Cross-language Retrieval Research Articles

Chinese-Vietnamese cross-lingual event retrieval method based on knowledge distillation

Cross-lingual event retrieval is an information retrieval task aimed at cross-lingual event retrieval among multiple languages to find text or documents related to a specific event. Specific to Chinese-Vietnamese cross-language event retrieval, it involves using Chinese as a query to retrieve Vietnamese documents related to the query event. The critical issue is how to efficiently align query and document representations with limited resources. Existing cross-language pre-training models are trained on large-scale multilingual corpora, but their training goals do not include explicit language alignment tasks. Due to the uneven distribution of training corpora between different languages, these models have The problem of language bias. Therefore, this linguistic bias is also inherited in cross-lingual retrieval based on these models. To solve this problem, this paper proposes a Chinese-Vietnamese cross-lingual event retrieval method based on knowledge distillation. This approach enables the model to learn good query-document matching features from monolingual retrieval by transferring knowledge from high-resource to low-resource languages. By enhancing the alignment between queries and documents in different languages in a shared semantic space, the method improves the performance of Chinese-Vietnamese cross-lingual event retrieval.

Approaches to Cross-Language Retrieval of Similar Legal Documents Based on Machine Learning

Approaches to Cross-Language Retrieval of Similar Legal Documents Based on Machine Learning

English Audio Language Retrieval Based on Adaptive Speech-Adjusting Algorithm

For the purpose of language retrieval for English listening, this paper designs and implements a cross-language information retrieval system for English listening. Different implementation methods of cross-language information retrieval, query, and translation are analyzed. The system adopts cross-language information retrieval technology based on bilingual dictionaries. According to the cross-language retrieval system of the existing bilingual dictionaries and monolingual dictionaries, based on the design and implementation of the fuzzy search dictionary lookup mechanism, the existing dictionary lookup mechanism is constructed and analyzed. Aiming at the problem of translation ambiguity in information retrieval systems based on bilingual dictionaries, a disambiguities elimination algorithm based on cooccurrence technology is proposed. In continuous speech, the speed of different speakers in different contexts is very different. Deviation from normal speech speed often leads to recognition errors, which makes recognition performance decline. Considering that the influence of speech speed on the length of speech units increases or decreases synchronously, and there is a strong correlation between the lengths of adjacent speech units, an adaptive speech speed algorithm is proposed based on the framework of implicit Markov model based on the information of the length of speech units. Experiments on number string and large vocabulary continuous speech recognition show that the algorithm is effective.

Unitization facilitates familiarity-based cross-language associative recognition

The unitization effect means a phenomenon in which familiarity can contribute to associative recognition judgments when pairs of items are treated as a single entity rather than two separate items. Cumulative evidences suggested that the unitization effect was not influenced by the type of language, and this effect could be generalized to bilinguals when they performed an associative recognition in their second language. In the present study, the influence of familiarity on cross-language associative retrieval under unitization and the underlying neurophysiological mechanism behind this effect were investigated. Participants completed two “study-test” tasks presented in intralinguistic (from Uygur to Uygur) or interlinguistic assignment (from Chinese to Uygur) respectively. The study showed that: (1) during intralinguistic assignments, both FN400 and LPC were found under unitization for balanced and unbalanced bilinguals, while an LPC but not FN400 was found under non-unitization. (2) During interlinguistic assignments, both FN400 and LPC were found under unitization for balanced bilinguals. However, an LPC but not FN400 was found under unitization for unbalanced bilinguals. Collectively, these results indicated that unitization facilitated familiarity to support cross-language retrieval. In particular, the effects of familiarity on cross-language retrieval were mediated by the second language proficiency.

An axiomatic approach to corpus-based cross-language information retrieval

A major challenge in cross-language information retrieval (CLIR) is the adoption of translation knowledge in retrieval models, as it affects term weighting which is known to highly impact the retrieval performance. Despite its importance, how different approaches for integration of translation knowledge into retrieval models relatively perform has not been analytically examined. In this paper, we present an analytical investigation of using translation knowledge in CLIR. In particular, by adopting the axiomatic analysis framework, we formulate impacts of using translation knowledge on document ranking as constraints that any cross-language retrieval model should satisfy. We then consider state-of-the-art CLIR methods and check whether they satisfy these constraints. Our study shows that none of the existing methods satisfies all constraints. Based on the defined constraints, we propose the hierarchical query modeling method for CLIR which satisfies more constraints and achieves a higher CLIR performance, compared to the existing methods.

