Phil Vines

Using the web for automated translation extraction in cross-language information retrieval

There have been significant advances in Cross-Language Information Retrieval (CLIR) in recent years. One of the major remaining reasons that CLIR does not perform as well as monolingual retrieval is the presence of out of vocabulary (OOV) terms. Previous work has either relied on manual intervention or has only been partially successful in solving this problem. We use a method that extends earlier work in this area by augmenting this with statistical analysis, and corpus-based translation disambiguation to dynamically discover translations of OOV terms. The method can be applied to both Chinese-English and English-Chinese CLIR, correctly extracting translations of OOV terms from the Web automatically, and thus is a significant improvement on earlier work.

Automatic acquisition of chinese–english parallel corpus from the web

Parallel corpora are a valuable resource for tasks such as cross-language information retrieval and data-driven natural language processing systems. Previously only small scale corpora have been available, thus restricting their practical use. This paper describes a system that overcomes this limitation by automatically collecting high quality parallel bilingual corpora from the web. Previous systems used a single principle feature for parallel web page verification, whereas we use multiple features to identify parallel texts via a k-nearest-neighbor classifier. Our system was evaluated using a data set containing 6500 Chinese–English candidate parallel pairs that have been manually annotated. Experiments show that the use of a k-nearest-neighbors classifier with multiple features achieves substantial improvements over the systems that use any one of these features. The system achieved a precision rate of 95% and a recall rate of 97%, and thus is a significant improvement over earlier work.

Using relative entropy for authorship attribution

Authorship attribution is the task of deciding who wrote a particular document. Several attribution approaches have been proposed in recent research, but none of these approaches is particularly satisfactory; some of them are ad hoc and most have defects in terms of scalability, effectiveness, and efficiency. In this paper, we propose a principled approach motivated from information theory to identify authors based on elements of writing style. We make use of the Kullback-Leibler divergence, a measure of how different two distributions are, and explore several different approaches to tokenizing documents to extract style markers. We use several data collections to examine the performance of our approach. We have found that our proposed approach is as effective as the best existing attribution methods for two class attribution, and is superior for multi-class attribution. It has lower computational cost and is cheaper to train. Finally, our results suggest this approach is a promising alternative for other categorization problems.

Chinese OOV translation and post-translation query expansion in chinese--english cross-lingual information retrieval

Cross-lingual information retrieval allows users to query mixed-language collections or to probe for documents written in an unfamiliar language. A major difficulty for cross-lingual information retrieval is the detection and translation of out-of-vocabulary (OOV) terms; for OOV terms in Chinese, another difficulty is segmentation. At NTCIR-4, we explored methods for translation and disambiguation for OOV terms when using a Chinese query on an English collection. We have developed a new segmentation-free technique for automatic translation of Chinese OOV terms using the web. We have also investigated the effects of distance factor and window size when using a hidden Markov model to provide disambiguation. Our experiments show these methods significantly improve effectiveness; in conjunction with our post-translation query expansion technique, effectiveness approaches that of monolingual retrieval.

Detection and translation of OOV terms prior to query time

Accurate cross-language information retrieval requires that query terms be correctly translated. Several new techniques to improve the translation of out of vocabulary terms in English-Chinese cross-language information retrieval have been developed. However, these require queries and a document collection to enable translation disambiguation. Although effective, they involve much processing and searching of the Web at query time, and may not be practical in a production web search engine. In this work, we consider what tasks maybe carried out beforehand, the goal being to reduce the processing required at query time. We have successfully developed new techniques to extract and translate out of vocabulary terms using the Web and add them into a translation dictionary prior to query time.

Authorship attribution via combination of evidence

Authorship attribution is a process of determining who wrote a particular document. We have found that different systems work well for particular sets of authors but not others. In this paper, we propose three authorship attribution systems, based on different ways of combining existing methodologies. All systems show better effectiveness than the state-of-art methods.

An empirical comparison of translation disambiguation techniques for chinese–english cross-language information retrieval

Disambiguation techniques are typically employed to reduce translation errors introduced during query translation in cross-lingual information retrieval. Previous work has used several techniques — based on term similarity, term co-occurrence, and language modelling. However, the previous experiments were conducted on different data sets, and thus the relative merits of each technique is presently unclear. The goal of this work is to compare the effectiveness of these techniques on the same Chinese–English data sets. Our results show that despite the different underlying models and formulae used, the aggregated results are comparable. However, there is wide variation in the translation of individual queries, suggesting that there is scope for further improvement.

A comparison of morpheme and word based document retrieval for Asian languages

Most document retrieval systems are word based. Words are very convenient retrieval units in English but not so in some Asian languages. The task of determining which morphemes constitute words in Vietnamese and Chinese is problematic, and has been assumed to be the reason that word based retrieval does not work so well. The paper examines a number of segmentation algorithms, and then reports on some experiments comparing morpheme and word based retrieval. It shows that morpheme based retrieval is hard to improve on.

Multi Queries Methods of the Chinese-English Bilingual Plagiarism Detection

Cross-language plagiarism detection identifies and extracts plagiarized text in a multilingual environment. In recent years, there has been a significant amount of work done involving English and European text. However, somewhat less attention has been paid to Asia languages. We compared a number of different strategies for Chinese-English bilingual plagiarism detection. We present methods for candidate document retrieval and compare four methods: (i) document keywords based, (ii) intrinsic plagiarism based, (iii) headers based, and (iv) machine translation queries. The results of our evaluation indicated that keywords based queries, the simplest and most efficient approach, gives acceptable results for newspaper articles. We also compared different percentage of keywords based query, and the results indicated that putting 50% keywords into queries can obtain the satisfied candidate documents set.