007/978-3-540-30468-5_40 fatcat:pjw56d2z5rdlhp4j6bh4buspze
« Previous Showing results 1 — 15 out of 334 results