2013
DOI: 10.1109/tkde.2012.117
|View full text |Cite
|
Sign up to set email alerts
|

Entity Translation Mining from Comparable Corpora: Combining Graph Mapping with Corpus Latent Features

Abstract: This paper addresses the problem of mining named entity translations from comparable corpora, specifically, mining English and Chinese named entity translation. We first observe that existing approaches use one or more of the following named entity similarity metrics: entity, entity context, and relationship. Motivated by this observation, we propose a new holistic approach by 1) combining all similarity types used and 2) additionally considering relationship context similarity between pairs of named entities,… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
2
1

Citation Types

0
5
0

Year Published

2014
2014
2021
2021

Publication Types

Select...
4
4

Relationship

3
5

Authors

Journals

citations
Cited by 8 publications
(5 citation statements)
references
References 18 publications
0
5
0
Order By: Relevance
“…For instance, Shao and Ng [23] integrated the E and EC. Lee et al [24] brought together E, EC and You et al [25] and Kim et al [26] not only merged all the features together, but also incorporated the additional latent features into their studies. Table Since Chinese characters contain significant semantic information, Chinese Hanzi and Japanese Kanji mapping tables can be very useful for improving the performance of MT and CLIR.…”
Section: Type Entity Relationshipmentioning
confidence: 99%
“…For instance, Shao and Ng [23] integrated the E and EC. Lee et al [24] brought together E, EC and You et al [25] and Kim et al [26] not only merged all the features together, but also incorporated the additional latent features into their studies. Table Since Chinese characters contain significant semantic information, Chinese Hanzi and Japanese Kanji mapping tables can be very useful for improving the performance of MT and CLIR.…”
Section: Type Entity Relationshipmentioning
confidence: 99%
“…Other interesting approaches such as [17], [18] rely on temporal distributions of entities. That is, two entities are considered to be similar if the two entities in different languages have similar occurrence distributions over time.…”
Section: Entity Translationmentioning
confidence: 99%
“…• Phonetic Similarity (PH) (Kim et al, 2013) • Off-the-shelf Translator: Google Translate 5 , Bing Translator 6…”
Section: Experimental Settingmentioning
confidence: 99%