In this paper, a new approach is presented for organizing pedagogical texts for researchers, based on a kernel projection from a hybrid text-researcher space onto the researcher’s ability space, where the text-researcher space includes text’s features as well as the researcher’s reasoning styles and intention in doing research. The approach has been applied to organizing pedagogical texts for t...

The growing availability of large on-line corpora encourages the study of word behaviour directly from accessible raw texts. However the methods by which lexical knowledge should be extracted from plain texts are still matter of debate and experimentation. In this paper it is presented an integrated tool for lexical acquisition from corpora, ARIOSTO, based on a hybrid methodology that combines ...

Although substantial efforts have been made to parse Chinese, very few have been practically used due to incapability of handling unrestricted texts. This paper realizes a practical system for Chinese parsing by using a hybrid model of phrase structure partial parsing and dependency parsing. This system showed good performance and high robustness in parsing unrestricted texts and has been appli...

Aligning texts and their multi-document summaries is the task of determining the correspondences among textual segments in the texts and in their corresponding summaries. The study of alignments allows a better understanding of the multi-document summarization process, which may subsidize new summarization models for producing more informative summaries. In this paper, we investigate some appro...

In this demonstration, we present a multi-source hybrid Question Answering (QA) system. Our system consists of four sub-systems. 1) a knowledge base based QA, 2) an information retrieval based QA, 3) a keyword QA and 4) an information-extraction to construct our own knowledge base from web texts. With these sub-systems, we can query three types of information sources: curated knowledge bases, a...

Although substantial efforts have been made to parse Chinese, very few have been practically used due to incapability of handling unrestricted texts. This paper realizes a practical system for Chinese parsing by using a hybrid model of phrase structure partial parsing and dependency parsing. This system showed good performance and high robustness in parsing unrestricted texts and has been appli...

We describe in this paper a hybrid approach to build automatically bilingual lexicons of Multiword Expressions (MWEs) from parallel corpora. We more specifically investigate the impact of using a domain-specific bilingual lexicon of MWEs on domain adaptation of an Example-Based Machine Translation (EBMT) system. We conducted experiments on the English-French language pair and two kinds of texts...

This paper presents a novel hybrid generative/discriminative model of word segmentation based on nonparametric Bayesian methods. Unlike ordinary discriminative word segmentation which relies only on labeled data, our semi-supervised model also leverages a huge amounts of unlabeled text to automatically learn new “words”, and further constrains them by using a labeled data to segment non-standar...