Filters








7,007 Hits in 7.3 sec

Acquisition of Translation Knowledge of Syntactically Ambiguous Named Entity
構文的あい昧性を持つ英語固有表現とその対訳表現の獲得

TAKEHIKO YOSHIMI, TAKESHI KUTSUMI, KATSUNORI KOTANI, ICHIKO SATA, HITOSHI ISAHARA
2005 Journal of Natural Language Processing  
TAKEHIKO YOSHIMI•õ,•õ•õ•õ,TAKESHI KUTSUMI•õ•õ,KATSUNORI KOTANI•õ•õ•õ ICHIKO SATA•õ•õ and HITOSHI ISAHARA•õ•õ•õ This paper proposes a method of extracting a bilingual pair of a syntactically ambiguous named  ...  entity and its counterpart from a sentence-aligned English-Japanese parallel corpus.This method computes the degree of semantic and phoneticsimilarities between an English named entity and its translation  ... 
doi:10.5715/jnlp.12.5_91 fatcat:cdtitdsk25bvtbu7qnfdexygwy

From Text to Knowledge [chapter]

M. Fernández, E. Villemonte de la Clergerie, M. Vilares
2007 Lecture Notes in Computer Science  
This implies the presence of nominal phrases, adjectives; and also adverbs to express frequency and intensity, and named entities to denote dimensions.  ...  This makes practicable knowledge acquisition a highly interesting topic, in particular in the case of technical and/or scientific documents with a highly structured wording that could simplify their computational  ...  This implies the presence of nominal phrases, adjectives; and also adverbs to express frequency and intensity, and named entities to denote dimensions.  ... 
doi:10.1007/978-3-540-75867-9_34 fatcat:f7izph7hmfe2vgz7irhvufoo2q

Close Integration of ML and NLP Tools in BioAlvis for Semantic Search in Bacteriology

Robert Bossy, Alain Kotoujansky, Sophie Aubin, Claire Nedellec
2008 Workshop on Semantic Web Applications and Tools for Life Sciences  
The resources required to run such platforms include named entity dictionaries, terminologies, grammars and ontologies.  ...  The precise specification of the ML task goal and target knowledge, and the adequate normalization of the training corpus representation can notably increase the quality of the acquired knowledge.  ...  The terminology part of this work has greatly benefited from Annick Lacombe's expertise.  ... 
dblp:conf/swat4ls/BossyKAN08 fatcat:qy2jev3y45bhdjz33twz3q73pm

Word segmentation based on database semantics in NChiql

Xiaofeng Meng, Shuang Liu, Shan Wang
2000 Journal of Computer Science and Technology  
The novel word-segmentation algorithm is based on the database semantic, namely Semantic Conceptual Model (SCM) for specific domain knowledge.  ...  Based on SCM, the segmenter labels the database semantics to words directly, which eases the disambiguation and translation (from natural language to database query) in NChiql.  ...  SCM extraction is the process of acquisition of sufficient domain knowledge and reconstruction of domain information especially the semantic and usage of words in order to extend the ability of language  ... 
doi:10.1007/bf02948870 fatcat:5dcjpscqxjbwnnrkwquz5jsuj4

Using a Natural Language Understanding System to Generate Semantic Web Content

Akshay Java, Sergei Nirneburg, Marjorie McShane, Timothy Finin, Jesse English, Anupam Joshi
2007 International Journal on Semantic Web and Information Systems (IJSWIS)  
to translate English text into a custom ontology-motivated knowledge representation language, the language of text meaning representations (TMRs).  ...  OntoSem concentrates on a variety of ambiguity resolution tasks as well as processing unexpected input and reference.  ...  preprocessing (tokenization, named-entity and acronym recognition, etc.), morphological, syntactic and semantic analysis, and the creation of TMRs. • The TMR language, which is the knowledge representation  ... 
doi:10.4018/jswis.2007100103 fatcat:eaiy7xbztza6xjlyvirqii2kg4

Mining conceptual graphs for knowledge acquisition

Milagros Fernández, Eric de la Clergerie, Manuel Vilares
2008 Proceeding of the 2nd ACM workshop on Improving non english web searching - iNEWS '08  
It enables the knowledge acquisition task to be performed without supervision, minimizing the possibility of failing to retrieve information contained in the document, in order to extract non-taxonomic  ...  This work addresses the use of computational linguistic analysis techniques for conceptual graphs learning from unstructured texts.  ...  Lexical ambiguities Formally, the morpho-syntactic phase consists of a pipeline named Sxpipe [8] that concatenates a number of different tasks such as chunking, entity recognition and tagging.  ... 
doi:10.1145/1460027.1460032 dblp:conf/cikm/FernandezCF08 fatcat:cz3m3a7zvjedtiqdffn6bsjj3e

Exploring Large-scale Acquisition of Multilingual Semantic Models for Predicates

Jordi Atserias, Mauro Castillo, Francis Real, Horacio Rodríguez, German Rigau
2003 Revista de Procesamiento de Lenguaje Natural (SEPLN)  
We analyze the special case of empatar. This word is monosemous in Spanish while its English translations tie and draw are highly ambiguous (9 and 33 senses respectively).  ...  We also plan to map Named Entities to these ontologies. We also plan to use more complex generalization slot mechanism e.g. using Conceptual Distance formulas.  ... 
dblp:journals/pdln/AtseriasCRRR03 fatcat:vkewyphrg5acbpild3wq6pblmm

