Articles

This paper proposes a general framework for the semantics of honorific expressions, includ- ing honorific pronouns, morphology, and dis- course particles. Such expressions are claimed to indicate a level of politeness which must be compatible with a level of formality fixed by the discourse context together with sociolin- guistic factors, …...

Most language models used for natural lan- guage processing are continuous. However, the assumption of such kind of models is too simple to cope with data sparsity problem. Al- though many useful smoothing techniques are developed to estimate these unseen sequences, it is still important to make full use of …...

We present a revised discourse theory based on segmented discourse represen- tation theory and provide a method for building a Japanese corpus suitable for causal relation extraction. This extends and refines the framework proposed in Kaneko and Bekki (2014), and we evalu- ate our corpus and compare it with that …...

We introduce a method for learning to align sentences in monolingual parallel articles for text simplification. In our approach, word keyness is integrated to prefer aligning essential words in sentences. The method involves estimating word keyness based on TF*IDF and semantic PageRank, and word nodes’ parts-of-speech and degrees of reference. …...

As enormous amount of electronic documents on the Web have been increasing, the ne- cessity of automatic summarization has also been increasing to help people grasp the essen- tial points of the documents. Many summa- rization techniques dealing with single doc- ument and multi-documents have been stud- ied. However, due …...

. According to Frame Semantics (Fillmore 1976), words’ meaning are best understood considering the semantic frame they play a role in, for the frame is what gives them context. FrameNet defines about 1000 such semantic frames, along with the roles arguments can fill in this frame. Our task is to …...

Adjacency pair recognition, a necessary com- ponent of discussion thread reconstruction, is the task of recognizing reply-to relations be- tween pairs of discussion turns. Previously, dialogue act classification and metadata-based features have been shown useful in adjacency pair recognition. However, for certain forums such as Wikipedia discussions, metadata is not …...

Lexical Cohesion is a commonly studied lin- guistic feature as it is easily identified from the surface of a text. However, the purposes for studying lexical cohesion are varied, and each purpose requires different methods. This study analyzes two short movie review texts for four different research purposes using lex- …...

. Keyphrases are single or multi-word expressions that represent the main content of a document. Key- phrases are useful in many applications such as document indexing or text summarization. However, most documents are not provided with keyphrases. To tackle this problem, researchers propose methods to automatically extract keyphrases from documents …...

. In this article, we propose a study on the words or multi-words which are good indicators of the opinion polarity of a text but have different polarity depending on the domain. We have performed experiments on French and English corpora, which show that taking these multi-polarity words into account …...

The paper tries to contribute to the general definition of discourse connectives. It examines connectives in broader sense, i.e. all language expressions that have an ability to express discourse relations within a text (e.g. both conjunctions like but, and, or and expressions like the condition for this is, due to …...

The purpose of this study is to investigate the influence of given-new ordering on word order change and topic marker WA, using a self-paced reading task. The results demonstrated that OACCSNOMV is sensitive to given-new information, but SNOMOACCV, STOPOACCV, and OTOPSNOMV are not. This fact can be explained by the …...

The Japanese discourse particles (sentence- final particles) ne and yone both have the functions that can be roughly characterized as the ⟨shared information⟩ use and the ⟨call for confirmation⟩ use. In the literature, an ad- equate descriptive analysis has not been ob- tained as to how the choice between the …...

By adopting recent advances in music creation technologies, such as digital audio worksta- tions and singing voice synthesizers, people can now create songs in their personal com- puters. Computers can also assist in creat- ing lyrics or generating them automatically, although this aspect has been less thoroughly researched and is …...

Spoken and written languages evolve constantly through their everyday usages. Combining with practical expectation for automatically generating synthetic speech suitable for various domains of context, such a reason makes Text-to-Speech (TTS) systems of living languages require characteristics that allow extensible handlers for new language phenomena or customized to the nature …...

Sarcasm is a form of communication that is intended to mock or harass someone by us- ing words with the opposite of their literal meaning. However, identification of sarcasm is somewhat difficult due to the gap between its literal and intended meaning. Recognition of sarcasm is a task that can …...

The primary goal of the present study is to de- scribe the basic prosodic differences between declaratives and polar questions in Fataluku, an underdocumented Papuan language spoken in the island nation of East Timor. Two robust prosodic differences between statements and questions are observed, namely, the duration of the final …...

In teaching and learning of English as a foreign language, the Internet serves as a source of authentic listening material, enabling learners to practice English in real contexts. An adaptive computer-assisted language learning and teaching system can pick up news clips as authentic materials from the Internet according to learner …...

Short utterances serve a multitude of different communicative functions in interactive speech and have attracted due attention in recent re- search in dialogue acts. This paper presents a quantitative description of three short utteranc- es i.e. that’s right, that’s true, that’s correct and their variations based on the Switchboard Dialogue …...

This study compares two constructions in Cantonese which shares similar features in their syntax and semantics. Previous works observe that comparatives often appear after experiential aspect in the verbal domain his- torically. This study builds upon this obser- vation and argues that the similarities between two constructions, comparatives and experien- …...