Bilingual Term Research Articles

Agua-cuerpo-territorio/Water-body-territory

This paper applies cuerpo-territorio (body-territory) to aquatic space through the bilingual concept of agua-cuerpo-territorio/water-body-territory. Based on a 2018 article that I wrote in Spanish and titled “Espacios acuáticos desde una descolonialidad hemisférica feminista” [Aquatic space from a decolonial and feminist hemispheric perspective], I will further develop the concept of water-body-territory that brings together literature on cuerpo-territorio (body-territory) and agua-territorio (water-territory) resulting in a bilingual term agua-cuerpo-territorio/water-body-territory. This implies that I will translate parts of the mentioned article from Spanish to English while situating it within hemispheric debates on the individual and collective body autonomy in aquatic space. Agua-cuerpo-territorio/water-body-territory will further the conceptual discussions that cuerpo-territorio has garnered across the Americas in feminist academic and activist settings on embodiment and decolonial feminist geography methodologies, in particular the relationship between water and the embodiment of collective death. Moreover, as I will make the case in this paper, this translation process is a praxis of decolonial feminist geopolitics that can engage with debates on collective bodily autonomy for the Americas.

LLMs-based machine translation for E-commerce

Large language models(LLMs) have shown promising performance for various downstream tasks, especially machine translation. However, LLMs and Specialized Translation Models (STMs) are designed to handle general translation needs, they are not well-suited for domains with specialized terms and writing styles, such as e-commerce, legal, and medicine. In the e-commerce domain, the text often contains many domain-specific terms and keyword-stacked structures, leading to poor translation quality with existing NMT methods. To tackle these problems, we have collected two resources specifically for the e-commerce domain, including aligned Chinese-English bilingual terms and parallel corpus from real e-commerce scenarios for model fine-tuning. We propose an LLMs-based E-commerce machine translation approach(LEMT) which includes LLMs utilization, e-commerce resources collection, and tokenizer optimization. We conduct two-stage fine-tuning and self-contrastive enhancement based on general LLMs to enable the model to learn translation features in the e-commerce domain. Through comprehensive evaluations on real e-commerce titles, our LEMT methodology demonstrates superior translation quality and robustness, outperforming leading NMT models such as NLLB, LLaMA, and even GPT-4.

Splitting Hairs: Designing Corpus-Driven Hairstyling Glossary Entries for a Diverse Audience

This paper illustrates a bilingual corpus-driven term extraction and description procedure (Bowker & Pearson, 2002) in the popular field of hairdressing. We present examples of term entries (fringe, texture, to wear) derived from ad-hoc corpora compiled on the SketchEngine platform (about 200,000 words total), focusing on translation equivalents and phraseologies. We also consider the advantages of such lexical explorations vis-à-vis the information available in professional publications. We finally present a proposal for the identification and design of terminological entries in a multimodal glossary, which should be comprehensive in content and adaptable to the needs of native and non-native speakers, professionals and laypeople.

L’intraduisibilité dans la traduction terminologique – un point de vue culturel

The Untranslatability in Terminological Translation – A Cultural Perspective
 The article tackles the untranslatability of perfumery French terms into Chinese and discusses the cultural explanatory factors that influence it. The first part is devoted to the theoretical presentation, which first defines culture as all that is created and known materially and spiritually, that it is the identity of a social group which differs from others. Translation is defined as a reformulation of the message in the target culture, and the essence of translating a term consists in determining its equivalent in the target language. The relation between the source term in the source language and the target term in the target language is theoretically an equivalence. However, terms are designations of concepts, and the creation of terms is a process of linguistic materialization of concepts. Since this process of linguistic materialization is cognitive and is strongly influenced by cultural practice and context, it is possible that the equivalence relation between the source term and the target term is not always absolute. It is possible that the so-called "equivalence" is just a partial equivalence or a functional equivalence. To justify the theoretical deduction, a terminology database in perfumery has been created, in which a certain number of French-Chinese terms in perfumery are collected. These terms constitute the object of analysis. The second part therefore specifies the inventory of French-Chinese terminological work in the field of perfumery, the parallel corpus in which the identification of bilingual terms is carried out, the principles to follow when identifying bilingual terms, the method used to construct the terminological database and to demonstrate the terms, and the method used to analyse the terms in the database. Then the third part is devoted to an observation of non-equivalences between French and Chinese terms. The non-equivalences are at the categorical and conceptual level. This means that the concepts designated by the French terms and the concepts designated by the Chinese terms are not mutually concordant. The non- equivalences are also found at the semantic level, which means that the French terms and their corresponding Chinese terms are semantically divergent. Examples cited from the terminological database testify first to the existence of categorial and conceptual non-equivalence, then to the absence of total semantic equivalence in the translation of terms. These non-equivalences are the direct causes of failures in the translation of terms, in other words, the direct cause of terminological untranslatability. A final discussion asserts that the indirect causes of the terminological untranslatability are found in cultural divergences. More precisely, the untranslatability is related to the practice of the field of perfumery and to the situation of terminological standardization in both countries. The different development in practice and in terminological work in perfumery between France and China leads to an unbalanced terminological development between the two languages, which manifests itself in the untranslatability of terms. The non-equivalences are also explained by the lack of terminological standardization in perfumery and the complexity in the perfumery market. Countless perfumed products, constant innovation of perfume notes, advertising strategies to increase turnover, etc., all this complexity is reflected in the linguistic description of products, including in terms. Finally, the conclusion opens a research perspective on terminological standardization in perfumery as well as on the translation approaches of translators faced with the untranslatability of terms.

