Articles

In recent years, machine learning methods beyond the confines of conventional super- vised learning have been used along with deep learning methods and intensively investigated. Fine-tuning, which improves the performance of one task by re-learning using the weights of a model learned for another task as ini- tial values, is …...

Automatic text highlighting aims to identify key portions that are most important to a reader. In this paper, we explore the use of ex- isting extractive summarization models for au- tomatically generating highlights; automatic highlight generation has not previously been addressed from this perspective. Evaluation studies typically rely on automated …...

Although depression is one of the most com- mon mental disorders, the depressed individ- uals may not be aware of their symptoms at all so that they sometimes miss the appropri- ate time for treatment. In order to prevent this problem, many researchers looked into so- cial media to figure …...

Expectation is known to have an impact on behavioral choices of human beings by intensifying the perception of something or distracting their attention away. However, little is known about how unexpected situations affect information processing. This study investigated the processing of possibility hedges. Specifically, it tested whether participants ignored possibility …...

This paper argues that external arguments are introduced as thematically underspecified and their thematic interpretation is determined at the C-I interface based on their context of occurrence. Specifically, this paper first argues for the underspecified nature of external arguments by showing the facts concerning the distribution of interpretationally variable arguments, …...

We propose a new method for domain adapta- tion by using a combination of multiple em- beddings for sentiment analysis. We first make the following embeddings for the doc- ument: (1) vector construction by using the bag-of-words model, (2) vector by dimen- sion reduction using SVD, and (3) embedded vector …...

This paper proposes introducing domain adap- tation into Japanese predicate-argument struc- ture (PAS) analysis. Our investigation of a Japanese balanced-corpus revealed that the distribution of argument types is different across text media, particularly the difference is significant when the argument is exophoric. The past Japanese PAS analysis research has disregarded …...

This paper proposes a novel attention mecha- nism, customized attention mechanism, for rela- tion classification. Based on the task require- ments, logical constraints of the attention mech- anism have been designed to control the learning process of network, which enhances the control- lability in learning. Specifically, a logical con- straint …...

Given the typological differences between Chinese and English, the question arises whether and how topic-prominent (TP) features affect the English development of L1-Chinese learners. The present study explores this question by examining the non-target-like structures surfacing in learners’ interlanguage. 200 essays were randomly selected from the Spoken and Written English …...

Semantic Role Labeling (SRL) has been ex- tensively studied, mostly for understanding English formal language. However, only a few reports exist for informal conversational text, especially for language being used in the chat- bot system. The challenges of informal texting language include a wide variety of slangs and abbreviations, short …...

This study utilized the concept of type per sentence (TPS) with regards to dependency types to identify differences among genres of English texts obtained from an English language corpus. This study also attempted to suggest that TPSs can indicate some of the differences between different genres of texts. TPSs can …...

This paper presents the first automatic sys- tem for Vietnamese spoonerism detection. By incorporating hand-crafted rules with Viet- namese language model, our system, although simple, achieves a promising result for this task. The proposed method achieves an over- all F1 score of 95.47% on the Vietnamese spoonerism dataset. 1...

This paper presents an interactive writing pro- totype system, SmartWrite, which provides Chinese word usage in the form of grammar patterns, collocations, and examples to assist language learners in writing. We propose a method of inducing common Chinese gram- mar patterns from a large-scale Chinese cor- pus. First, we try …...

In this paper we proposed the use of effective features and transfer leaning to improve the accuracies of neural-network-based models for accurate semantic role labeling (SRL) of Japanese, which is an aggregated language. We first reveal that the final morphemes in each argument, which have not been dis- cussed in …...

Estimating the intensity of emotion has gained significance as modern textual inputs in po- tential applications like social media, retail markets, psychology, advertisementse- etc., carry a lot of emotions, feelings, expres- sions along with its meaning. However, the approaches of traditional sentiment analysis primarily focuses on classifying the sentiment in …...

The scarcity of large corpora in reading dis- ambiguated words is a major limitation in lin- guistic analysis and the initiation of a statisti- cal approach to word reading disambiguation. As readings of words are usually not written in documents like meanings of words, there- fore, human annotation is necessary …...

Named Entity Recognition (NER) is a chal- lenging sequence labeling task which requires a deep understanding of the orthographic and distributional representation of words. In this paper, we propose a novel neural architec- ture that benefits from word and character level information and dependencies across ad- jacent labels. This model …...

We have developed a method for extracting the coherence features from a paragraph by matching similar words in its sentences. We conducted an experiment with a parallel Ger- man corpus containing 2000 human-created and 2000 machine-translated paragraphs. The result showed that our method achieved the best performance (accuracy = 72.3%, …...

Previous approaches to training syntax- based sentiment classification models required phrase-level annotated corpora, which are not readily available in many languages other than English. Thus, we propose the use of tree- structured Long Short-Term Memory with an attention mechanism that pays attention to each subtree of a parse tree. Experimental …...

Extracting clean textual content from the Web is the first and an essential step to resolve most of down-stream natural language processing tasks. Previous works in web content extrac- tion focus mainly on web pages with a single main block of textual content, such as news ar- ticles and blog …...