Articles

Modelling and understanding dialogues in a conversation depends on identifying the user intent from the given text. Unknown or new intent detection has became an important task, as in a realistic scenario a user intent may fre- quently change over time and divert even to an intent previously not encountered. …...

We investigated the influence of the native language (L1) and its relationship preserved in second language (L2) Japanese texts by machine learning methods. We firstly per- formed native language identification (NLI) on L2 Japanese texts and proposed the char- acter type as a new Japanese-specific feature in NLI. Combining it …...

Bilingual corpus is an important resource for many applications of natural language pro- cessing (NLP). About low-resource language pairs, it is more necessary to build them au- tomatically. In this paper, we propose a novel method that uses an embedding model with a sentence length ratio to align sentences from …...

In this paper, we describe the results of our research aimed at detecting depression in Japanese sentences. In the United States and elsewhere, machine learning approaches to detect depression from language have been demonstrated. However, in Japanese text, there are only two studies that have addressed the detection of depression. …...

Chinese word segmentation and part-of- speech tagging are necessary tasks in terms of computational linguistics and application of natural language processing. Many re- searchers still debate the demand for Chinese word segmentation and part-of-speech tagging in the deep learning era. Nevertheless, resolv- ing ambiguities and detecting unknown words are challenging …...

Aspect-based sentiment analysis is a chal- lenging task that plays an essential role in natural language processing (NLP) and arti- ficial intelligence. However, recent works only focused on aspect detection and senti- ment classification but ignored the sub-task of detecting user opinion, which has im- mense potential in practical applications. …...

Adopting Control Theory, this paper proposes that subject-oriented resultative compounds in Taiwan Southern Min (TSM) have a biclausal structure with PRO as the subject of the second verb. According to the Principle of Minimal Distance (Rosenbaum 1967, 1970), PRO should be controlled by the closest c-commanding antecedent. Therefore, the closest …...

This paper proposes a new perspective to study verbal semantics based on the corpus-based study of near-synonyms. In particular, the author tries to discriminate the near-synonym “tui1 (push)” and “la1 (pull)” by investigating the literal collocations and metaphoric usages through the data extracted from the Chinese Word Sketch (CWS). The …...

In the past few years, generative adversarial networks (GANs) have become increasingly important in natural language generation. How- ever, their performance seems to still have a sig- nificant margin for improvement. For this rea- son, in this paper we propose a new adversarial training method that tackles some of the …...

With the massive success of stochastic lan- guage models, some claim that the symbolic approach is not necessary for natural language processing. However, recent studies made use of linguistically motivated meaning representa- tion of Abstract Meaning Representation and Minimal Recursion Semantics in a natural lan- guage generation task and achieved …...

The lack of parallel data is an obstacle in data- driven grammatical error correction. Recently, researchers have addressed this problem by exploring data augmentation methods. number of studies have focused on improvingA the diversity of errors in generated data. To in- vestigate the importance of error diversity and its impact …...

The widespread use of social networking ser- vices (SNSs) such as Twitter and Facebook in recent years have rendered it easy to in- teract with various people all over the world. Analysis of the user personality and emotion using features such as the text information and image information on SNSs …...

The present paper explored the language change in Chi- nese political discourse in Mainland through the investi- gation of the relationship between sentence and clause based on Menzerath-Altmann law. The results showed that the relationship between sentence and clause in first and second periods (1978-1982 and 1997-2001) Chinese political discourses …...

Recently, several studies have proposed pre- trained encoder-decoder models using mono- lingual data, such as BART, which can im- prove the accuracy of seq2seq tasks via fine- tuning with task-specific data. However, the effectiveness of pre-training using monolingual data requires further verification, as previous experiments on machine translation have fo- …...

This study proposes a new supervised atten- tion mechanism for grammatical error correc- tion, which is trained to focus the encoder- decoder attention to each word in the corrected sentence on words adjacent to corresponding words in the error sentence. Experiments on the CoNLL 2014 test set show that the …...

This paper investigates the differences between Tui and La under the framework of MARVS. Using Gigaword2 Corpus and Sinica Corpus as corpora and Sketch Engine as the query tool, the study is a conducted following three procedures. First, preliminary observation on morphosyntactic differences in these two verbs is obtained by …...

There are two types of datasets for data-to- text: one uses raw data obtained in the real world, and the other is constructed artificially for a controlled task. A straightforwardly out- put text is generated from its paired input data for a manually constructed dataset because the dataset is well …...

In all the natural languages that exist in the world, word collocation plays an important role. The methods of collocation extraction are diverse. On this basis, we compare a variety of commonly used collocation methods from the perspective of vocabulary and grammar, so that researchers can choose specific research methods …...

Many studies were recently done for investi- gating the properties of contextual language models but surprisingly, only a few of them consider the properties of these models in terms of semantic similarity. In this article, we first focus on these properties for English by ex- ploiting the distributional principle of …...

Non-native speakers of English tend to use in- appropriate expressions when relating to aca- demic writing. This may cause a non-fluent essay and probably unable to convey the pre- cise meaning of the texts. Therefore, it is im- portant to choose the best suitable vocabulary when writing an academic article, …...