Cross-language Retrieval Research Articles

Biomedical information retrieval across languages

This work presents a new dictionary-based approach to biomedical cross-language information retrieval (CLIR) that addresses many of the general and domain-specific challenges in current CLIR research. Our method is based on a multilingual lexicon that was generated partly manually and partly automatically, and currently covers six European languages. It contains morphologically meaningful word fragments, termed subwords. Using subwords instead of entire words significantly reduces the number of lexical entries necessary to sufficiently cover a specific language and domain. Mediation between queries and documents is based on these subwords as well as on lists of word-n-grams that are generated from large monolingual corpora and constitute possible translation units. The translations are then sent to a standard Internet search engine. This process makes our approach an effective tool for searching the biomedical content of the World Wide Web in different languages. We evaluate this approach using the OHSUMED corpus, a large medical document collection, within a cross-language retrieval setting.

The CLEF 2005 Automatic Medical Image Annotation Task

In this paper, the automatic annotation task of the 2005 CLEF cross-language image retrieval campaign (ImageCLEF) is described. This paper focuses on the database used, the task setup, and the plans for further medical image annotation tasks in the context of ImageCLEF. Furthermore, a short summary of the results of 2005 is given. The automatic annotation task was added to ImageCLEF in 2005 and provides the first international evaluation of state-of-the-art methods for completely automatic annotation of medical images based on visual properties. The aim of this task is to explore and promote the use of automatic annotation techniques to allow for extracting semantic information from little-annotated medical images. A database of 10.000 images was established and annotated by experienced physicians resulting in 57 classes, each with at least 10 images. Detailed analysis is done regarding the (i) image representation, (ii) classification method, and (iii) learning method. Based on the strong participation of the 2005 campain, future benchmarks are planned.

TREC: Experiment and Evaluation in Information Retrieval Ellen M. Voorhees and Donna K. Harman (editors) (National Institute of Standards and Technology), Cambridge, MA: The MIT Press (Digital libraries and electronic publishing series, edited by William Y. Arms), 2005, x+462 pp; hardbound, ISBN 0-262-22073-3, $45.00

The Text REtrieval Conference (TREC), a yearly workshop hosted by the US government's National Institute of Standards and Technology, provides the infrastructure necessary for large-scale evaluation of text retrieval methodologies. With the goal of accelerating research in this area, TREC created the first large test collections of full-text documents and standardized retrieval evaluation. The impact has been significant; since TREC's beginning in 1992, retrieval effectiveness has approximately doubled. TREC has built a variety of large test collections, including collections for such specialized retrieval tasks as cross-language retrieval and retrieval of speech. Moreover, TREC has accelerated the transfer of research ideas into commercial systems, as demonstrated in the number of retrieval techniques developed in TREC that are now used in Web search engines.This book provides a comprehensive review of TREC research, summarizing the variety of TREC results, documenting the best practices in experimental information retrieval, and suggesting areas for further research. The first part of the book describes TREC's history, test collections, and retrieval methodology. Next, the book provides track reports -- describing the evaluations of specific tasks, including routing and filtering, interactive retrieval, and retrieving noisy text. The final part of the book offers perspectives on TREC from such participants as Microsoft Research, University of Massachusetts, Cornell University, University of Waterloo, City University of New York, and IBM. The book will be of interest to researchers in information retrieval and related technologies, including natural language processing.

Integrating textual and visual information for cross-language image retrieval: A trans-media dictionary approach

This paper explores the integration of textual and visual information for cross-language image retrieval. An approach which automatically transforms textual queries into visual representations is proposed. First, we mine the relationships between text and images and employ the mined relationships to construct visual queries from textual ones. Then, the retrieval results of textual and visual queries are combined. To evaluate the proposed approach, we conduct English monolingual and Chinese–English cross-language retrieval experiments. The selection of suitable textual query terms to construct visual queries is the major issue. Experimental results show that the proposed approach improves retrieval performance, and use of nouns is appropriate to generate visual queries.

Automatic lexeme acquisition for a multilingual medical subword thesaurus

Purpose We present a method for the automated acquisition of a multilingual medical lexicon (for Spanish, French and Swedish) to be used within the framework of a medical cross-language text retrieval system. Methods For the lexical acquisition process, we incorporate seed lexicons and lists of trusted term translations derived from the UMLS Metathesaurus. The seed lexicons for Spanish, French and Swedish are automatically generated from (previously manually constructed) Portuguese, German and English sources by simple string transformations. Lexical and semantic hypotheses are then validated by processing pairs of term translations. In a last step, we use the cleaned list of “approved” translations in order to augment, step by step, the target dictionaries by processing the parallel corpora in terms of co-occurrence patterns of hypothesized translation equivalents which cannot be derived by simple character substitutions. Results An existing multilingual lexicon for the medical domain with about 60,000 entries for English, German, and Portuguese was automatically augmented by more then 17,000 new lexemes for Spanish, French, and Swedish. Conclusions Our approach constitutes a promising method for the automated creation of new lexicon entries and their linkage to semantic identifiers.

