Articles

. This paper investigates automatic wrapper generation and maintenance for Forums, Blogs and News web sites. Web pages are increasingly dynamically generated using a common template populated with data from databases. This paper proposes a novel method that uses tree alignment and transfer learning method to generate the wrapper from …...

. The mapping between grammatical functions and thematic roles of resultative constructions has been widely discussed in different frameworks of syntax, and theories have been proposed to account for the mismatches between them. The question behind the construction of these mapping theories always lies in the choice of suppressing one …...

. The distinction between concrete and abstract concepts is psychologically valid but so far it can hardly be quantified in any objective way, which prevents it from being further studied in computational linguistics. This paper proposes a systematic way to measure concreteness from the surface structure of dictionary definitions. Comparing …...

. This paper attempts to provide a refined description with a quantitative analysis about the deontic modals zo3-ded4 (做得) and sii2-ded4 (使得) in Taiwanese Hakka. While the affirmative-negative relationship is symmetrical structurally, it manifests in an asymmetrical manner semantically. The logic notations will be applied to clarify the intriguing interaction …...

. This paper presents a comparison of two designs for implementing argument frame information on verbs. In the first design, alternating verbs will be represented with one lexical entry pr. possible argument frame. In the other design, each verb form will be associated with only one lexical entry containing a …...

. In this paper, we investigate the language model (LM) adaptation issue for Statis- tical Machine Translation (SMT). In order to overcome the weight bias on the LM obtained from the development data, a simple but effective method is proposed to adapt the LM for diverse test datasets by employing …...

. In this paper, we propose a simple and intuitive yet linguistically and practically motivated method for English-Chinese name transliteration generation. Our system is essentially a syllable-based Maximum Matching system. It uses the Onset First Principle to syllabify English names and align them with Chinese names. The bilingual lexicon containing …...

. Cross-Language Information Retrieval (CLIR) system uses dictionaries for information retrieval. However, out of vocabulary (OOV) terms cannot be found in dictionaries. Although many researchers in the past have endeavored to solve the OOV term translation problem, but little attention has been paid to hybrid translations “α1- antitrypsin deficiency (α1-抗胰蛋白酶缺乏症)”. …...

. This paper investigates the effect of quantification in sentence processing. The experimental results show that temporarily ambiguous sentences that begin with the univer- sally quantified NPs reduced the garden path effect in contrast to the ones that begin with bare NPs. This fact is accounted for by assuming that …...

. Surface realizers are used at the final phase of natural language text generation to convert abstract or symbolic representations of information to linguistic forms in a particular human language. Rules of grammar for the target language are applied to produce text that is syntactically, morphologically and orthographically correct. In …...

. Outputs of NLP tools can be regarded as sets of annotations of predefined charac- ters included in a processed document. These annotations are said erroneous if they disagree with the annotations given by the experts. Innovative architectures have been proposed to an- notate and revise annotations by processing errors …...

. We present a methodology for constructing automatically verifiable and human- readable interlinguas, which simultaneously combine expressivity and simplicity. By defining the interlingua using the same formalism as the one used to define the analysis and generation grammars, it is feasible, in a natural way, both (1) to generate a …...

This study examines how different dimensions of corpus frequency data may affect the outcome of statistical modeling of lexical items. The corpus used in our analysis is an elderly speaker corpus in its early development, and the target words are temporal expressions, which might reveal how the speech produced by …...

This paper aims at finding the relationships between intelligibility and comprehensibility in speech synthesizers, and tries to design an appropriate comprehension task for evaluating the speech synthesizers’ comprehensibility. It is predicted that speech synthesizer with higher intelligibility, will have greater performance in comprehension. Also, since the two most popular used …...

This work represents several unsupervised feature selections based on frequent strings that help improve conditional random fields (CRF) model for Chinese word segmentation (CWS). These features include character-based N-gram (CNG), Accessor Variety based string (AVS), and Term Contributed Frequency (TCF) with a specific manner of boundary overlapping. For the experiment, …...

In this paper, we develop a series of algorithms to improve the noise robustness of speech features based on discrete cosine transform (DCT). The DCT-based modulation spectra of clean speech feature streams in the training set are employed to generate two sequences representing the reference magnitudes and magnitude weights, respectively. …...

Consensus is the desired result in many argu- mentative discourses such as negotiations, public debates, and goal-oriented forums. However, due to the fact that usually people are poor arguers, a support of argumentation is necessary. Web-2 provides means for the on- line discussions which have their characteristic features. In our …...

We extract new terminology from a text by term validation in a dictionary. Our ap- proach is based on estimating probabili- ties for previously unseen terms, i.e. not present in a dictionary. To do this we apply several probabilistic models previ- ously not used for term recognition and propose a …...

We propose the creation and use of a mul- tilingual parallel news corpus annotated with opinion towards entities, produced by projecting sentiment annotation from one language to several others. The objective is to save annotation time for development and evaluation purposes, and to guarantee comparability of opinion mining evalua- tion …...

This paper presents a system based on Finite State Technology that recognises and classifies numerical entities in texts written in Basque. The system deals with a wide range of entities, such as temporal expressions, numbers related to units of measurement, or those that refer to common nouns. The system obtains …...