Inter-lingual correspondence between the conceptual systems of patent law in Russia and the United States

Due to its deep connection with international law and the requirement to register patents in every country where protection of an invention is sought, patent law requires an immense number of translations every year. Nevertheless, considerable diversity in national patent legislations around the world hinders translation of patent documentation because of significant terminology differences. This paper studies patent law terminology equivalence in Russian and U.S. patent law. The main objective is to identify concept correlation between the main patent law terms in the U.S. and Russian legal systems and to classify the identified term-pairs according to their degree of equivalency, pointing out problematic cases and suggesting ways of their resolution for better translation of documents in this field. This objective is reached through comparative definitional analysis of the key patent law terminological units extracted from legislation texts, monolingual term glossaries, and bilingual term dictionaries. Notwithstanding the predominance of full equivalents, the research shows that national patent law systems preserve their characteristic features which result in a significant number of partially equivalent and non-equivalent terms, many of which are related to the very basic patent law concepts such as patentability. However, no currently existing bilingual English-Russian or Russian-English dictionary provides up-to-date and accurate information about Russian and American patent law terms with all necessary remarks concerning possible differences between the concepts. The research results can serve as the basis for compilation of a specialised bilingual glossary of Russian and American patent terms which can be used as a reference during translation of patent documentation.

Automatic SNOMED CT coding of Chinese clinical terms via attention-based semantic matching

BackgroundA considerable amount of meaningful information is routinely recorded in Chinese clinical data in text format, referred to as Chinese clinical terms. The lack of coding is a major difficulty hindering the application of clinical terms. SNOMED CT is a widely used and comprehensive clinical health care terminology collection because of its coverage, granularity, clinical orientation, and logical underpinning. It is useful and efficient for automatically assigning SNOMED CT codes to Chinese clinical terms, but it still faces several problems. Current cross-language clinical term matching studies rely on external resources, such as machine translation and rule-based methods. Semantic matching methods have achieved strong performance on text matching, but few studies have been done on cross-language clinical term matching. We present an effective attention-based semantic matching algorithm to automatically cross-language code Chinese clinical terms with SNOMED CT. MethodFirstly, BERT was used to turn the input into word embedding. Then, the word embeddings were encoded through a BiLSTM with self-attention to focus on capturing distant relationships among words with different weights depending on their contribution to semantic matching. Then, decomposable attention was used to make semantic matching trivially parallelizable to speed up calculation. Finally, fully connected layers and a sigmoid were utilized to output matching results. ResultsThe 29,960 manually coded Chinese clinical terms, 30,040 unmatched Chinese clinical terms and SNOMED CT codes were collected to evaluate the proposed method. Compared with the existing semantic matching method, the proposed approach achieves state-of-the-art results demonstrating the effectiveness of the method with an accuracy of 0.905, a precision of 0.856, a recall of 0.518, and an F-measure of 0.645. The proposed Chinese-English bilingual term mapping, Chinese character-level and word-level encoder, English word-level encoder, BERT model, and attention mechanism performed better than other methods. ConclusionThe proposed automatic SNOMED CT coding approach of Chinese clinical terms via attention-based semantic matching can improve the performance of automated SNOMED CT code assignment for Chinese clinical terms and improve the efficiency of the code assignment.

