In this paper, we investigate a resampling approach for domain adaptation from a resource-rich domain (patent domain) to a resource-scarce target domain (newspaper domain) in Statistical Machine Translation (SMT). We propose two resampling methods for domain adaptation in SMT: random resampling and resampling for instance weighting. The random resampling randomly adds sentence pairs from the re...

This paper presents two sentence retrieval methods. We adopt the task definition done in the TREC Novelty Track: sentence retrieval consists in the extraction of the relevant sentences for a query from a set of relevant documents for that query. We have compared the performance of the Latent Semantic Indexing (LSI) retrieval model against the performance of a topic identification method, also b...

There are several reasons to expect that recognising word order errors in a text will be a difficult problem, and recognition rates reported in the literature are in fact low. Although grammatical rules constructed by computational linguists improve the performance of a grammar checker in word order diagnosis, the repairing task is still very difficult. This paper describes a method to repair a...

For learning foreign language pronunciation, prosodic features are important as much as, or more than segmental features. For Japanese speakers, one of difficulties to learn English pronunciation is rhythm because of the differences between two languages: mora-timing rhythm and stress-timing rhythm. In order to correct errors in rhythm, the method of evaluating sentence stress that constitutes ...

The quality of a sentence translated by a machine translation (MT) system is difficult to evaluate. We propose a method for automatically evaluating the quality of each translation. In general, when translating a given sentence, one or more conditions should be satisfied to maintain a high translation quality. In EnglishJapanese translation, for example, prepositions and infinitives must be app...

A hedge is a linguistic device used to avoid using a categorical sentence. Hedges can be used to determine whether a sentence is factual by merely regarding a sentence containing hedges as non-factual. In this paper, we perform a comparative experiment of various classification methods for hedge detection. Among four different classification methods, we observe that SVM shows the best performan...

Voice conversion has been used in many applications. The methods based on vector quantization codebook and Gaussian mixture models need dynamic time warping on parallel sentence corpus for generating mapping functions. Recent study tries to use less training data, and even without parallel sentence corpus. This paper presents a voice conversion method without using parallel sentence corpus. It ...

Sentiment classification is a fundamental task in opinion mining. However, most existing systems require a sentiment lexicon to guide sentiment classification, which inevitably suffer from the problem of unknown words. In this paper, we present a morpheme-based fine-to-coarse strategy for Chinese sentence-level sentiment classification. To approach this, we first employ morphological productivi...

This paper describes a Chinese keyboard intelligent fullsentence input method system based on tri-gram language model. In this system, we use efficient algorithms to reduce the size of the language model, accelerate the search and enhance the accuracy. The n-gram model is presented in a novel structure, which shrinks the model and enables it with look-ahead and buffer techniques to reduce the t...

We have developed a sentence extraction system that estimates the significance of sentences by integrating four scoring functions that use as evidence sentence location, sentence length, TF/IDF values of words, and similarity to the title. Similarity to a given query is also added to the system in the summarization task for information retrieval. Parameters for scoring functions were optimized ...