Recent work on joint word segmentation, POS (Part Of Speech) tagging, and dependency parsing in Chinese has two key problems: the first is that word segmentation based on character and dependency parsing based on word were not combined well in the transition-based framework, and the second is that the joint model suffers from the insufficiency of annotated corpus. In order to resolve the first problem, we propose to transform the traditional word-based dependency tree into character-based dependency tree by using the internal structure of words and then propose a novel character-level joint model for the three tasks. In order to resolve the second problem, we propose a novel semi-supervised joint model for exploiting n-gram feature and dependency subtree feature from partially-annotated corpus. Experimental results on the Chinese Treebank show that our joint model achieved 98.31%, 94.84% and 81.71% for Chinese word segmentation, POS tagging, and dependency parsing, respectively. Our model outperforms the pipeline model of the three tasks by 0.92%, 1.77% and 3.95%, respectively. Particularly, the F1 value of word segmentation and POS tagging achieved the best result compared with those reported until now.

为了缓解双语语料不足导致的翻译知识欠缺问题,提出基于复述技术的翻译框架.此框架利用第三种语言获取带有概率的复述知识表,以Lattice表示输入句子的多种复述形式,扩展解码器使之可以对Lattice形式的输入进行解码,将复述知识作为特征加入到对数线性模型的目标函数中.在保持原始翻译知识表不变的情况下,此框架不仅可以增大短语翻译表对源语言现象的覆盖率,也能够增加候选译文表现形式的多样性.在3个不同规模训练集上的对比实验结果表明,在训练语料规模最小的情况下(10 K句对),系统性能有明显提升(BLEU+l.4％);在训练语料规模最大的情况下(1M句对),系统性能也取得一定提升(BLEU+0.32％).

In developing a domain-specific Chinese-English machine translation system,the accuracy of Chinese word segmentation in large-scale training corpus often decreases because of unknown words.The lack of domain-specific annotated corpus makes supervised learning approaches unable to adapt.This problem results in many errors in translation knowledge extraction and therefore seriously affects translation quality.To resolve the domain adaptation problem,we implemented Chinese word segmentation by exploiting n-gram statistical features in raw corpus and bilingually motivated word segmentation information in parallel corpus,respectively.We further propose a latticebased method to combine multiple results and use dynamic programming algorithm to get the best word segmentation result.For evaluation,we conducted experiments of Chinese word segmentation and Chinese-English machine translation using the data of NTCIR-10Chinese-English patent task.The experimental results show that the proposed method brought about improvements both in F-measure of the Chinese word segmentation and in BLEU score of the Chinese-English statistical machine translation system.

In the process of developing a domain-specific Chinese-English machine translation system, the accuracy of Chinese word segmentation on large amounts of training text often decreases because of unknown words. The lack of domain-specific annotated corpus makes supervised learning approaches unable to adapt to a target domain. This problem results in many errors in translation knowledge extraction and therefore seriously lowers translation quality. To solve the domain adaptation problem, we implement Chinese word segmentation by exploring n-gram statistical features in large Chinese raw corpus and bilingually motivated Chinese word segmentation, respectively. Moreover, we propose a method of combining multiple Chinese word segmentation results based on linear model to augment domain adaptation. For evaluation, we conduct experiments of Chinese word segmentation and Chinese-English machine translation using the data of NTCIR-10 Chinese-English patent task. The experimental results showed that the proposed method achieves improvements in both F-measure of the Chinese word segmentation and BLEU score of the Chinese-English statistical machine translation system.

A key problem in Chinese Word Segmentation is that the performance of a system will decrease when applied to a different domain. We propose an approach in which n-gram features from large raw corpus are explored to realize domain adaptation for Chinese Word Segmentation. The n-gram features include n-gram frequency feature and AV feature. We used the CRF model and a raw corpus consisting of 1 million patent description sentences to verify the proposed method. For test data, 300 patent description sentences are randomly selected and manually annotated. The results show that the improvement of Chinese Word Segmentation on the test data achieved at 2.53%.