Methodological Framework for the Development of an English-Lithuanian Cybersecurity Termbase

The aim of the paper is to present a methodological framework for the development of an English-Lithuanian bilingual termbase in the cybersecurity domain, which can be applied as a model for other language pairs and other specialised domains. It is argued that the presented methodological approach can ensure creation of high-quality bilingual termbases even with limited available resources. The paper touches upon the methods and problems of dataset (corpora) compilation, terminology annotation, automatic bilingual term extraction (BiTE) and alignment, knowledge-rich context extraction, and linguistic linked open data (LLOD) technologies. The paper presents theoretical considerations as well as the arguments on the effectiveness of the described methods. The theoretical analysis and a pilot study allow arguing that: 1) a combination of parallel and comparable corpora enable to considerably expand the amount and variety of data sources that can be used for terminology extraction; this methodology is especially important for less-resourced languages which often lack parallel data; 2) deep learning systems trained by using manually annotated data (gold standard corpora) allow effective automatization of extraction of terminological data and metadata, which enables to regularly update termbases with minimised manual input; 3) LLOD technologies enable to integrate the terminological data into the global linguistic data ecosystem and make it reusable, searchable and discoverable across the Web.

COVID term: a bilingual terminology for COVID-19

BackgroundThe coronavirus disease (COVID-19), a pneumonia caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) has shown its destructiveness with more than one million confirmed cases and dozens of thousands of death, which is highly contagious and still spreading globally. World-wide studies have been conducted aiming to understand the COVID-19 mechanism, transmission, clinical features, etc. A cross-language terminology of COVID-19 is essential for improving knowledge sharing and scientific discovery dissemination.MethodsWe developed a bilingual terminology of COVID-19 named COVID Term with mapping Chinese and English terms. The terminology was constructed as follows: (1) Classification schema design; (2) Concept representation model building; (3) Term source selection and term extraction; (4) Hierarchical structure construction; (5) Quality control (6) Web service. We built open access for the terminology, providing search, browse, and download services.ResultsThe proposed COVID Term include 10 categories: disease, anatomic site, clinical manifestation, demographic and socioeconomic characteristics, living organism, qualifiers, psychological assistance, medical equipment, instruments and materials, epidemic prevention and control, diagnosis and treatment technique respectively. In total, COVID Terms covered 464 concepts with 724 Chinese terms and 887 English terms. All terms are openly available online (COVID Term URL: http://covidterm.imicams.ac.cn).ConclusionsCOVID Term is a bilingual terminology focused on COVID-19, the epidemic pneumonia with a high risk of infection around the world. It will provide updated bilingual terms of the disease to help health providers and medical professionals retrieve and exchange information and knowledge in multiple languages. COVID Term was released in machine-readable formats (e.g., XML and JSON), which would contribute to the information retrieval, machine translation and advanced intelligent techniques application.

Bilingualism of Indonesian-English in Article Titles: A Case Study in Indonesian Mechanical Engineering Articles

Bilingualism happens not only orally but also in written Indonesian articles. Usually, the articles use Indonesian and English terms. Bilingualism even can be seen in the articles’ titles. One of the fields that often use bilingual terms is found in Mechanical Engineering's articles. It happens because mechanical engineering has specialized terminology that sometimes untranslated into Indonesian terms. Many Indonesian experts have translated many English books with many variations of translation results. Therefore, the translation results are still questioned whether they are acceptable or not in Indonesian. This study aims to examine the factors of bilingualisms by observing titles of articles and finding the translation methods to translate the terminology from English to Indonesian. This study was qualitative research; by using questionnaires and observation, the research reveals that the main factor is untranslatability, where the English terminology cannot find its equivalent meaning in Indonesian. By using Molina and Albir's translation techniques, researchers reveal that the English terminologies can be translated in Indonesian using (1) amplification, (2) borrowing, (3) established equivalence, (4) calque, and (5) literal translation. This study concludes that the untranslatability problem can be solved when the experts try to use the accepted translation results rather than using English terms.

