Although Dense Passage Retrieval (DPR) models have achieved significantly enhanced performance, their widespread application is still hindered by the demanding inference efficiency and high deployment costs.Knowledge distillation is an efficient method to compress models, which transfers knowledge from strong teacher models to weak student models.Previous studies have proved the effectiveness of knowledge distillation in DPR.However, there often remains a significant performance gap between the teacher and the distilled student.To narrow this performance gap, we propose MTA4DPR, a Multi-Teaching-Assistants based iterative knowledge distillation method for Dense Passage Retrieval, which transfers knowledge from the teacher to the student with the help of multiple assistants in an iterative manner; with each iteration, the student learns from more performant assistants and more difficult data.The experimental results show that our 66M student model achieves the state-ofthe-art performance among models with same parameters on multiple datasets, and is very competitive when compared with larger, even LLM-based, DPR models.

In this paper, we construct an entity recognition and linking system using Chinese Wikipedia and knowledge base. We utilize refined filter rules in entity recognition module, and then generate candidate entities by search engine and attributes in Wikipedia article pages. In entity linking module, we propose a hybrid entity re-ranking method combined with three features: textual and semantic match-degree, the similarity between candidate entity and entity mention, entity frequency. Finally, we get the linking results by the entity’s final score. In the task of entity recognition and linking in search queries at NLPCC 2015, the Average-F1 value of this method achieved 61.1% in 3849 test dataset, which ranks second place in fourteen teams.

This paper proposes a method to recognize stroke orders of on-line handwritten Chinese characters based on analyzing both spatial and temporal information. A novel control-point-based analysis method is presented for spatial information analysis to match strokes with various shapes and styles. Its computation complexity is much lower than image correlation method and is suitable for applications on mobile devices. For temporal information analysis, Hidden Markov Model is adopted and a proposed rectification method is integrated to find the optimal pair-wise matching result of stroke sequences. Experimental results proved the effectiveness of the proposed method. The verification rate is 99.6% on the test set.

Dictionaries have often been used for query translation in cross-language information retrieval (CLIR). However, we are faced with the problem of translation ambiguity, i.e. multiple translations are stored in a dictionary for a word. In addition, a word-by-word query translation is not precise enough. In this paper, we explore several methods to improve the previous dictionary-based query translation. First, as many as possible, noun phrases are recognized and translated as a whole by using statistical models and phrase translation patterns. Second, the best word translations are selected based on the cohesion of the translation words. Our experimental results on TREC English-Chinese CLIR collection show that these techniques result in significant improvements over the simple dictionary approaches, and achieve even better performance than a high-quality machine translation system.

Writing English is a big barrier for most Chinese users. To build a computer-aided system that helps Chinese users not only on spelling checking and grammar checking but also on writing in the way of native-English is a challenging task. Although machine translation is widely used for this purpose, how to find an efficient way in which human collaborates with computers remains an open issue. In this paper, based on the comprehensive study of Chinese users requirements, we propose an approach to machine aided English writing system, which consists of two components: 1) a statistical approach to word spelling help, and 2) an information retrieval based approach to intelligent recommendation by providing suggestive example sentences. Both components work together in a unified way, and highly improve the productivity of English writing. We also developed a pilot system, namely PENS (Perfect ENglish System). Preliminary experiments show very promising results.

This paper presents a novel statistical model for automatic identification of English baseNP. It uses two steps: the N-best Part-Of-Speech (POS) tagging and baseNP identification given the N-best POS-sequences. Unlike the other approaches where the two steps are separated, we integrate them into a unified statistical framework. Our model also integrates lexical information. Finally, Viterbi algorithm is applied to make global search in the entire sentence, allowing us to obtain linear complexity for the entire process. Compared with other methods using the same testing set, our approach achieves 92.3% in precision and 93.2% in recall. The result is comparable with or better than the previously reported results.