Cross-lingual Wikification Using Multilingual Embeddings
Published 1 January 2016Open access
Chen-Tse Tsai, Dan Roth
Citations114
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
This paper jointly training multi-lingual embeddings for words and Wikipedia titles in 12 languages shows that the proposed approach outperforms various baselines and compares favorably with the best systems on the TAC KBP2015 Entity Linking task.
Abstract
Cross-lingual Wikification is the task of grounding mentions written in non-English documents to entries in the English Wikipedia.This task involves the problem of comparing textual clues across languages, which requires developing a notion of similarity between text snippets across languages.In this paper, we address this problem by jointly training multilingual embeddings for words and Wikipedia titles.The proposed method can be applied to all languages represented in Wikipedia, including those for which no machine translation technology is available.We create a challenging dataset in 12 languages and show that our proposed approach outperforms various baselines.Moreover, our model compares favorably with the best systems on the TAC KBP2015 Entity Linking task including those that relied on the availability of translation from the target language to English.
Keywords
Computer ScienceSocial Sciences
arXiv (Cornell University)Distributed Representations of Words and Phrases and their Compositionality
18,086 Citations2013Tomáš Mikolov, Ilya Sutskever +3 more
This paper presents a simple method for finding phrases in text, and shows that learning good vector representations for millions of phrases is possible and describes a simple alternative to the hierarchical softmax called negative sampling.
arXiv (Cornell University)Efficient Estimation of Word Representations in Vector Space
18,050 Citations2013Tomáš Mikolov, Kai Chen +2 more
Two novel model architectures for computing continuous vector representations of words from very large data sets are proposed and it is shown that these vectors provide state-of-the-art performance on the authors' test set for measuring syntactic and semantic word similarities.
Learning to link with wikipedia
1,266 Citations2008David Milne, Ian H. Witten
This paper explains how machine learning can be used to identify significant terms within unstructured text, and enrich it with links to the appropriate Wikipedia articles, and performs very well, with recall and precision of almost 75%.
Large-Scale Named Entity Disambiguation Based on Wikipedia Data
1,072 Citations2007Silviu Cucerzan
Through a process of maximizing the agreement between the contextual information extracted from Wikipedia and the context of a document, as well as the agreement among the category tags associated with the candidate entities, the implemented system shows high disambiguation accuracy on both news stories and Wikipedia articles.
Wikify!
921 Citations2007Rada Mihalcea, Andras Csomai
This paper introduces the use of Wikipedia as a resource for automatic keyword extraction and word sense disambiguation, and shows how this online encyclopedia can be used to achieve state-of-the-art results on both these tasks.
Using Encyclopedic Knowledge for Named Entity Disambiguation
812 Citations2006Răzvan Bunescu, Marius Paşca
A disambiguation SVM kernel is trained to exploit the high coverage and rich structure of the knowledge encoded in an online encyclopedia and significantly outperforms a less informed baseline.
TAGME
750 Citations2010Paolo Ferragina, Ugo Scaiella
Transactions of the Association for Computational LinguisticsEntity Linking meets Word Sense Disambiguation: a Unified Approach
747 Citations2014Andrea Moro, Alessandro Raganato +1 more
Babelfy is presented, a unified graph-based approach to EL and WSD based on a loose identification of candidate meanings coupled with a densest subgraph heuristic which selects high-coherence semantic interpretations.
Improving Vector Space Word Representations Using Multilingual Correlation
655 Citations2014Manaal Faruqui, Chris Dyer
This paper argues that lexico-semantic content should additionally be invariant across languages and proposes a simple technique based on canonical correlation analysis (CCA) for incorporating multilingual evidence into vectors generated monolingually.
TIB Data ManagerLocal and global algorithms for disambiguation to Wikipedia
623 Citations2024Lev Ratinov
This work analyzes approaches that utilize information from Wikipedia link structure to arrive at coherent sets of disambiguations for a given document, and compares them to more traditional (local) approaches.
Overview of the TAC 2010 Knowledge Base Population Track
419 Citations2010Heng Ji, Ralph Grishman +3 more
An overview of the task definition and annotation challenges associated with KBP2010 is provided and the evaluation results and lessons that are learned are discussed based on detailed analysis.
