Using the technique of "semantic mirroring" a graph is obtained that represents words and their translations from a parallel corpus or a bilingual lexicon. The connectedness of the graph holds information ab...
详细信息
graph-basedmethods that are en vogue in the social network analysis area, such as centrality models, have been recently applied to linguistic knowledge bases, including unsupervised Word Sense Disambiguation. Althoug...
详细信息
Linguists use phylogenetic methods to build evolutionary trees of languages given lexical, phonological, and morphological data. Perfect phylogeny is too restrictive to explain most data sets. Conservative Dollo phylo...
详细信息
作者：
Biemann, Chris
475 Brannan St Ste. 330 San Francisco CA 94107 United States
This paper examines the influence of features based on clusters of co-occurrences for supervised Word Sense Disambiguation and Lexical Substitution. Cooccurrence cluster features are derived from clustering the local ...
详细信息
This work extends the study of Germann et al. (2010) in investigating the lexical organization of verbs. Particularly, we look at the influence of frequency on the process of lexical acquis ition and use. We examine d...
详细信息
Using the technique of"semantic mirroring" a graph is obtained that represents words and their translations from a parallel corpus or a bilingual lexicon. The connectedness of the graph holds information abo...
详细信息
This paper proposes an unsupervised word sense disambiguation method for the biomedical domain. In this paper, a network representation of co-occurrence data is first defined to represent both word senses and word con...
详细信息
The proceedings contain 12 papers. The topics discussed include: network analysis reveals structure indicative of syntax in the corpus of undeciphered Indus civilization inscriptions;bipartite spectral graph partition...
ISBN:
(纸本)193243254X
The proceedings contain 12 papers. The topics discussed include: network analysis reveals structure indicative of syntax in the corpus of undeciphered Indus civilization inscriptions;bipartite spectral graph partitioning to co-cluster varieties and sound correspondences in dialectology;WikiWalk: random walks on Wikipedia for semantic relatedness;classifying Japanese polysemous verbs based on Fuzzy C-means clustering;measuring semantic relatedness with vector space models and random walks;ranking and semi-supervised classification on large scale graphs using Map-Reduce;opinion graphs for polarity and discourse classification;a cohesion graphbased approach for unsupervised recognition of literal and non-literal use of multiword expressions;social (distributed) language modeling, clustering and dialectometry;and quantitative analysis of treebanks using frequent subtree mining methods.
In this survey we overview graph-based clustering and its applications in computational linguistics. We summarize graph-based clustering as a five-part story: hypothesis, modeling, measure, algorithm and evaluation. W...
ISBN:
(纸本)9781932432770
In this survey we overview graph-based clustering and its applications in computational linguistics. We summarize graph-based clustering as a five-part story: hypothesis, modeling, measure, algorithm and evaluation. We then survey three typical NLP problems in which graph-based clustering approaches have been successfully applied. Finally, we comment on the strengths and weaknesses of graph-based clustering and envision that graph-based clustering is a promising solution for some emerging NLP problems.
The talk will commence by discussing some of the problems that arise when machine learning is applied to graph structures. A taxonomy of different methods organised around a) clustering b) characterisation and c) cons...
ISBN:
(纸本)9781932432770
The talk will commence by discussing some of the problems that arise when machine learning is applied to graph structures. A taxonomy of different methods organised around a) clustering b) characterisation and c) constructing generative models in the graph domain will be introduced. With this taxonomy in hand, Dr. Hancock will then describe a number of graph-spectral algorithms that can be applied to solve the many different problems inherent to graphs, drawing examples from computer vision research.
暂无评论