Problems of Reusing an Existing MT System

Ondrej Bojar, Petr Homola, Vladislav Kubon
2005 International Joint Conference on Natural Language Processing  
A special attention is paid to the problem of named entity recognition and to the method of automatic acquisition of lexico-syntactic information for the bilingual dictionary of the system.  ...  This paper describes an attempt to recycle parts of the Czech-to-Russian machine translation system (MT) in the new Czech-to-English MT system.  ...  Named entity recognition module Named entities (NE) are atomic units such as proper names, temporal expressions (e.g., dates) and quantities (e.g., monetary expressions).  ... 
dblp:conf/ijcnlp/BojarHK05 fatcat:k6js3o7awrdwdbdc27u7isycny

Ambiguity Resolution : An Analytical Study

Prashant Y. Itankar, Nikhat Raza
2020 International Journal of Scientific Research in Computer Science Engineering and Information Technology  
This paper focus on the in-depth analysis of such ambiguity, issues in Language Translation, how WSD resolves the ambiguity and contribute towards building a framework.  ...  Resolving ambiguity for translation involves working with various natural language processing techniques to investigate the structure of the languages, availability of lexical resources etc.  ...  It normally points to three entities namely living, non-living and facts/events. Living entities are again categorized into animate and humans.  ... 
doi:10.32628/cseit2062135 fatcat:p6o43nume5a7biltte4oednosy

Anaphora Resolution in English Ambiguous Sentences by ESL Learners

Shujat Ali
2021 PAKISTAN LANGUAGES AND HUMANITIES REVIEW  
The strategies of gender and number agreement, syntactic knowledge and real-world knowledge were the most frequently used strategies; while, the least frequently used strategy for anaphora resolution was  ...  discourse knowledge.  ...  The results of anaphora resolution through syntactic knowledge in English ambiguous sentences are shown in the table.  ... 
doi:10.47205/plhr.2021(5-ii)1.13 fatcat:xzc4kc3wqfa73p2uj7jljnrrou

Knowledge Authoring and Question Answering via Controlled Natural Language

Tiantian Gao, Michael Wagner
2018 International Conference on Logic Programming  
Knowledge acquisition from text is the process of automatically acquiring, organizing and structuring knowledge from text which can be used to perform question answering or complex reasoning.  ...  Controlled Natural Languages (CNLs) emerged as a technology to author knowledge using a restricted subset of English.  ...  However, it is ambiguous whether the user intends to acquire company or person entities or both.  ... 
doi:10.4230/oasics.iclp.2018.21 dblp:conf/iclp/Gao18 fatcat:sbntkyun7nfkfktcoryqftqmju

Identification of Composite Named Entities in a Spanish Textual Database [chapter]

Sofía N. Galicia-Haro, Alexander Gelbukh, Igor A. Bolshakov
2004 Lecture Notes in Computer Science  
Named entities (NE) mentioned in textual databases constitute an important part of their semantics. Lists of those NE are an important knowledge source for diverse tasks.  ...  We present a method for NE identification focused on composite proper names (names with coordinated constituents and names with several prepositional phrases.)  ...  Syntactic Ambiguity Discourse Structures Discourse structures could be another source for knowledge acquisition. Entities could be extracted from the analysis of particular sequences of texts.  ... 
doi:10.1007/978-3-540-27779-8_37 fatcat:t3qtrqvbkzh3hidrwsifc7bbta

Text Understanding Agents and the Semantic Web

A. Java, T. Finin, S. Nirenburg
2006 Proceedings of the 39th Annual Hawaii International Conference on System Sciences (HICSS'06)  
A central problem underlying both sets of tasks is that of translating knowledge between OntoSem's KR language and ontologies and those of the Semantic Web.  ...  Another set of tasks works in reverse -querying the Web for facts needed by OntoSem, translating them from OWL into OntoSem's native KR language and importing the results.  ...  Ambiguity is also an issue when dealing with NL text. Human language can have ambiguity at both syntactic and semantic level.  ... 
doi:10.1109/hicss.2006.452 dblp:conf/hicss/JavaFN06 fatcat:fvl65nhydbfqxc4tfamuzb5vie

From Regulatory Texts to BRMS: How to Guide the Acquisition of Business Rules? [chapter]

Abdooulaye Guissé, François Lévy, Adeline Nazarenko
2012 Lecture Notes in Computer Science  
information and of implicit semantic entities to get a set of self-sufficient and unambiguous rule statements.  ...  This paper tackles the problem of rule acquisition, which is critical for the development of BRMS.  ...  To the best of our knowledge, only [8] considers a direct translation of legal texts but, after a parsing step, the abstract syntax trees are translated by hand into CTL 2 .  ... 
doi:10.1007/978-3-642-32689-9_7 fatcat:xzeky7lufvcoflwip2szqulodq

The Effect of Corpus Size on Case Frame Acquisition for Predicate-Argument Structure Analysis

Ryohei SASANO, Daisuke KAWAHARA, Sadao KUROHASHI
2010 IEICE transactions on information and systems  
Then, we apply these case frames to syntactic and case structure analysis, and zero anaphora resolution, in order to investigate the relationship between the corpus size for case frame acquisition and  ...  This paper reports the effect of corpus size on case frame acquisition for predicate-argument structure analysis in Japanese.  ...  resolution, we used the correct morphemes, named entities, syntactic structures and coreference relations that were manually annotated.  ... 
doi:10.1587/transinf.e93.d.1361 fatcat:xmvxeirxujgeldyolbqnwy2ypy
« Previous Showing results 1 — 15 out of 7,007 results