Cross-language question retrieval with multi-layer representation and layer-wise adversary

In cross-language question retrieval (CLQR), users employ a new question in one language to search the community question answering (CQA) archives for similar questions in another language. In addition to the ranking problem in monolingual question retrieval, one needs to bridge the language gap in CLQR. The existing adversarial models for cross-language learning normally rely on a single adversarial component. Since natural languages consist of units of different abstract levels, we argue that crossing the language gap adaptatively on different levels with multiple adversarial components should lead to smoother text representation and better CLQR performance. To this end, we first encode questions into multi-layer representations of different abstract levels with a CNN based model which enhances conventional models with diverse kernel shapes and the corresponding pooling strategy so as to capture different aspects of a text segment. We then impose a set of adversarial components on different layers of question representation so as to decide the appropriate abstract levels and their role in performing cross-language mapping. Experimental results on two real-world datasets demonstrate that our model outperforms state-of-the-art models for CLQR, which is on par with the strong machine translation baselines and most monolingual baselines.

Arabic Language Sentiment Analysis Via Cross-Language Translation

Social platforms on the web give us a huge amount of data like comments, messages, products' reviews and posts. Sentiment analysis on social users' data is a valuable analysis for automatically understanding people's opinions about products or some interesting topics, and this analysis provides valuable information for informed decision making in different domains. Arab web users number is about 200 million users; this huge number represents the strong impact on marketing which makes the sentiment analysis of Arabic language hot topic. This paper proposed an Arabic sentiment analysis model to increase the accuracy of Arabic sentiment analysis. It is based on a cross-language retrieval model. The proposed model was tested on a dataset extracted from twitter and manually sentimentally classified by experts, and it achieved 90.62% accuracy.

English corpus and literary analysis based on statistical language model

In this paper, the cross-language retrieval model based on statistical language model, cross-lingual text categorization method and cross-lingual text clustering method are studied systematically and deeply. Without any help of cross-lingual resources such as machine translation and bilingual dictionaries, this paper can solve the many-to-many problem of word translation in CLIR and solve the problem of unregistered words partially. Under a unified framework, a series of topics are extracted from bilingual parallel corpora to form the thematic space for each language. Thematic space of each language exists independently, and the bilingual subject space is established through the bilingual semantic correspondence. The bilingual subject space reflects the semantic correspondence between documents and documents, words and words. It reveals the inherent structure and internal relations among languages and languages.

Leveraging comparable corpora for cross-lingual information retrieval in resource-lean language pairs

Cross-language information retrieval (CLIR) has so far been studied with the assumption that some rich linguistic resources such as bilingual dictionaries or parallel corpora are available. But creation of such high quality resources is labor-intensive and they are not always at hand. In this paper we investigate the feasibility of using only comparable corpora for CLIR, without relying on other linguistic resources. Comparable corpora are text documents in different languages that cover similar topics and are often naturally attainable (e.g., news articles published in different languages at the same time period). We adapt an existing cross-lingual word association mining method and incorporate it into a language modeling approach to cross-language retrieval. We investigate different strategies for estimating the target query language models. Our evaluation results on the TREC Arabic---English cross-lingual data show that the proposed method is effective for the CLIR task, demonstrating that it is feasible to perform cross-lingual information retrieval with just comparable corpora.

Quality issues in Thesaurus building. A case study from the medical domain

To ensure the quality of a medical thesaurus is a non-trivial task, due to the inherent complexity of medical terminology. The peculiarities of the medical sublanguage and the subjectivism of lexicographers' choices complicate the thesaurus construction process. Our experience is based on the MorphoSaurus lexicon, the basis of a biomedical cross-language indexing and retrieval system. We describe two complementary maintenance approaches, viz. i) corpus-based error detection, and ii) thesaurus anomaly detection. These techniques were developed to detect so-called dynamic and static errors, which are committed by the lexicographers during the construction and maintenance process. Considering multilingual parallel corpora, the distribution of semantic identifiers should be similar whenever comparing related texts in different languages. In the first approach, those semantic identifiers are identified that exhibit greatest frequency variations when comparing text pairs. A manual review of these search results is supposed to spot content errors, which are subsequently classified and fixed by the lexicographers. The second approach analyses transaction-based anomalies, which are identified by interpreting the log of lexicographers' actions during thesaurus maintenance. This methodology highlights the four most common types of this kind of anomaly and evaluates the effectiveness of the corpus-based detection techniques. The overall quality improvement of the thesaurus was evaluated using the OHSUMED IR benchmark.

