Articles

Recently, quite a few studies have been progressive for temporal relation extraction, which is an important work used in sev- eral natural language processing applications. However, less concentration has been paid to corpora of Asian languages. In this work, we explored the feasibility of applying neural net- works to temporal …...

Multidimensional analysis (MDA) is vital for the description of writing style. Several stud- ies have explored factors that may predict the style of learner writing. However, researchers have not treated learner speech in much de- tail. This paper sets out to examine whether proficiency, gender, and academic genre sig- nificantly …...

Chinese inter-clausal anaphora, as in Wo suiran xiang facai, keshi bugan maoxian. ‘I although want to get rich, yet don’t dare to take risks’ is considered ‘rather striking’ (Chao, 1968) because of the way the subject can be fronted or not, which might come from reference patterns of the two …...

In this paper, we attested modifiers in Mandarin and their effects on the verbal complexes. In the past, the Aktionsart of verbs is often discussed within the verbal events. Here, we discuss how modifiers can change or modify the aspects of the verbal semantics by examining several (reduplicated) modifiers in …...

This paper aims to demonstrate that the lexical meanings of major ditransitive verbs (okur- ‘send,’ atae- ‘give,’ and ur- ‘sell’) in Japanese are the same as those of their English counter- parts. Specifically, we will argue that send-type verbs encode both caused motion and caused possession whereas give-type and sell-type …...

Studies based on linguistic theories have reported that internet celebrities em- ploy various persuasion strategies in their speeches. Since persuasion is closely re- lated to pragmatics which involves peo- ple’s cultural background or world knowl- edge and makes it harder for researchers to capture a specific pattern, various fea- tures …...

This paper examines island effects in Viet- namese relativization using methods in exper- imental syntax developed by Sprouse (2007). Typologically a wh-in-situ language, it is debatable whether Vietnamese employs wh- movement in the formation of relative clauses. If Vietnamese relativization is the result of wh-movement process, relativizing certain el- ements …...

Translation universals have been studied extensively in literature, politics, and business but rarely touched in technical field. This paper presents the investigation of translation universals in a new corpus consisting of articles translated by Chinese professionals in computing from English journals and magazines by using statistic findings, principal component analysis …...

Modern pre-trained language models are mostly built upon backbones stacking self- attention and feed-forward layers in an in- terleaved order. In this paper, beyond this stereotyped layer pattern, we aim to improve pre-trained models by exploiting layer vari- ety from two aspects: the layer type set and the layer order. …...

This study introduces a Time Series Analysis approach to metaphor development in a corpus of public discourse as a case study to examine the potential implications for the strategic use of metaphors in discourse over time. The corpus covers 20 years of public speeches by the government leaders in Hong …...

This study attempted to construct the semantic rep- resentation of the two near-synonyms of attention, zhu4yi4 and zhuan1xin1, based on MARVS theory. Since cross-strait semantic comparison has been an important topic in lexical semantic research, we also provided a fine-grained comparison of their even- tive meanings as well as their …...

In extractive summarization, searching for the most salient sentences to generate summaries can be resolved by applying meta-heuristic optimization algorithms including genetic algorithms (GAs), par- ticle swarm optimization (PSO), etc. In these approaches, the best solution, i.e. the expected summary, is found by optimizing an objective function, tak- ing into …...

Answer sentence selection is an important sub-task in Question Answering (QA) that de- termines the correct answer sentence from a passage. This task can naturally be reduced to the semantic text similarity problem between question and answer candidate. In this work, we investigate the significance of various sim- ilarity measures …...

Sentence-BERT is model which based on “Bidirectional Encoder Representations from Transformers” (BERT) for building sentence embedding. This model has abilities for se- mantic analysis similar to BERT; however, the processing need not be online like in BERT. Therefore, it is also effective for similar sen- tence searches. No Japanese sentence-BERT …...

This study presents the quantitative and qual- itative analyses of natural language process- ing (NLP) scientific literature during a 15- year period, from 2006 to 2020, of an un- derrepresented region, the Philippines. This aims to identify the current state of research work and further highlight research gaps for research …...

In this paper, we propose a novel method which establishes a newborn relation between Signal Processing and Natural Language Pro- cessing (NLP) method via Variational Mode Decomposition (VMD). Unlike the modern Neural Network approaches for NLP which are complex and often masked from the end user, our approach involving Term …...

This pilot study attempts a novel compari­ son on how metaphors of BITTERNESS are used in English and Mandarin Chinese, in or­ der to identify subtle cross­linguistic differ­ ences. Using dictionary definitions and Word­ Net databases, we conduct a lexical semantic analysis and establish the various senses “bit­ ter words” …...

Recent researches have demonstrated that BERT shows potential in a wide range of natural language processing tasks. is adopted as an encoder for many state-It of-the-art automatic summarizing sys- tems, which achieve excellent performance. However, so far, there is not much work done for Vietnamese. In this paper, we showcase …...

Visual question answering (VQA) is a hot topic that has recently drew the atten- tion of researchers from domains as di- verse as natural language processing and computer vision. In spite of the fact that numerous VQA datasets and models have been fundamentally considered in English, there are no related …...

. Using Chinese Gigaword Corpus, this study aims to explore the similarities and differences between two Chinese verbs “制服” (zhì fú) and “制 約” (zhì yuē), so as to understand the lexicosemantics of verbs with and without an endpoint. First, the distributional patterns show that the two verbs occur mainly …...