结合主题依存特征和Bigram的汉语语言建模方法

在 Bigram语言模型建模过程中 ,语言被看作符号集序列 ,没有考虑语言本身具有的语法和语义结构特征 .虽然在线的文本训练数据迅速增长 ,但语言模型的性能却很难再获得大幅度的提高 .基于统计方法语言建模的基本原理 ,提出了一种结合 Bigram和主题依存特征的中文语言建模方法 .初步实验结果表明 ,该方法可有效地补充 Bigram模型提取特征的不足 。

Word sense disambiguation using semantic relatedness measurement

All human languages have words that can mean different things in different contexts, such words with multiple meanings are potentially “ambiguous”. The process of “deciding which of several meanings of a term is intended in a given context” is known as “word sense disambiguation (WSD)”. This paper presents a method of WSD that assigns a target word the sense that is most related to the senses of its neighbor words. We explore the use of measures of relatedness between word senses based on a novel hybrid approach. First, we investigate how to “literally” and “regularly” express a “concept”. We apply set algebra to WordNet’s synsets cooperating with WordNet’s word ontology. In this way we establish regular rules for constructing various representations (lexical notations) of a concept using Boolean operators and word forms in various synset(s) defined in WordNet. Then we establish a formal mechanism for quantifying and estimating the semantic relatedness between concepts—we facilitate “concept distribution statistics” to determine the degree of semantic relatedness between two lexically expressed con- cepts. The experimental results showed good performance on Semcor, a subset of Brown corpus. We observe that measures of semantic relatedness are useful sources of information for WSD.

Construction of unsupervised sentiment classifier on idioms resources

Sentiment analysis is the computational study of how opinions, attitudes, emotions, and perspectives are expressed in language, and has been the important task of natural language processing. Sentiment analysis is highly valuable for both research and practical applications. The focuses were put on the difficulties in the construction of sentiment classifiers which normally need tremendous labeled domain training data, and a novel unsupervised framework was proposed to make use of the Chinese idiom resources to develop a general sentiment classifier. Furthermore, the domain adaption of general sentiment classifier was improved by taking the general classifier as the base of a self-training procedure to get a domain self-training sentiment classifier. To validate the effect of the unsupervised framework, several experiments were carried out on publicly available Chinese online reviews dataset. The experiments show that the proposed framework is effective and achieves encouraging results. Specifically, the general classifier outperforms two baselines(a Na?ve 50% baseline and a cross-domain classifier), and the bootstrapping self-training classifier approximates the upper bound domain-specific classifier with the lowest accuracy of 81.5%, but the performance is more stable and the framework needs no labeled training dataset.

Improved hidden Markov model for speech recognition and POS tagging

In order to overcome defects of the classical hidden Markov model (HMM), Markov family model (MFM), a new statistical model was proposed. Markov family model was applied to speech recognition and natural language processing. The speaker independently continuous speech recognition experiments and the part-of-speech tagging experiments show that Markov family model has higher performance than hidden Markov model. The precision is enhanced from 94.642% to 96.214% in the part-of-speech tagging experiments, and the work rate is reduced by 11.9% in the speech recognition experiments with respect to HMM baseline system.

Alignment of the Polish-English Parallel Text for a Statistical Machine ＂Translation

Text alignment is crucial to the accuracy of MT （Machine Translation） systems, some NLP （Natural Language Processing） tools or any other text processing tasks requiring bilingual data. This research proposes a language independent sentence alignment approach based on Polish （not position-sensitive language） to English experiments. This alignment approach was developed on the TED （Translanguage English Database） talks corpus, but can be used for any text domain or language pair. The proposed approach implements various heuristics for sentence recognition. Some of them value synonyms and semantic text structure analysis as a part of additional information. Minimization of data loss was ensured. The solution is compared to other sentence alignment implementations. Also an improvement in MT system score with text processed with the described tool is shown.

A Modular Incremental Model for English Full Parsing

In this paper, we present a modular incremental statistical model for English full parsing. Unlike other full parsing approaches in which the analysis of the sentence is a uniform process, our model separates the full parsing into shallow parsing and sentence skeleton parsing. In shallow parsing, we finish POS tagging, Base NP identification, prepositional phrase attachment and subordinate clause identification. In skeleton parsing, we use a layered feature-oriented statistical method. Modularity possesses the advantage of solving different problems in parsing with corresponding mechanisms. Feature-oriented rule is able to express the complex lingual phenomena at the key point if needed. Evaluated on Penn Treebank corpus, we obtained 89.2% precision and 89.8% recall.