A Data Driven Approach for Raw Material Terminology

The research presented in this paper aims at creating a bilingual (sr-en), easily searchable, hypertext, born-digital, corpus-based terminological database of raw material terminology for dictionary production. The approach is based on linking dictionaries related to the raw material domain, both digitally born and printed, into a lexicon structure, aligning terminology from different dictionaries as much as possible. This paper presents the main features of this approach, data used for compilation of the terminological database, the procedure by which it has been generated and a mobile application for its use. Available (terminological) resources will be presented—paper dictionaries and digital resources related to the raw material domain, as well as general lexica morphological dictionaries. Resource preparation started with dictionary (retro)digitisation and corpora enlargement, followed by adding new Serbian terms to general lexica dictionaries, as well as adding bilingual terms. Dictionary development is relying on corpus analysis, details of which are also presented. Usage examples, collocations and concordances play an important role in raw material terminology, and have also been included in this research. Some important related issues discussed are collocation extraction methods, the use of domain labels, lexical and semantic relations, definitions and subentries.

The KAS corpus of Slovenian academic writing

The paper presents the KAS corpus of Slovenian academic writing, which consists of almost 65,000 B.A./B.Sc., 16,000 M.A./M.Sc. and 1600 Ph.D. theses (5 million pages or 1.7 billion tokens) gathered from the digital libraries of Slovenian higher education institutions via the Slovenian Open Science portal. We discuss the compilation, meta-data, annotation, and distribution of the corpus, which is made freely available via on-line concordancers and is openly available for research through the CLARIN.SI research infrastructure. We also present the tools for mono- and bilingual term extraction and for thesis structure annotation that were developed in the scope of the project, including the manually annotated datasets used to train these tools. This specialised corpus, large by any standards, represents a substantial and highly useful language resource for the study of Slovenian academic writing and for terminology extraction.

La comprensión lectora en la enseñanza del español LE/L2: De la teoría a la práctica by Victoria Rodrigo

Reviewed by: La comprensión lectora en la enseñanza del español LE/L2: De la teoría a la práctica by Victoria Rodrigo Pete Swanson Rodrigo, Victoria. La comprensión lectora en la enseñanza del español LE/L2: De la teoría a la práctica. Routledge. 2019. Pp. 304. ISBN 978-1-13865-177-7. In La comprensión lectora en la enseñanza del español LE/L2: de la teoría a la práctica Rodrigo advances state-of-the-art theory and teaching practices for integrating reading skills into the teaching of Spanish. Serving as part of a cogent line of research on the effects of integrating reading into the Spanish as a foreign language curriculum, this timely publication bridges a much needed gap between research supporting reading as an integral part of second language acquisition (SLA) and classroom practice. Throughout the book, the author explains her goal of motivating students to read in the target language as well as to read a variety of genres and texts. Following a brief introduction and an explanation of a few preliminary concepts related to reading and SLA, the book is divided into 12 chapters. Afterward, Rodrigo offers some notes, a bibliography, a helpful glossary of bilingual terms, and answers to the activities presented in the book. In each chapter, she provides a consistent format that includes the chapter’s objectives, questions for reflection as readers enjoy the chapter, an overview of ideas, concepts, and studies related to the chapter, activities, pedagogical considerations, critical question appropriate for discussion, and readings that may be of interest to readers in order to gain a deeper understanding of the theme presented in the chapter. The author makes a special effort to relate her ideas to the proficiency levels for reading as set forth by the American Council on the Teaching of Foreign Language (ACTFL) and by the Common European Framework of Reference for Languages (CEFR). In chapter 1, “El proceso de lectura: fundamentos teóricos,” Rodrigo begins by presenting some general principles related to reading such as top-down and bottom-up processing while paying special attention to cognitive schema theory. She includes 13 activities in which readers can engage before providing several Consideraciones pedagógicas and further readings related to theoretical foundations of teaching reading, which are found at the end of each of the chapters. In chapter 2, “La mecánica de la lectura: características del lector eficaz,” she begins by posing six questions related to the mechanics of reading. In the chapter she discusses the research on various topics such as how eye movement, visual field, and the brain interacts and impacts one’s ability to read. Near the end of the chapter she presents characteristics of effective readers, the importance of readers acquiring reading fluency, and offers some suggestions on how to become a better reader. Chapter 3, “El poder de la lectura: la lectura en L2,” focuses on reading in the second language. Specifically, Rodrigo makes reference to Cummin’s (1979) notion of linguistic interdependence where certain first language knowledge can be positively transferred during the process of second language acquisition. Afterward, she presents the linguistic and cognitive benefits of reading in the second language. Next, in chapter 4, “Estrategias de lectura: los buenos lectores,” she lays out pre-reading, during the reading, and post-reading strategies. Among other parts of this book, I found this section to be of the utmost importance as many language teachers tend to underestimate the efficacy of pre-reading and post-reading strategies and activities. Near the end of the chapter, Rodrigo includes a brief Likert-scale survey that language teachers [End Page 139] can use with their students to reflect on certain strategies. In the following two chapters, “La comprensión lectora: la importancia del léxico” (chapter 5) and “Tipos de texto y formas de leer: criterios para su selección” (chapter 6), she discusses the role that vocabulary plays in reading by focusing on incidental acquisition and direct instruction as well as types of text and the criteria that should be used when selecting texts for second language learners. In my experience...

