Articles

Since the inception of Generative Adver- sarial Networks (GANs), synthetic im- age generation has taken a giant leap because of the ability of these networks to generate high-quality images, however, the same cannot be said for text genera- tion. A major challenge encountered in text generation using GAN’s is the …...

This paper is an exploration of three types of dependency distances of the sentences in a multilingual parallel corpus, in order to verify the expectation that we can obtain an objective, quantitative measure to indicate cross-linguistic variation of the syntactic- structural setting of human languages. The results indicated that pair-wise …...

This study intends to explore a Chinese synonym pair “liaojie” and “zhidao” via the Chinese GigaWord Corpus. Detailed analysis of the pair is conducted to reveal their different semantic and syntactic features. In particular, the author analyzed the event structure module and role module of the two words based on …...

This paper investigates prosodic pauses in bă, gěi, and ràng constructions in Taiwan Mandarin and adopts a corpus-based approach by collecting spoken data from an online corpus, NCCU Corpus of Spoken Taiwan Mandarin. The results show that prosodic pauses are not preferred before and after the bă, gěi, and ràng …...

This paper examines the distribution of the semantic classes of dative verbs in syntactic constructions, focusing on data from English and Cantonese. While both languages have two dative constructions, the prepositional dative construction (PDC) and the double object construction (DOC), they differ as to the extent they extend these constructions …...

In the field of factoid question answering (QA), it is known that the state-of-the-art tech- nology has achieved an accuracy comparable to human. However, in the area of non-factoid QA, there are only limited numbers of datasets for training QA models. So within the field of the non-factoid QA, Chen …...

Frequent usage of complex expressions with numbers and of the terms that require domain knowledge makes it more difficult to com- prehend and summarize financial news arti- cles than that of other daily news articles. We present a transformer-based model for the au- tomatic summarization of the financial news articles …...

This study applied sentiment analysis to the corpus data and analyzes the men’s and women’s speech. For the analysis, the BNC64 corpus was used and three different types of analyses were employed: dictionary- based analysis, GRU-based analysis, and BERT-based analysis. When the data were analyzed with the dictionary-based analysis, there …...

This research aims to explore an optimal model for automatic word sense disambiguation for highly polysemous markers BUN, TUNG and LAU in Taiwan Hakka, a low-resource language. The performance of word sense disambiguation tasks is carried out by examining DNN, BiLSTM and CNN models under different window spans. The results …...

BERT, which has been successfully applied to many types of natural language process- ing (NLP) tasks, is also effective with vari- ous information retrieval (IR) tasks. However, it is not easy to obtain appropriate data for fine-tuning a BERT model. This paper pro- poses a method that can improve IR …...

This article presents an antonym database con- struction based on the Word List by Seman- tic Principles. Antonym word pair candidates were extracted, after which we performed a cognitive experiment to rate the antonyms ac- cording to crowdsourcing. We then annotated the types of antonyms. The statistics based on the …...

Multi-party dialogue machine reading compre- hension (MRC) raises an even more challeng- ing understanding goal on dialogue with more than two involved speakers, compared with the traditional plain passage style MRC. To accu- rately perform the question-answering (QA) task according to such multi-party dialogue, models have to handle fundamentally differ- …...

The use of hedges plays an important role in daily language use. Based on the spoken texts of British National Corpus (BNC), the study attempts to explore the similarities and differences of hedges employed by the British males and females in their talks. A comparison was made in the frequency …...

In English and Japanese, verbs like smear and load can appear in two alternate variants while expressing nearly the same meaning. It has been argued that there is a semantic difference be- tween locatum-as-object variant and location-as- object variant: location-as-object variant im- poses holistic interpretation, but locatum-as-ob- ject variant allows …...

We release our synthetic parallel paraphrase corpus across 17 languages: Arabic, Catalan, Czech, German, English, Spanish, Estonian, French, Hindi, Indonesian, Italian, Dutch, Ro- manian, Russian, Swedish, Vietnamese, and Chinese. Our method relies only on mono- lingual data and a neural machine translation system to generate paraphrases, hence simple to apply. …...

Significant progress in sentiment analysis and emotion recognition has been made recently, and there has also been an increase in the re- quirements for solving real-world problems. However, human language is complicated and multimodal, making it difficult for computers or artificial intelligence systems to understand. In this study, we adopt …...

Retrieving similar sentences from a given col- lection of sentences is essential in a range of applications. In this work, we propose a novel method to retrieve several sentences that cover an input sentence in form and mean- ing with minimal redundancy, so as to en- hance the overall coverage …...

This paper investigates automatic assessments of text readability for second language learn- ers. The goodness of text readability as- sessment methods has been evaluated using the correlation coefficients between their read- ability scores and labels annotated to the texts by language teachers. For measuring this cor- relation, previous papers have …...

Contextualised word embeddings generated from Neural Language Models (NLMs), such as BERT, represent a word with a vector that considers the semantics of the target word as well its context. On the other hand, static word embeddings such as GloVe represent words by relatively low-dimensional, memory- and compute-efficient vectors but …...

The Module-Attribute Representation of Ver- bal Semantics (MARVS) has been served as an excellent tool for the analysis and differentiation of Chinese near synonymous verbs. In the current study, two Chinese near- synonymous verbs 蹦 (b`eng; to jump) and 跳 (ti`ao; to jump) which have not been investi- gated in …...