Articles

This paper describes a statistical approach for modeling Chinese-to-English back-transliteration. Unlike previous approaches, the model does not involve the use of either a pronunciation dictionary for converting source words into phonetic symbols or manually assigned phonetic similarity scores between source and target words. The parameters of the proposed model are …...

In this paper, vector-distance-weighted algorithm and representative-vector-distance algorithm are described and used to implement the process of automatic text classification. Two experiments have been done by means of the algorithms (experiment) is based on vector-distance-weighted algorithm and experiment2 is based on representative-vector-distance algorithm). Characters are selected as features. The average …...

The Semantic Knowledge-base of Contemporary Chinese (SKCC) is a large scale Chinese semantic resource developed by the Institute of Computational Linguistics of Peking University. It provides a large amount of semantic information such as semantic hierarchy and collocation features for 66,539 Chinese words and their English counterparts. Its POS and …...

: The history and development of Uyghur language is introduced. After a brief...

We propose and study a new variant of the SVM — the SVM with uneven margins, tailored for document categorisation problems (i.e. problems where classes are highly unbalanced). Our experiments showed that the new algorithm significantly outper- formed the SVM with respect to the document categorisation for small categories. Furthermore, …...

The main aim of this paper is to provide a new analysis of licensers of negative polarity items (NPIs). The problems with Fauconnier-Ladusaw's downward entailment analysis have been argued since Linebarger (1980). I will show that there exists a class of weak NPI licensers characterized by non-monotonicity and exclusivity. Weak …...

The problem of verb-noun categorial ambiguity is critical and relatively unique for non-inflectional languages, especially Chinese. We consider the verb-noun categorial fluidity a continuum and any categorial shift a transitional process. A synchronous corpus-based study was conducted to compare the phenomenon with respect to news texts collected from Hong Kong, …...

Topic segmentation, which aims to fmd the boundaries between topic blocks in a text, is an important task for semantic analysis of texts. Although different solutions have been proposed for the task, many limitations and difficulties exist in the approaches. In particular most of the methods do not work well …...

Part-of-speech tagging for a large corpus is a labour intensive and time-consuming task. In order to achieve fast and high quality tagging, algorithms should be high precision and in particular, its tagging results should require less manual proofreading. In this paper, we proposed a context-rule model to achieve both the …...

Chinese is written without word delimiters so word segmentation is generally considered a key step in processing Chinese texts. This paper presents a new statistical approach to segment Chinese sequences into words based on contextual entropy on both sides of a bigram. It is used to capture the dependency with …...

This paper proposes a new scope calculation system named a phase-based approach. The new system treats scope calculation as a feature-matching operation between more than one interpretable feature related to quantification (henceforth Fqunt1). We call this matching operation Fq.nrmatching. It is shown that the working space of Fquanrmatching is restricted …...

To what degree do different languages share similar conceptual metaphors? Charteris-Black and Ennis (2001) examined this question by running a comparative, corpus-based study of metaphors in Spanish and English financial reporting. They argue that both languages show considerable similarity in the choice of conceptual metaphors with the same linguistic expressions …...

This paper attempts to explore the semantics of onomatopoeic speech act verbs. Language abounds with small bits of utterances to show speaker's emotions, to maintain the flow of speech and to do some daily exchange routines. These tiny vocalizations have been regarded as vocal gestures and largely studied under the …...

We report on a preliminary investigation of the difficulty of converting a grammar of one lan- guage into a grammar of a typologically similar language. In this investigation, we started with the ParGram grammar of Japanese and used that as the basis for a grammar of Korean. The re- sults …...

This paper presents the model that can be used to filter the texts which the user is interested in from a large scale of source texts in Chinese or in English. Each text which the user is interested in can be represented as a vector in the vector space of …...

This paper presents an integrated approach for Chinese word segmentation, which can perform disambiguation and unknown word identification simultaneously on the input. In this work, a hybrid model is used to score known word candidates and unknown word candidates equally by incorporating the modified word-formation models (viz. word-juncture models and …...

Latent Semantic Indexing (LSI) approach provides a promising solution to overcome the language barrier between queries and documents, but unfortunately the high dimensions of the training matrix is computationally prohibitive for its key step of Singular Value Decomposition (SVD). Based on the semantic parallelism of the multi-linguistic training corpus we …...

We present a method for the automatic learning of stemming rules for the Indonesian language. The learning process uses an unlabelled corpus. In the first phase the candidate (word, stem) pairs are automatically extracted from a set of online documents. This phase uses a dictionary but is nevertheless not trivial …...

This paper studies the derivation of multiple nominative constructions (MNC) in Japanese. First, discussing the MNC-sentences in which there is a relation of inalienable possession between nominative noun phrases, I will argue that the set of local economy principles that choose among potentially possible steps at a single stage of …...

The contemporary Japanese verbal honorific constructions can be motivated in view of the RRG clausal organization and its operator hierarchy. I will present an analysis of the subject honorific construction based on a functional analysis of existential and copulative verbs, and relate it to adjectival verbs. I will also sketch …...