Cross lingual text classification by mining multilingual topics from wikipedia

Ni, Xiaochuan; Sun, Ju; Hu, Jian; Zheng, C.

doi:10.1145/1935826.1935887

Cited by 48 publications

(45 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Bilingual word representations could serve as an useful source knowledge for problems in cross-lingual information retrieval (Levow, Oard, & Resnik, 2005;Vulić, De Smet, & Moens, 2013), statistical machine translation (Wu, Wang, & Zong, 2008), document classification (Ni, Sun, Hu, & Chen, 2011;Klementiev et al, 2012;Hermann & Blunsom, 2014b;Chandar, Lauly, Larochelle, Khapra, Ravindran, Raykar, & Saha, 2014;Vulić, De Smet, Tang, & Moens, 2015), bilingual lexicon extraction (Tamura, Watanabe, & Sumita, 2012;Vulić & Moens, 2013a), or knowledge transfer and annotation projection from resource-rich to resource-poor languages for a myriad of NLP tasks such as dependency parsing, POS tagging, semantic role labeling or selectional preferences (Yarowsky & Ngai, 2001;Padó & Lapata, 2009;Peirsman & Padó, 2010;Das & Petrov, 2011;Täckström, Das, Petrov, McDonald, & Nivre, 2013;Ganchev & Das, 2013;Tiedemann, Agić, & Nivre, 2014;Xiao & Guo, 2014). Other interesting application domains are machine translation (e.g., Zou, Socher, Cer, & Manning, 2013;Wu, Dong, Hu, Yu, He, Wu, Wang, & Liu, 2014;Zhang, Liu, Li, Zhou, & Zong, 2014) and cross-lingual information retrieval (e.g., .…”

Section: Bilingual Word Embeddingsmentioning

confidence: 99%

Bilingual Distributed Word Representations from Document-Aligned Comparable Data

Vulić

Moens

2016

jair

View full text Add to dashboard Cite

We propose a new model for learning bilingual word representations from non-parallel document-aligned data. Following the recent advances in word representation learning, our model learns dense real-valued word vectors, that is, bilingual word embeddings (BWEs). Unlike prior work on inducing BWEs which heavily relied on parallel sentence-aligned corpora and/or readily available translation resources such as dictionaries, the article reveals that BWEs may be learned solely on the basis of document-aligned comparable data without any additional lexical resources nor syntactic information. We present a comparison of our approach with previous state-of-the-art models for learning bilingual word representations from comparable data that rely on the framework of multilingual probabilistic topic modeling (MuPTM), as well as with distributional local context-counting models. We demonstrate the utility of the induced BWEs in two semantic tasks: (1) bilingual lexicon extraction, (2) suggesting word translations in context for polysemous words. Our simple yet effective BWE-based models significantly outperform the MuPTM-based and contextcounting representation models from comparable data as well as prior BWE-based models, and acquire the best reported results on both tasks for all three tested language pairs.

show abstract

Section: Bilingual Word Embeddingsmentioning

confidence: 99%

Bilingual Distributed Word Representations from Document-Aligned Comparable Data

Vulić

Moens

2016

jair

View full text Add to dashboard Cite

show abstract

“…For instance, the multilingual thesaurus EUROVOC (created by the European Commission's Publications Office) was used in [18] for document similarity purposes; however, EUROVOC utilizes less than 6 000 descriptors, which leads to evident limits in semantic coverage. Furthermore, other knowledge bases such as EuroWordNet [20] only utilize lexicographic information, while conversely studies that focus on Wikipedia (e.g., [16,2]) cannot profitably leverage on lexical ontology knowledge.…”

Section: Background On Babelnetmentioning

confidence: 99%

“…This is partly explained by the increased popularity of tools for collaboratively editing through contributors across the world, which eases the production of different language-written documents, leading to a new phenomenon of multilingual information overload. Analyzing multilingual document collections is getting increased attention as it can support a variety of tasks, such as building translation resources [20,14], detection of plagiarism in patent collections [1], cross-lingual document similarity and multilingual document classification [18,16,6,2,5].…”

Section: Introductionmentioning

confidence: 99%

“…A common approach is resorting to machine translation techniques or bilingual dictionaries to map a document to the target language, and then perform cross-lingual document similarity and categorization (e.g., [6,9]). Some works (e.g., [16,2]) have also used Wikipedia as benchmark or knowledge base. However, in a cross-lingual supervised setting, the classification performance can significantly vary by exchanging documents from source to target languages.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Knowledge-Based Representation for Transductive Multilingual Document Classification

Romeo

Ienco

Tagarelli

2015

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. Multilingual document classification is often addressed by approaches that rely on language-specific resources (e.g., bilingual dictionaries and machine translation tools) to evaluate cross-lingual document similarities. However, the required transformations may alter the original document semantics, raising additional issues to the known difficulty of obtaining high-quality labeled datasets. To overcome such issues we propose a new framework for multilingual document classification under a transductive learning setting. We exploit a large-scale multilingual knowledge base, BabelNet, to support the modeling of different language-written documents into a common conceptual space, without requiring any language translation process. We resort to a state-of-theart transductive learner to produce the document classification. Results on two real-world multilingual corpora have highlighted the effectiveness of the proposed document model w.r.t. document representations usually involved in multilingual and cross-lingual analysis, and the robustness of the transductive setting for multilingual document classification.

show abstract

“…These translations are usually obtained through machine translation techniques based on a selected anchor language. Conversely, a comparable corpus is a collection of multilingual documents written over the same set of classes (Ni et al, 2011;Yogatama and Tanaka-Ishii, 2009) without any restriction about translation or perfect correspondence between documents. To mine this kind of corpus, external knowledge is employed to map concepts or terms from a language to another (Kumar et al, 2011c;Kumar et al, 2011a), which enables the extraction of crosslingual document correlations.…”

Section: Introductionmentioning

confidence: 99%

Semantic-Based Multilingual Document Clustering via Tensor Modeling

Romeo¹,

Tagarelli²,

Ienco³

2014

Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)

View full text Add to dashboard Cite

A major challenge in document clustering research arises from the growing amount of text data written in different languages. Previous approaches depend on language-specific solutions (e.g., bilingual dictionaries, sequential machine translation) to evaluate document similarities, and the required transformations may alter the original document semantics. To cope with this issue we propose a new document clustering approach for multilingual corpora that (i) exploits a large-scale multilingual knowledge base, (ii) takes advantage of the multi-topic nature of the text documents, and (iii) employs a tensor-based model to deal with high dimensionality and sparseness. Results have shown the significance of our approach and its better performance w.r.t. classic document clustering approaches, in both a balanced and an unbalanced corpus evaluation.

show abstract

Cross lingual text classification by mining multilingual topics from wikipedia

Cited by 48 publications

References 17 publications

Bilingual Distributed Word Representations from Document-Aligned Comparable Data

Bilingual Distributed Word Representations from Document-Aligned Comparable Data

Knowledge-Based Representation for Transductive Multilingual Document Classification

Semantic-Based Multilingual Document Clustering via Tensor Modeling

Contact Info

Product

Resources

About