An intelligent Web agent that autonomously learns how to translate

We describe the design of an autonomous agent that can teach itself how to translate from a foreign language, by first assembling its own training set, then using it to improve its vocabulary and language model. The key idea is that a Statistical Machine Translation package can be used for the Cross-Language Retrieval Task of assembling a training set from a vast amount of available text e.g. a large multilingual corpus, or the Web and then train on that data, repeating the process several times. The stability issues related to such a feedback loop are addressed by a mathematical model, connecting statistical and control-theoretic aspects of the system. We test it on controlled environment and real-world tasks, showing that indeed this agent can improve its translation performance autonomously and in a stable fashion, when seeded with a very small initial training set. We develop a multiprocessor version of the agent that directly accesses the Web using a Web search engine and taking advantage of the big amount of data available there. The modelling approach we develop for this agent is general, and we believe that it will be useful for an entire class of self-learning autonomous agents working on the Web.

Concepts Mapping in the Legal Domain: Some Reflections

AbstractThis paper, by Ginevra Peruginelli, examines the general issue of mapping concepts of different legal orders, with a focus on legal terminology and semantics of the law. Interoperability between legal thesauri is a possible operative solution in so far as it meets two important functions: cross-collection retrieval and cross-language retrieval. At a practical level a feasibility study, carried out by the Institute of Legal Information Theory and Techniques of the National Research Council of Italy is described. The study aims at aligning a number of thesauri used in e-government services within the EU, while testing new methods of automatic mapping.

Biomedical Imaging Modality Classification Using Combined Visual Features and Textual Terms

We describe an approach for the automatic modality classification in medical image retrieval task of the 2010 CLEF cross-language image retrieval campaign (ImageCLEF). This paper is focused on the process of feature extraction from medical images and fuses the different extracted visual features and textual feature for modality classification. To extract visual features from the images, we used histogram descriptor of edge, gray, or color intensity and block-based variation as global features and SIFT histogram as local feature. For textual feature of image representation, the binary histogram of some predefined vocabulary words from image captions is used. Then, we combine the different features using normalized kernel functions for SVM classification. Furthermore, for some easy misclassified modality pairs such as CT and MR or PET and NM modalities, a local classifier is used for distinguishing samples in the pair modality to improve performance. The proposed strategy is evaluated with the provided modality dataset by ImageCLEF 2010.

Handbook of research on Web 2.0, 3.0, and X.0: technologies, business, and social applications

As the Web continues to evolve, advances in Web technology forge many new applications that were not previously feasible, resulting in new usage paradigms in business, social interaction, governance, and education. The Handbook of Research on Web 2.0, 3.0, and X.0: Technologies, Business, and Social Applications is a comprehensive reference source on next-generation Web technologies and their applications. This in-depth two volume collection covers the latest aspects and applications of Web technologies including the introduction of virtual reality commerce systems, the importance of social bookmarking, cross-language data retrieval, image searching, cutting-edge Web security technologies, and innovative healthcare and finance applications on the Web. Examining the social, cultural, and ethical issues these applications present, this Handbook of Research discusses real-world examples and case studies valuable to academicians, researchers, and practitioners.

Does dictionary based bilingual retrieval work in a non-normalized index?

Many operational IR indexes are non-normalized, i.e. no lemmatization or stemming techniques, etc. have been employed in indexing. This poses a challenge for dictionary-based cross-language retrieval (CLIR), because translations are mostly lemmas. In this study, we face the challenge of dictionary-based CLIR in a non-normalized index. We test two optional approaches: FCG (Frequent Case Generation) and s-gramming. The idea of FCG is to automatically generate the most frequent inflected forms for a given lemma. FCG has been tested in monolingual retrieval and has been shown to be a good method for inflected retrieval, especially for highly inflected languages. S-gramming is an approximate string matching technique (an extension of n-gramming). The language pairs in our tests were English–Finnish, English–Swedish, Swedish–Finnish and Finnish–Swedish. Both our approaches performed quite well, but the results varied depending on the language pair. S-gramming and FCG performed quite equally in all the other language pairs except Finnish–Swedish, where s-gramming outperformed FCG.

