Goto

Collaborating Authors

Learning Inter-Related Statistical Query Translation Models for English-Chinese Bi-Directional CLIR

AAAI Conferences

To support more precise query translation for English-Chinese Bi-Directional Cross-Language Information Retrieval (CLIR), we have developed a novel framework by integrating a semantic network to characterize the correlations between multiple inter-related text terms of interest and learn their inter-related statistical query translation models. First, a semantic network is automatically generated from large-scale English-Chinese bilingual parallel corpora to characterize the correlations between a large number of text terms of interest. Second, the semantic network is exploited to learn the statistical query translation models for such text terms of interest. Finally, these inter-related query translation models are used to translate the queries more precisely and achieve more effective CLIR. Our experiments on a large number of official public data have obtained very positive results.


Radiology, News, Education, Service

#artificialintelligence

The vast number of CT presentations at RSNA 2019 is a testament to the modality's resilience and its value to the medical imaging community. Of the numerous factors that have contributed to CT's long-standing relevance, its adaptability certainly ranks high among them. This year's RSNA meeting looks to serve as a reminder of just how adaptable CT continues to be: Presentations will reaffirm the utility of tried-and-true imaging techniques and also feature relatively new technologies that have already begun reshaping the approach radiologists take to common clinical applications. Perhaps one of the best examples of this theme lies in the diagnostic evaluation of heart disease. Researchers will discuss the benefits of traditional coronary CT angiography (CCTA), one of the most reliable noninvasive methods for examining patients suspected of having coronary artery disease.


Word Sense Disambiguation for All Words Without Hard Labor

AAAI Conferences

While the most accurate word sense disambiguation systems are built using supervised learning from sense-tagged data, scaling them up to all words of a language has proved elusive, since preparing a sense-tagged corpus for all words of a language is time-consuming and human labor intensive. In this paper, we propose and implement a completely automatic approach to scale up word sense disambiguation to all words of English.  Our approach relies on English-Chinese parallel corpora, English-Chinese bilingual dictionaries, and automatic methods of finding synonyms of Chinese words. No additional human sense annotations or word translations are needed. We conducted a large-scale empirical evaluation on more than 29,000 noun tokens in English texts annotated in OntoNotes 2.0, based on its coarse-grained sense inventory.  The evaluation results show that our approach is able to achieve high accuracy, outperforming the first-sense baseline and coming close to a prior reported approach that requires manual human efforts to provide Chinese translations of English senses.


Oracle-free Detection of Translation Issue for Neural Machine Translation

arXiv.org Artificial Intelligence

Neural Machine Translation (NMT) has been widely adopted over recent years due to its advantages on various translation tasks. However, NMT systems can be error-prone due to the intractability of natural languages and the design of neural networks, bringing issues to their translations. These issues could potentially lead to information loss, wrong semantics, and low readability in translations, compromising the usefulness of NMT and leading to potential non-trivial consequences. Although there are existing approaches, such as using the BLEU score, on quality assessment and issue detection for NMT, such approaches face two serious limitations. First, such solutions require oracle translations, i.e., reference translations, which are often unavailable, e.g., in production environments. Second, such approaches cannot pinpoint the issue types and locations within translations. To address such limitations, we propose a new approach aiming to precisely detect issues in translations without requiring oracle translations. Our approach focuses on two most prominent issues in NMT translations by including two detection algorithms. Our experimental results show that our new approach could achieve high effectiveness on real-world datasets. Our successful experience on deploying the proposed algorithms in both the development and production environments of WeChat, a messenger app with over one billion of monthly active users, helps eliminate numerous defects of our NMT model, monitor the effectiveness on real-world translation tasks, and collect in-house test cases, producing high industry impact.


AI Research in the People's Republic of China: A Review

AI Magazine

Editor's note: The AI Magazine is initiating a series of articles Since the 1970's AI research has become very active in China and certain results have been achieved. After that, many university departments awarding majors in computer science were organized. They tried to expand the applications of the computer and to develop theories. Considerable efforts were made for this purpose, but these brought few notable results, as a practical process is too complex to identify. However a veteran worker or a technician often manages somewhat better than a computer in process control.