Knowledge Graph and Text Jointly Embedding
412 Citations2014Zhen Wang, Jianwen Zhang +2 more
Large scale experiments on Freebase and a Wikipedia/NY Times corpus show that jointly embedding brings promising improvement in the accuracy of predicting facts, compared to separately embedding knowledge graphs and text.
Bilingual Word Representations with Monolingual Quality in Mind
331 Citations2015Thang Luong, Hieu Pham +1 more
This work proposes a joint model to learn word representations from scratch that utilizes both the context coocurrence information through the monolingual component and the meaning equivalent signals from the bilingual constraint to learn high quality bilingual representations efficiently.
arXiv (Cornell University)BilBOWA: Fast Bilingual Distributed Representations without Word Alignments
314 Citations2014Stephan Gouws, Yoshua Bengio +1 more
Optimizing Chinese word segmentation for machine translation performance
302 Citations2008Pi-Chuan Chang, Michel Galley +1 more
It is demonstrated that optimizing segmentation for an existing segmentation standard does not always yield better MT performance, and it is found that other factors such as segmentation consistency and granularity of Chinese "words" can be more important for machine translation.
Relational Inference for Wikification
202 Citations2013Cheng Xiao, Dan Roth
This paper provides an extensible, efficient and modular Integer Linear Programming (ILP) formulation of Wikification that incorporates the entity-relation inference problem, and shows that the ability to identify relations in text helps both candidate generation and ranking Wikipedia titles considerably.
Named entity disambiguation by leveraging wikipedia semantic knowledge
164 Citations2009Xianpei Han, Jun Zhao
A novel similarity measure is proposed to leverage Wikipedia semantic knowledge for disambiguation, which surpasses other knowledge bases by the coverage of concepts, rich semantic information and up-to-date content and has been tested on the standard WePS data sets.
Neural ComputationLarge-Scale Linear RankSVM
135 Citations2014Ching-pei Lee, Chih‐Jen Lin
This letter systematically study existing works, discusses their advantages and disadvantages, and proposes an efficient algorithm that is useful to quickly produce a baseline model, and develops a robust linear rankSVM tool for public use.
Bilingual Word Embeddings from Non-Parallel Document-Aligned Data Applied to Bilingual Lexicon Induction
121 Citations2015Ivan Vulić, Marie‐Francine Moens
It is shown that the BWE-based BLI models significantly outperform the MuPTM-based and context-counting models in this setting, and obtain the best reported BLI results for all three tested language pairs.
arXiv (Cornell University)TAGME: on-the-fly annotation of short text fragments (by Wikipedia entities)
106 Citations2010Paolo Ferragina, Ugo Scaiella
arXiv (Cornell University)Multilingual Distributed Representations without Word Alignment
68 Citations2013Karl Moritz Hermann, Phil Blunsom
Learning Cross-lingual Word Embeddings via Matrix Co-factorization
59 Citations2015Tianze Shi, Zhiyuan Liu +2 more
A matrix cofactorization framework for learning cross-lingual word embeddings that explicitly defines monolingual training objectives in the form of matrix decomposition, and induces cross-lingsual constraints for simultaneously factorizing monolingUAL matrices.
Cross-Language Entity Linking
52 Citations2011Paul McNamee, James Mayfield +3 more
A new test collection is created to evaluate cross-language entity linking performance in twenty-one languages and presents experiments that examine issues such as: the importance of transliteration; the utility of cross- language information retrieval; and, the potential benefit of multilingual named entity recognition.
Language and Domain Independent Entity Linking with Quantified Collective Validation
38 Citations2015Han Wang, Jin Zheng +3 more
A novel unsupervised algorithm named Quantified Collective Validation is presented that avoids excessive linguistic analysis on the source documents and fully leverages the knowledge base structure for the entity linking task.
arXiv (Cornell University)Leveraging Monolingual Data for Crosslingual Compositional Word\n Representations
25 Citations2014Hubert Soyer, Pontus Stenetorp +1 more
arXiv (Cornell University)Leveraging Monolingual Data for Crosslingual Compositional Word Representations
15 Citations2014Hubert Soyer, Pontus Stenetorp +1 more