Combination Approaches in Korean Information Retrieval: Words vs. n-grams, and Query Translation vs. Document Translation

This paper reports our proposal and experimental results at the NTCIR-4 CLIR task. For monolingual information retrieval, we use a combination strategy that integrates words and n-grams at the ranked list level. In combining words and n-grams, we concentrate on generating several ranked lists showing different retrieval characteristics on word and n-gram indexes by incorporating feedback schemes. For cross-language information retrieval, we attempt a dictionary-based bi-directional combination of query translation and document translation. For both query translation and document translation, their naive translation is used. Experimental evaluations on CJK monolingual and KC/KJ cross-language retrieval give promising results on our combination approaches: words vs. ngrams, and query translation vs. document translation.

English-Arabic Cross-Language Information Retrieval Based on Parallel Documents

In cross-language information retrieval (CLIR), queries in a source language are used to retrieve relevant documents in a target language. This paper describes the automatic construction of a translation matrix for English-Arabic CLIR applications. English-Arabic parallel sentences are translated using an adaptation of the expected mutual information measure (EMIM) technique and a matrix of translation terms is created. We evaluate our translation matrix as part of a retrieval system by comparing the effectiveness of cross-language retrieval and monolingual retrieval. The results show that the performance of English-Arabic CLIR using the translation matrix for query translation is either comparable to or better than that of monolingual Arabic retrieval depending on the number of translation terms used and the type of indexing method chosen.

Towards effective strategies for monolingual and bilingual information retrieval

At the NTCIR-4 workshop, Justsystem Corporation (JSC) and Clairvoyance Corporation (CC) collaborated in the cross-language retrieval task (CLIR). Our goal was to evaluate the performance and robustness of our recently developed commercial-grade CLIR systems for English and Asian languages. The main contribution of this article is the investigation of different strategies, their interactions in both monolingual and bilingual retrieval tasks, and their respective contributions to operational retrieval systems in the context of NTCIR-4. We report results of Japanese and English monolingual retrieval and results of Japanese-to-English bilingual retrieval. In monolingual retrieval analysis, we examine two special properties of the NTCIR experimental design (two levels of relevance and identical queries in multiple languages) and explore how they interact with strategies of our retrieval system, including pseudo-relevance feedback, multi-word term down-weighting, and term weight merging strategies. Our analysis shows that the choice of language (English or Japanese) does not have a significant impact on retrieval performance. Query expansion is slightly more effective with relaxed judgments than with rigid judgments. For better retrieval performance, weights of multi-word terms should be lowered. In the bilingual retrieval analysis, we aim to identify robust strategies that are effective when used alone and when used in combination with other strategies. We examine cross-lingual specific strategies such as translation disambiguation and translation structuring, as well as general strategies such as pseudo-relevance feedback and multi-word term down-weighting. For shorter title topics, pseudo-relevance feedback is a major performance enhancer, but translation structuring affects retrieval performance negatively when used alone or in combination with other strategies. All experimented strategies improve retrieval performance for the longer description topics, with pseudo-relevance feedback and translation structuring as the major contributors.

MorphoSaurus

We propose an interlingua-based indexing approach to account for the particular challenges that arise in the design and implementation of cross-language document retrieval systems for the medical domain. Documents, as well as queries, are mapped to a language-independent conceptual layer on which retrieval operations are performed. We contrast this approach with the direct translation of German queries to English ones which, subsequently, are matched against English documents. We evaluate both approaches, interlingua-based and direct translation, on a large medical document collection, the OHSUMED corpus. A substantial benefit for interlingua-based document retrieval using German queries on English texts is found, which amounts to 93% of the (monolingual) English baseline. Most state-of-the-art cross-language information retrieval systems translate user queries to the language(s) of the target documents. In contra-distinction to this approach, translating both documents and user queries into a language-independent, concept-like representation format is more beneficial to enhance cross-language retrieval performance.

