Results 241 to 250 of about 35,833 (287)
Some of the next articles are maybe not open access.
Word Sense Disambiguation Based on Feature Ranking Graph
2015 IEEE 29th International Conference on Advanced Information Networking and Applications Workshops, 2015Research in the field of WSD has been conducted in computational linguistics as a specific task for many years. Language and context features have been shown to be very helpful for the task of word sense disambiguation. In this paper, we investigate the effectiveness of the graph-based ranking method on features from limited language data of word sense
Yeqing Li, Xiaoyu Qiu
openaire +1 more source
Clustering-based Feature Selection for Verb Sense Disambiguation
2005 International Conference on Natural Language Processing and Knowledge Engineering, 2006This paper presents a novel feature selection algorithm for supervised verb sense disambiguation. The algorithm disambiguates and aggregates WordNet synsets of a verb's noun phrase (NP) arguments in the training data. It was then used to filter out irrelevant WordNet semantic features introduced by the ambiguity of verb NP arguments.
null Jinying Chen, M. Palmer
openaire +1 more source
Word sense disambiguation features for taxonomy extraction
Computación y Sistemas, 2018Many NLP tasks, such as fact extraction, coreference reso- lution and alike, rely on existing lexical taxonomies or ontologies. One of possible ways to create a lexical taxonomy is to extract taxonomic re- lations from monolingual dictionary or encyclopedia: a semi-formalized resource designed to contain many such relations. Word-sense disam- biguation
openaire +1 more source
Disambiguating Recognition Results by Prosodic Features
1997For the purpose of realizing an effective use of prosodic features in automatic speech recognition, a method was proposed to check the suitability of a recognition candidate through its fundamental frequency contour. In this method, a fundamental frequency contour is generated for each recognition candidate and compared with the observed contour.
openaire +1 more source
Evaluation of Feature Combination for Effective Structural Disambiguation
2004In this paper, we present the useful features of a syntactic constituent for a probabilistic parsing model and analyze the combination of the features in order to disambiguate parse trees effectively. Unlike most of previous works focusing on the features of a single head, the features of a functional head, the features of a content head, and the ...
So-Young Park +3 more
openaire +1 more source
Effectiveness Comparison of Feature Words for Word Sense Disambiguation
INTERNATIONAL JOURNAL ON Advances in Information Sciences and Service Sciences, 2012The context of ambiguous words is the most important clue for word sense disambiguation (WSD). The selection and weight assignment of feature words affect the performance of WSD directly. The existing method usually selects the words in a certain length of window as feature words, which is easy to induce noise words in a short distance and neglect ...
Wenpeng Lu -, Heyan Huang -
openaire +1 more source
Significance of Syntactic Features for Word Sense Disambiguation
2004In this paper we explore the use of syntax in improving the performance of Word Sense Disambiguation(WSD) systems. We argue that not all words in a sentence are useful for disambiguating the senses of a target word and eliminating noise is important.
Sasi Kanth Ala, Narayana Murthy Kavi
openaire +1 more source
Research on Feature Weights of Liheci Word Sense Disambiguation
2015 8th International Symposium on Computational Intelligence and Design (ISCID), 2015Concerning the problems of the comparative translation is not accurate in machine translation and the useful information is unable to match in information retrieval, a liheci word sense disambiguation method is adopted and a classifier model is established using Support Vector Machines(SVM).
Zhenjing Zhang, Xinfu Li, Xuedong Tian
openaire +1 more source
Word Polarity Disambiguation Using Bayesian Model and Opinion-Level Features
Cognitive Computation, 2014Contextual polarity ambiguity is an important problem in sentiment analysis. Many opinion keywords carry varying polarities in different contexts, posing huge challenges for sentiment analysis research. Previous work on contextual polarity disambiguation makes use of term-level context, such as words and patterns, and resolves the polarity with a range
Yunqing Xia +3 more
openaire +1 more source
A method for Word Sense Disambiguation combining contextual semantic features
2016 International Conference on Asian Language Processing (IALP), 2016Word Sense Disambiguation (WSD) methods based on supervised learning usually convert WSD to a classification problem. Traditional WSD methods based on supervised learning often only consider the word, position, part of speech and some other superficial morphological and syntactic features.
Liang Wen +3 more
openaire +1 more source