Reproduction, replication, analysis and adaptation of a term alignment approach

In this paper, we look at the issue of reproducibility and replicability in bilingual terminology alignment (BTA). We propose a set of best practices for reproducibility and replicability of NLP papers and analyze several influential BTA papers from this perspective. Next, we present our attempts at replication and reproduction, where we focus on a bilingual terminology alignment approach described by Aker et al. (Extracting bilingual terminologies from comparable corpora. In: Proceedings of the 51st annual meeting of the association for computational linguistics, vol. 1 402–411, 2013) who treat bilingual term alignment as a binary classification problem and train an SVM classifier on various dictionary and cognate-based features. Despite closely following the original paper with only minor deviations—in areas where the original description is not clear enough—we obtained significantly worse results than the authors of the original paper. We then analyze the reasons for the discrepancy and describe our attempts at adaptation of the approach to improve the results. Only after several adaptations, we achieve results which are close to the results published in the original paper. Finally, we perform the experiments to verify the replicability and reproducibility of our own code. We publish our code and datasets online to assure the reproducibility of the results of our experiments and implement the selected BTA models in an online platform making them easily reusable even by the technically less-skilled researchers.

IDENTIFYING SOCIAL MEDIA RESOURCES AVAILABLE TO CAREGIVERS OF ALS PATIENTS

Background: Amyotrophic Lateral Sclerosis (ALS) is a progressive neurodegenerative disorder that causes muscle weakness, disability, and death, with survival of 3-5 years and affecting all populations including Hispanics. ALS patients are mostly cared for by family caregivers (FCG) who experience burden, psychological distress and impaired quality-of-life. Thus, FCG may not leave their homes to access resources. Social media might be a way to accessing support, but little is known about quality/quantity of AL- FCG resources. Research Objectives: To identify and categorize types of bilingual resources available to ALS-FCG in Facebook. Methods: We used Facebook both groups (public and closed groups) and pages and collected numbers-of-likes, organization type and resource provided. Bilingual search terms (Spanish) included ALS/ALS-caregiver. Results: 24 pages/31 groups in English vs. 37 pages/29 groups in Spanish. English resources had more likes/members (3510/790 vs.410/95; p<0.001) and were more active (60+ posts in recent month). Community resources and provision of social support were similarly shared through groups in both languages; advocacy was more prominent among Spanish groups (69%vs.39%, p<0.001). English pages significantly provided more social support (96% vs.65%, p<0.001), more caregiver skills (67%vs.49%, p<0.001), inspirational roles (88% vs.59%, p<0.001). Spanish pages and groups were better in providing news/research to FCG (59%vs.16%, p<0.001). Implications for research, policy or practice: Facebook provides numerous useful bilingual resources to ALS-FCG. FCG may receive social support, inspiration, training, news/research and advocacy. Further interventions need to actively improve the role of social-media in supporting bilingual ALS FCG and use it as a platform of dissemination.

TermEnsembler

Abstract This paper describes TermEnsembler, a bilingual term extraction and alignment system utilizing a novel ensemble learning approach to bilingual term alignment. In the proposed system, the processing starts with monolingual term extraction from a language industry standard file type containing aligned English and Slovenian texts. The two separate term lists are then automatically aligned using an ensemble of seven bilingual alignment methods, which are first executed separately and then merged using the weights learned with an evolutionary algorithm. In the experiments, the weights were learned on one domain and tested on two other domains. When evaluated on the top 400 aligned term pairs, the precision of term alignment is over 96%, while the number of correctly aligned multi-word unit terms exceeds 30% when evaluated on the top 400 term pairs.