Translation events in cross-language information retrieval

Cross-Language Information Retrieval (CLIR) systems enable users to formulate queries in their native language to retrieve documents in foreign languages. Because queries and documents in CLIR do not necessarily share the same language, translation is needed before matching can take place. This translation step tends to cause a reduction in the retrieval performance of CLIR as compared to monolingual information retrieval. To understand the events occurring in crosslanguage retrieval query translation and the relation of these events to retrieval performance, the study explored the following research questions:

Anchor text mining for translation of Web queries

To discover translation knowledge in diverse data resources on the Web, this article proposes an effective approach to finding translation equivalents of query terms and constructing multilingual lexicons through the mining of Web anchor texts and link structures. Although Web anchor texts are wide-scoped hypertext resources, not every particular pair of languages contains sufficient anchor texts for effective extraction of translations for Web queries. For more generalized applications, the approach is designed based on a transitive translation model. The translation equivalents of a query term can be extracted via its translation in an intermediate language. To reduce interference from translation errors, the approach further integrates a competitive linking algorithm into the process of determining the most probable translation. A series of experiments has been conducted, including performance tests on term translation extraction, cross-language information retrieval, and translation suggestions for practical Web search services, respectively. The obtained experimental results have shown that the proposed approach is effective in extracting translations of unknown queries, is easy to combine with the probabilistic retrieval model to improve the cross-language retrieval performance, and is very useful when the considered language pairs lack a sufficient number of anchor texts. Based on the approach, an experimental system called LiveTrans has been developed for English--Chinese cross-language Web search.

Mandarin–English Information (MEI): investigating translingual speech retrieval

This paper describes the Mandarin–English Information (MEI) project, where we investigated the problem of cross-language spoken document retrieval (CL-SDR), and developed one of the first English–Chinese CL-SDR systems. Our system accepts an entire English news story (text) as query, and retrieves relevant Chinese broadcast news stories (audio) from the document collection. Hence, this is a cross-language and cross-media retrieval task. We applied a multi-scale approach to our problem, which unifies the use of phrases, words and subwords in retrieval. The English queries are translated into Chinese by means of a dictionary-based approach, where we have integrated phrase-based translation with word-by-word translation. Untranslatable named entities are transliterated by a novel subword translation technique. The multi-scale approach can be divided into three subtasks – multi-scale query formulation, multi-scale audio indexing (by speech recognition) and multi-scale retrieval. Experimental results demonstrate that the use of phrase-based translation and subword translation gave performance gains, and multi-scale retrieval outperforms word-based retrieval.

Applying query structuring in cross-language retrieval

We will explore various ways to apply query structuring in cross-language information retrieval. In the first test, English queries were translated into Finnish using an electronic dictionary, and were run in a Finnish newspaper database of 55,000 articles. Queries were structured by combining the Finnish translation equivalents of the same English query key using the syn-operator of the InQuery retrieval system. Structured queries performed markedly better than unstructured queries. Second, the effects of compound-based structuring using a proximity operator for the translation equivalents of query language compound components were tested. The method was not useful in syn-based queries but resulted in decrease in retrieval effectiveness. Proper names are often non-identical spelling variants in different languages. This allows n-gram based translation of names not included in a dictionary. In the third test, a query structuring method where the Boolean and-operator was used to assign more weight to keys translated through n-gram matching gave good results.

Semantic annotation for concept-based cross-language medical information retrieval

We present a framework for concept-based cross-language information retrieval in the medical domain, which is under development in the MUCHMORE project. Our approach is based on using the Unified Medical Language System (UMLS) as the primary source of semantic data. Documents and queries are annotated with multiple layers of linguistic information. Linguistic processing includes part-of-speech tagging, morphological analysis, phrase recognition and the identification of medical terms and semantic relations between them. The paper describes experiments in monolingual and cross-language document retrieval, performed on a corpus of medical abstracts. Results show that linguistic processing, especially lemmatization and compound analysis for German, is a crucial step in achieving a good baseline performance. On the other hand, they show that semantic information, specifically the combined use of concepts and relations, increases the performance in monolingual and cross-language retrieval.

Evaluating Chinese Text Retrieval with Multilingual Queries

This paper reports the design of a Chinese test collection with multilingual queries and the application of this test collection to evaluate information retrieval (IR) systems. The effective indexing units, IR models, translation techniques, and query expansion for Chinese text retrieval are identified. The collaboration of East Asian countries for construction of test collections for cross-language multilingual text retrieval is also discussed in this paper. As well, a tool is designed to help assessors judge relevance and gather the events of relevance judgment. The log file created by this tool will be used to analyze the behaviors of assessors in the future.