Accessing Legal Information Across Boundaries: A New Challenge

AbstractIn the actual multilingual and multicultural environment there is a significant need, in the academic world, in the legal profession, in business settings as well as in the context of public administration services to citizens, of common understanding and exchange of legal concepts of the various legal systems. At the same time, there is a strong pressure for the preservation of their basic sense and value. Both requirements are quite difficult to meet, and they are complicated by the complexity of legal language and by the variety of modalities used to express law within the various legal systems. Unlike a number of technical and scientific disciplines where a fair correspondence exists between concepts across languages, serious difficulties arise in interpreting law across countries and languages. This is largely due to the system-bound nature of legal terminology. This paper focuses on cross-language retrieval systems’ ability to facilitate access to legal information across different languages and legal orders. As such, issues are addressed relating to linguistics and translation theory, comparative law, theory of law, as well as natural language processing techniques, while some recommendations are provided with the aim to contribute to cross-language retrieval of law.

Frequency-based identification of correct translation equivalents (FITE) obtained through transformation rules

We devised a novel statistical technique for the identification of the translation equivalents of source words obtained by transformation rule based translation (TRT). The effectiveness of the technique called frequency-based identification of translation equivalents ( FITE ) was tested using biological and medical cross-lingual spelling variants and out-of-vocabulary (OOV) words in Spanish-English and Finnish-English TRT. The results showed that, depending on the source language and frequency corpus, FITE-TRT (the identification of translation equivalents from TRT's translation set by means of the FITE technique) may achieve high translation recall. In the case of the Web as the frequency corpus, translation recall was 89.2%--91.0% for Spanish-English FITE-TRT. For both language pairs FITE-TRT achieved high translation precision: 95.0%--98.8%. The technique also reliably identified native source language words: source words that cannot be correctly translated by TRT. Dictionary-based CLIR augmented with FITE-TRT performed substantially better than basic dictionary-based CLIR where OOV keys were kept intact. FITE-TRT with Web document frequencies was the best technique among several fuzzy translation/matching approaches tested in cross-language retrieval experiments. We also discuss the application of FITE-TRT in the automatic construction of multilingual dictionaries.

On the role of user-centred evaluation in the advancement of interactive information retrieval

This paper discusses the role of user-centred evaluations as an essential method for researching interactive information retrieval. It draws mainly on the work carried out during the Clarity Project where different user-centred evaluations were run during the lifecycle of a cross-language information retrieval system. The iterative testing was not only instrumental to the development of a usable system, but it enhanced our knowledge of the potential, impact, and actual use of cross-language information retrieval technology. Indeed the role of the user evaluation was dual: by testing a specific prototype it was possible to gain a micro-view and assess the effectiveness of each component of the complex system; by cumulating the result of all the evaluations (in total 43 people were involved) it was possible to build a macro-view of how cross-language retrieval would impact on users and their tasks. By showing the richness of results that can be acquired, this paper aims at stimulating researchers into considering user-centred evaluations as a flexible, adaptable and comprehensive technique for investigating non-traditional information access systems.

Image retrieval: Benchmarking visual information indexing and retrieval systems

Image retrieval: Benchmarking visual information indexing and retrieval systems

Advanced learning algorithms for cross-language patent retrieval and classification

We study several machine learning algorithms for cross-language patent retrieval and classification. In comparison with most of other studies involving machine learning for cross-language information retrieval, which basically used learning techniques for monolingual sub-tasks, our learning algorithms exploit the bilingual training documents and learn a semantic representation from them. We study Japanese–English cross-language patent retrieval using Kernel Canonical Correlation Analysis (KCCA), a method of correlating linear relationships between two variables in kernel defined feature spaces. The results are quite encouraging and are significantly better than those obtained by other state of the art methods. We also investigate learning algorithms for cross-language document classification. The learning algorithm are based on KCCA and Support Vector Machines (SVM). In particular, we study two ways of combining the KCCA and SVM and found that one particular combination called SVM_2k achieved better results than other learning algorithms for either bilingual or monolingual test documents.