Articles

Realizing expressive text-to-speech synthesis needs both text processing and the rendering of natural expressive speech. This paper fo- cuses on the former as a front-end task in the production of synthetic speech, and in- vestigates a novel method for predicting em- phasized accent phrases from advertisement text information. For this …...

The aim of this paper is to examine the parallelism between tonal transitions and musical note transitions in Thai pop songs based on the data from 30 current pop songs. The results suggest that there is a statistically significant parallelism between tonal transitions and musical note transitions. Interestingly, the results …...

This paper describes a method of multi- document summarization with evolutionary computation. In automatic document sum- marization, the method to make a summary by finding the best combination of important sentences in target documents is popular ap- proach. To find the best combination of sen- tences, explicit solution techniques such …...

Automatic detection of antonymy is an important task in Natural Language Processing (NLP) for Information Retrieval (IR), Ontology Learning (OL) and many other semantic applications. However, current unsupervised approaches to antonymy detection are still not fully effective because they cannot discriminate antonyms from synonyms. In this paper, we introduce APAnt, …...

In this paper, we discuss news source detec- tion (NSD), which involves finding additional information of a message generated in so- cial media to understand the original message more deeply. We propose an NSD method based on the text segmentation and two exten- sion models using web content and post …...

We present a novel segmentation ap- proach for Phrase-Based Statistical Ma- chine Translation (PB-SMT) to languages where word boundaries are not obviously marked by using both monolingual and bi- lingual information and demonstrate that (1) unsegmented corpus is able to provide the nearly identical result compares to manually segmented corpus …...

The Unicode standard identifies and provides representation of the vast majority of known characters used in today’s writing systems. Many of these characters belong to the unified Han series, which encapsulates characters from writing systems used in languages such as Chinese, Japanese and Korean languages. These pictographic characters are often …...

Spelling recognition is a workaround to recognize unfamiliar words, such as proper names or unregistered words in a dictionary, which typically cause ambiguous pronunciations. In the Thai spelling task, some alphabets cannot be differentiated by only spectral cues. In such cases, tonal cues play a critical role in distinguishing those …...

Internal state predicates or ISPs refer to internal states of sentient beings, such as emotions, sensations and thought processes. Japanese ISPs with zero pronouns exhibit the “person restriction” in that the zero form of their subjects must be first person at the utterance time. This paper examines the person restriction …...

Mathematical word problems (MWP) test crit- ical aspects of reading comprehension in con- junction with generating a solution that agrees with the “story” in the problem. In this paper we design and construct an MWP solver in a systematic manner, as a step towards enabling comprehension in mathematics and teaching …...

This paper reports on a corpus-based quantitative study of the use of nominalizations across China English and British English in two comparable media corpora. In contrast to previous corpus-based studies of nominalizations, we start by using a syntactic approach and proceed with some methodological innovations incorporating large lexical databases and …...

We propose a statistical frame-based approach (FBA) for natural language processing, and demonstrate its advantage over traditional ma- chine learning methods by using topic detec- tion as a case study. FBA perceives and iden- tifies semantic knowledge in a more general manner by collecting important linguistic pat- terns within documents …...

This article presents novel data on partial case- marking in Japanese stripping/sluicing: only the final NP in multiple stripping/sluicing may lack a case particle. These data challenge previous works that assign radically distinct structures to stripping/sluicing depending on whether or not case-marking is involved. These case-marking patterns are reducible to …...

We propose a novel framework for zero-shot learning of topic-dependent language models, which enables the learning of language mod- els corresponding to specific topics for which no language data is available. To realize zero- shot learning, we exploit the semantic compo- sitionality of the target topics. Complex topics are normally …...

This paper follows the lead of Chung (2013), examining the phonological suppression of the wh-expression in English and Korean. We argue that the wh-expression itself cannot undergo ellipsis/deletion/dropping, as it carries information focus. However, it can do so, when in anaphoricity with the preceding token of wh-expression, it changes into …...

The field of distributional-compositional se- mantics has yielded a range of computational models for composing the vector of a phrase from those of constituent word vectors. Ex- isting models have various ranges of their expressiveness, recursivity, and trainability. However, these models have not been exam- ined closely for their compositionality. …...

The pseudo-passive is peculiar in that (i) the DP that appears to be the complement of a preposition undergoes passivization, and (ii) it is semantically characterized by the fact that it describes a resultant state or a characteristic of the Theme. The first peculiarity can be explained if the DP …...

In this paper, I introduce a learning challenge for various models of parameter setting in generative syntax, namely a scenario where all input to the learner underdetermines the target parameter setting. This scenario is exempli- fied by the case of zero-derived causatives in English, as discussed in Pylkkänen (2008). I …...

This paper takes an in-depth look at the relationship between mechanically extracted keywords and ‘Top Ten News of the Year’ compiled by the news editors. A previous study that briefly touched on the topic concludes there does not seem to exist any meaningful connection between the two. In this paper, …...

Text from social media is significant key information to understand social movement. However, the length of the social media text is typically short and concise with a lot of absent words. Our task is to identify the proper keyword representing the message content that we are accounting for. Instead of …...