In text generation, various kinds of choices need to be decided. In the conventional framework, which can be called "one-path generation framework," these choices are decided in an order designed carefully in advance. However, many researchers have pointed out that the choices, generally, depend on one another and the one-path generation framework cannot handle these interdependencies sufficien...
In text generation, various kinds of choices need to be decided. In conventional frameworks, which we call one-path generation frameworks , those decisions are made in an order carefully designed in advance. In general, however, since choices depend on one another, it is difficult to make optimal decisions in such frameworks. Our approach to this issue is to introduce the revision process into ...
In this paper, we present a dependency treebased method for sentiment classification of Japanese and English subjective sentences using conditional random fields with hidden variables. Subjective sentences often contain words which reverse the sentiment polarities of other words. Therefore, interactions between words need to be considered in sentiment classification, which is difficult to be ha...
Many natural language processing tasks, including information extraction, question answering and recognizing textual entailment, require analysis of the polarity, focus of polarity, tense, aspect, mood and source of the event mentions in a text in addition to its predicateargument structure analysis. We refer to modality, polarity and other associated information as extended modality. In this p...
Of The Afnlp, Toh Tuck Link, Susumu Akamine, Daisuke Kawahara, Yoshikiyo Kato, Tetsuji Nakagawa, Kentaro Inui
[Refereed]
ii Preface Welcome to the proceedings of the demo session. This volume contains the abstracts of the software demonstrations presented at the combined 47th Annual Meeting of the Association for Computational Linguistics and 4th International Joint Conference on Natural Language Processing, held in Suntec, Singapore, on August 3. The demonstrations program offers the presentation of early resear...
We demonstrate an information credibility analysis system called WISDOM. The purpose of WISDOM is to evaluate the credibility of information available on the Web from multiple viewpoints. WISDOM considers the following to be the source of information credibility: information contents, information senders, and information appearances. We aim at analyzing and organizing these measures on the basi...
In this paper, we discuss how to annotate coreference and predicate-argument relations in Japanese written text. There have been research activities for building Japanese text corpora annotated with coreference and predicate-argument relations as are done in the Kyoto Text Corpus version 4.0 (Kawahara et al., 2002) and the GDA-Tagged Corpus (Hasida, 2005). However, there is still much room for ...
We approach the zero-anaphora resolution problem by decomposing it into intra-sentential and inter-sentential zeroanaphora resolution. For the former problem, syntactic patterns of the appearance of zero-pronouns and their antecedents are useful clues. Taking Japanese as a target language, we empirically demonstrate that incorporating rich syntactic pattern features in a state-of-the-art learni...
This paper describes our ongoing research project on text simplification for congenitally deaf people. Text simplification we are aiming at is the task of offering a deaf reader a syntactic and lexical paraphrase of a given text for assisting her/him to understand what it means.
ecei.tohoku.ac.jp