웹 이용자의 검색엔진 활용 및 탐색 행위와 성향 분석

본 연구는 웹 이용자들이 검색엔진을 어떻게 선택하여. 어떠한 기능들을 활용하며, 검색결과는 어떻게 평가하는지 그리고 어떤 어려움을 겪고 있는지를 밝혀 보고자 하였다. 28명의 대학의 교수와 대학원생으로 구성된 이용자들을 대상으로 한 인터뷰결과를 분석한다. 연구 결과에 따르면, 본 연구의 참가자들은 검색결과에 대한 평가보다는 특정한 기능이나 익숙함에 근거하여 엔진을 선택하였다. 이들은 통합검색에 대해서는 의견이 양분되어 있었으며, 연산자의 사용이 결과에 미치는 영향이 거의 없다고 보고 있었다. 검색엔진에 대한 평가를 내릴 때에도 검색결과의 정확성외에 결과를 보여주는 인터페이스 디자인에도 상당한 관심을 가지고 있는 것으로 나타났다. This study examines overall user experience associated with Web search engine use including selection, usage of search features, evaluation. The data were collected through individual interviews with 28 faculty members and graduate students. It was found that users tend to select a search engine based on experience and knowledge of certain features and familiarity with an engine itself more than based on previous experience with search results. The results showed the users had mixed opinions regarding cross language retrieval while they did not believe the usage of operators effect the search results. It appears that users are interested in interface design as well as the accuracy of search results.

Exploiting the LDC Chinese-English Bilingual Wordlist for Cross Language Information Retrieval

We investigated using the LDC English/Chinese bilingual wordlists for English-Chinese cross language retrieval. It is shown that the Chinese-to-English wordlist can be considered as both a phrase and word dictionary, and is preferable to the English-to-Chinese version in terms of phrase translation and word translation selection. Additional techniques such as frequency-based term selection, translation set weighting and term co-occurrence data were employed. Experiments show that within the TREC 5&6 Chinese corpus and retrieval environment, 74% of monolingual effectiveness is achievable for short queries of a few English words, and 85% for long queries of paragraph sizes.

CROSS-LANGUAGE TEXT RETRIEVAL BY QUERY TRANSLATION USING TERM REWEIGHTING

In a dictionary-based query translation for cross-language text retrieval, transfer ambiguity is one of the main causes of performance deterioration, but the problem has not received significant attention in this field. To resolve transfer ambiguity, this paper proposes a two-phase query translation based on term reweighting, which uses a bilingual transfer dictionary, originally designed for machine translation. In general, source language query terms each show some word association with others, so that their correct translations should be more likely to co-occur in target documents. Based on this simple intuition, the first phase discriminates more relevant target documents from the others. Using statistical and ranking information from the highly relevant documents, the second phase then converts a translated query vector into reweighted form to add an extra weight on probably correct target terms. In experiments, the results were remarkable: the proposed method achieved almost the same performance as the monolingual IR system, actually contributing to an improvement of precision by about 9% over a baseline system.

SIGIR workshop on interactive retrieval at TREC and beyond

The annual Text Retrieval Conference (TREC) has become a major event in information retrieval (IR) research. Over the last few years, its main focus has changed from the common ad hoc and routing tasks to tracks focused on special interests, such as cross-language retrieval, question answering, and large database/Web retrieval. In each of the tracks, a common task and test collection is developed each year for all participating groups to undertake. One problem the tracks have is a paucity of face-to-face meetings, since the only certain time each track actually meets is at the annual TREC meeting. For many tracks, this time is too early to work out all the details of the coming year’s track, and most additional work is done via email.

Using eurowordnet in a concept-based approach to cross-language text retrieval

We present an approach to cross-language text retrieval based on the EuroWordNet (EWN) multilingual semantic database. EuroWordNet is a multilingual, WordNet-like database with basic semantic relations between words for several European languages (English, Dutch, Spanish, Italian, German, French, Czech, and Estonian). In addition to the relations in WordNet 1.5, EWN includes domain labels, cross-language, and cross-part-of-speech relations, which are directly useful for multilingual information retrieval. In our approach, documents in any language covered by EuroWordNet are indexed in a space of language-independent concepts (the EuroWordNet Inter Lingual Index), thus turning term weighting and query/document matching into language-independent tasks. We report on the results of a number of experiments that measure the potential benefits of the approach and its tolerance to word sense disambiguation errors. In our monolingual experiments, the classical, vector space model for text retrieval is shown to give better results (up to 29% better in our experiments) if WordNet synsets are chosen as the indexing space, instead of word forms. This result is obtained for a manually disambiguated test collection derived from the SEMCOR annotated corpus. The sensitivity of retrieval performance to (automatic) disambiguation errors is also measured. Our preliminary bilingual experiments, also reported here, show that our approach can sensibly outperform a naive, dictionary-based, translation of the query terms into the target language.