共查询到18条相似文献,搜索用时 531 毫秒
1.
2.
扩展HMM模型可以解决词语对齐结果与句法约束冲突,从而更好地进行词语对齐。在短语对齐基础上利
用目标语言的短语结构树抽取翻译规则。采用扩展CYK算法CYKA+作为系统的解码器,该算法可以处理非乔姆
斯基范式的翻译规则;采用两轮解码算法在解码过程中整合语言模型。实验表明,与传统词语对齐模型相比,改进的
HMM词语对齐模型具有更高的对齐准确率,并且翻译结果的BLEU评测得分更高。采用翻译规则的系统在不同数
据集上具有更稳定的翻译结果。两轮解码算法与立方剪枝算法具有相近的解码质量,但前者解码速度更快。 相似文献
3.
基于WordNet词义消歧的系统融合 总被引:3,自引:3,他引:0
最近混淆网络在融合多个机器翻译结果中展示很好的性能. 然而为了克服在不同的翻译系统中不同的词序, 假设对齐在混淆网络的构建上仍然是一个重要的问题. 但以往的对齐方法都没有考虑到语义信息. 本文为了更好地改进系统融合的性能, 提出了用词义消歧(Word sense disambiguation, WSD)来指导混淆网络中的对齐. 同时骨架翻译的选择也是通过计算句子间的相似度来获得的, 句子的相似性计算使用了二分图的最大匹配算法. 为了使得基于WordNet词义消歧方法融入到系统中, 本文将翻译错误率(Translation error rate, TER)算法进行了改进, 实验结果显示本方法的性能好于经典的TER算法的性能. 相似文献
4.
针对目前混淆网络生成算法速度与精度不能兼顾的不足,提出一种新的汉语音节混淆网络生成的方法.本算法采用类似轴对齐算法,对音节网格每次提取一条局部路径与参考路径对齐,根据每次对齐路径与参考路径长度不同,采用不同的策略生成混淆网络,并在生成混淆网络之后对其应用一种新的解码框架进行重打分.实验表明,该算法生成的混淆网络精度较高,时间复杂度优于轴对齐算法,且重打分后的识别率有显著提高. 相似文献
5.
6.
7.
8.
基于高斯混合模型的遥感影像连续型朴素贝叶斯网络分类器 总被引:1,自引:0,他引:1
提出了一种新的嵌入高斯混合模型(GMM,Gaussian Mixture Model)遥感影像朴素贝叶斯网络模型GMM-NBC(GMMbased Na ve Bayesian Classifier)。针对连续型朴素贝叶斯网络分类器中假设地物服从单一高斯分布的缺点,该方法将地物在特征空间的分布用高斯混合模型来模拟,用改进EM算法自动获取高斯混合模型的参数;高斯混合模型整体作为一个子节点嵌入朴素贝叶斯网络中,将其输出作为节点(特征)的中间类后验概率,在朴素贝叶斯网络的框架下进行融合获得最终的类后验概率。对多光谱和高光谱数据的分类实验结果表明,该方法较传统贝叶斯分类器分类效果要好,且有较强的鲁棒性。 相似文献
9.
基于分层语块分析的统计翻译研究 总被引:1,自引:0,他引:1
本文描述了一个基于分层语块分析的统计翻译模型。该模型在形式上不仅符合同步上下文无关文法,而且融合了基于条件随机场的英文语块分析知识,因此基于分层语块分析的统计翻译模型做到了将句法翻译模型和短语翻译模型有效地结合。该系统的解码算法改进了线图分析的CKY算法,融入了线性的N-gram语言模型。目前,本文主要针对中文-英文的口语翻译进行了一系列实验,并以国际口语评测IWSLT(International Workshop on Spoken Language Translation)为标准,在2005年的评测测试集上,BLEU和NIST得分均比统计短语翻译系统有所提高。 相似文献
10.
在普通话大词汇量连续语音识别中,使用最大后验概率决策规则解码得到的是具有最小句子错误率的识别结果,但是本文通常使用字错误率作为识别结果的评测标准.为了使识别结果具有最小字错误率,在充分考虑汉语语言特点的基础上,提出了一种汉字混淆网络算法.这种算法能够有效地将普通话大词汇量连续语音识别系统输出的词格转换成为汉字混淆网络.详细讨论了最小贝叶斯风险决策规则理论及使用汉字混淆网络进行的解码过程.基于2005 HTRDP(863)评测数据集进行的实验结果表明,这种使用汉语字混淆网络的方法有效地降低了普通话大词汇量连续语音识别结果的字错误率. 相似文献
11.
In this paper we describe a method that can be used for Minimum Bayes Risk (MBR) decoding for speech recognition. Our algorithm can take as input either a single lattice, or multiple lattices for system combination. It has similar functionality to the widely used Consensus method, but has a clearer theoretical basis and appears to give better results both for MBR decoding and system combination. Many different approximations have been described to solve the MBR decoding problem, which is very difficult from an optimization point of view. Our proposed method solves the problem through a novel forward–backward recursion on the lattice, not requiring time markings. We prove that our algorithm iteratively improves a bound on the Bayes risk. 相似文献
12.
机器翻译系统融合技术综述 总被引:4,自引:1,他引:3
该文对机器翻译研究中的系统融合方法进行了全面综述和分析。根据在多系统输出结果的基础上进行融合的层次差异,我们将系统融合方法分为三类 句子级系统融合、短语级系统融合和词汇级系统融合。然后,针对这三种融合方法,该文分别介绍了它们各自具有代表性的研究工作,包括实现方法、置信度估计和解码算法等,并着重阐述了近年来使用广泛的词汇级系统融合方法中用于构造混淆网络的词对齐技术。最后,该文对这三类系统融合方法进行了比较、总结和展望。 相似文献
13.
《IEEE transactions on audio, speech, and language processing》2008,16(7):1222-1237
14.
15.
16.
Information fusion is a powerful approach to increasing the accuracy of biometric authentication systems, and is currently an active area of research. The majority of studies focus on combining the results from multiple verification systems at the match score level using either a classification or combination scheme. However, there are advantages to performing the fusion at an earlier stage of processing. Fingerprint registration involves finding the translation and rotation parameters that align two fingerprints; a challenging problem that can be approached in a number of ways. The fusion of fingerprint alignment algorithms is introduced in the form of dynamic registration selection. A Bayesian statistical framework is used to select the most probable alignment produced by competing algorithms. The results of the proposed technique are tested on multiple FVC 2002 databases, and are shown to outperform methods based on match score combination. 相似文献
17.
18.
Machine translation is traditionally formulated as the transduction of strings of words from the source to the target language. As a result, additional lexical processing steps such as morphological analysis, transliteration, and tokenization are required to process the internal structure of words to help cope with data-sparsity issues that occur when simply dividing words according to white spaces. In this paper, we take a different approach: not dividing lexical processing and translation into two steps, but simply viewing translation as a single transduction between character strings in the source and target languages. In particular, we demonstrate that the key to achieving accuracies on a par with word-based translation in the character-based framework is the use of a many-to-many alignment strategy that can accurately capture correspondences between arbitrary substrings. We build on the alignment method proposed in Neubig et al. (Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics. Portland, Oregon, pp. 632–641, 2011), improving its efficiency and accuracy with a focus on character-based translation. Using a many-to-many aligner imbued with these improvements, we demonstrate that the traditional framework of phrase-based machine translation sees large gains in accuracy over character-based translation with more naive alignment methods, and achieves comparable results to word-based translation for two distant language pairs. 相似文献