John Fryer’s Contribution to Standardization of Translated Scientific Terminology in Modern China

John Fryer was a British missionary in the late Qing Dynasty who came to China and was employed by The Translation Department of Kiangnan Arsenal. He has been engaged in the translation work for over 28 years, not only having translated a great deal of Western scientific works into Chinese, but also having contributed greatly to the standardization of the scientific terminology translation. This paper first attempts to probe into Fryer’s scientific translation practice and his translation ideas, and then points out that Fryer’s major contributions to the standardization of the scientific terminology translation in Modern China are that the magazine Ko-chih-hui-pien he established had helped greatly with the popularization of modern scientific knowledge, that the book Mirroring the Origins of Chemistry he translated had paved the way for the term translation of modern chemical elements, and that various lists of bilingual technical terms he made, to a great degree, had standardized the translation of scientific terminology.

Genex+, a Semantic-based Automatic Extractor of Examples Applied to Bilingual Terms

Genex+, a Semantic-based Automatic Extractor of Examples Applied to Bilingual Terms

Prolingua se bydrae tot terminologieontwikkeling in Afrikaans

Prolingua's Contribution to Terminology Development in Afri­kaans. The research problem addressed in this article deals with the isolated development of Afri­kaans terminology in a multilingual dispensation. The research problem manifests itself in three ways: the need for such terminology; the sustainability thereof; and whether a single institu­tion, such as Prolingua, could maintain such development. Prolingua, an association for English and Afrikaans language practitioners, was founded in 1950. At the time it was known as the Trans­vaal Association of Municipal Translators . As the name indicated, the members were mainly munici­pal officials. Municipal services included several services that, at the time needed bilingual terms for various areas in the workplace. The country's bilingual language policy then required terms to be translated and created for all municipal departments — suddenly there was a need for Afri­kaans terms. The aim of the newly established association was, among other things, to translate, create and standardise terminology and to discuss problems with translation. Later more attention was given to terminology-related problems and the association became more inclusive and inviting for language practitioners from other institutions to join its ranks. This article deals with the need for Afrikaans terminology and gives information on the history of Prolingua and its contribution to terminology development in Afrikaans, i.e. the Prolingua term list and other products and services. The contributions made by external collaborators regarding terminology development also receive attention. Prolingua's cooperation with other institutions is discussed. The article concludes with recommendations for a way forward. Keywords: classic origin; collaborator; cooperation; database; digiti­sation; digitalisation; harmonisation; language policy; language practi­tioner; neologism; online terminology products; standardisation; tech­nical dictionary; term creation; term list; terminology develop­ment; terminology; terminology management system

Improving automatic Chinese–Japanese patent translation using bilingual term extraction

The identification of terms in scientific and patent documents is a crucial issue for applications like information retrieval, text categorization, and also for machine translation. This paper describes a method to improve Chinese–Japanese statistical machine translation of patents by re‐tokenizing the training corpus with aligned bilingual multi‐word terms. We automatically extract multi‐word terms from monolingual corpora by combining statistical and linguistic filtering methods. An automatic alignment method is used to identify corresponding terms. The most promising bilingual multi‐word terms are extracted by setting some threshold on translation probabilities and further filtering by considering the components of the bilingual multi‐word terms in characters as well as the ratio of their lengths in words. We also use kanji (Japanese)–hanzi (Chinese) character conversion to confirm and extract more promising bilingual multi‐word terms. We obtain a high quality of correspondence with 93% in bilingual term extraction and a significant improvement of 1.5 BLEU score in a translation experiment. © 2017 Institute of Electrical Engineers of Japan. Published by John Wiley &amp; Sons, Inc.

Cross-lingual event-centered news clustering based on elements semantic correlations of different news

Cross-lingual event-centered news clustering aims to perform the clustering of news documents written in different languages into groups of documents that describe the same event. In order to solve the problem of similarity computation between bi-lingual documents, this paper propose a new method based on semantic correlations of news elements. First, using bilingual entity lexical and terms co-occurrences in news to acquire the semantic correlation of news elements in different language. Then, we compute the similarity between news in different languages using the GVSM model on this basis. Finally, Spectral Clustering is applied to categorize news stories. Experimental results show our method achieves promising results on the F value.