Articles

This paper presents our attempt to develop an Indonesian multi-word expression (MWE) identification framework. The framework con- sists of three different steps. In the first step, we surveyed any definitions and categorizations of MWEs in the previous studies. In the second step, sentences from our language corpora are segmented and …...

Meaning Representation for MWE: A study of the mapping of aspectuality based on Mandarin light verb jiayi Lu Lu Nianwen Xue Hong Kong Polytechnic University Brandeis University lu-cbs.lu@polyu.edu.hk xuen@brandeis.edu Chu-Ren Huang Hong Kong Polytechnic University churen.huang@polyu.edu.hk Abstract Multiword expression (MWE) refers to various types of linguistic units that are made …...

Lexical reduplications (LR) in Cantonese are multiword expressions (MWEs) that are frozen and unproductive. The meanings of LR are often non-compositional, such as hung4 bok1 bok1 ‘bright red’, where bok1 bok1 does not contribute any meaning to hung4 ‘red’. This can pose a challenge in parsing and nat- ural language …...

Persian, like many other Asian languages, li- censes the use of bare nouns in object position. Such sequences are often treated as multi- word expressions (compound verbs/light verb constructions, and pseudo-incorporation con- structions). In the paper, I argue against a uniform treatment of all ‘bare noun + verb’ sequences in …...

In recent years, the quality of machine transla- tion has significantly improved, and it is con- sidered that translation of a novel becomes possible. However, when performing transla- tion for novels by a machine translation, it needs an evaluation method that performs com- parison using a vector of distributed represen- …...

This paper describes the first trial of neu- ral machine translation (NMT) from historical Japanese to contemporary Japanese. To com- pensate for the lack of parallel data, we used pre-trained word embeddings for the input of the system and performed diachronic domain adaptation in the order of time. We investi- …...

Our study presents a series of experiments on speech recognition with endangered and ex- tinct Samoyedic languages, spoken in North- ern and Southern Siberia. To best of our knowledge, this is the first time a functional ASR system is built for an extinct language. We achieve with Kamas language a …...

Japanese has a grammatical class commonly referred to as “verbal nouns (VN)”, whose members form a phrasal verb in combination with the light verb SURU. While most VNs can be used as the head of a complement nominal (subject, object, etc.) of a predicate, some lack this use and are …...

In this paper, we propose a method of ex- tracting novel character information such as characters’ names, gender, age, occupations, and a part of relationships between characters from synopses of fantasy novels in Japanese using sequence labeling by comparing se- quence labeling models based on CRF (Con- ditional Random Fields) …...

When making comparisons, Japanese allows somewhat sloppy comparisons. In Japanese, ‘Taro’s grade is better than Hanako’ means Taro’s grade is better than Hanako’s grade. Also, when referring to a difference, ‘Taro’s opinion is different from Hanako’ in Japanese means Taro’s opinion is different from Hanako’s opinion. Such collocations are widely …...

Transformers have recently achieved promis- ing results in many natural language process- ing tasks; however, the understanding of trans- formers for information extraction in business scenarios is still an open question. This paper bridges the gap by introducing an investiga- tion to understand the behavior of transform- ers in extracting …...

Part-of-Speech (POS) tagging is considered a preliminary task for parsing any language, which in turn is required for many Natural Language Processing (NLP) applications. Ex- isting work on the Hindi language for this task reported results on either the General or the News domain from the Hindi-Urdu Treebank that relied …...

We conducted a corpus-based study on near synonymous cognitive verbs “renwei 認為” and “yiwei 以為” with a similar meaning of “to think” in Chinese. The motivation of this study is that information trustworthiness in propositions var- ies with the use of “renwei” or “yiwei”, which concerns the issue of speakers’ …...

Text summarization is an important yet chal- lenging task in natural language processing. In this paper, we investigate Pointer Genera- tor Networks for sentence compression. Using Vietnamese as a case study, our model could yield sentence summaries with high quality of syntax, factual correctness and completeness. Interestingly, we demonstrate that …...

In the text classification problem, the im- balance of labels in datasets affect the per- formance of the text-classification models. Practically, the data about user comments on social networking sites not altogether appeared - the administrators often only allow positive comments and hide negative comments. Thus, when collecting the data …...

The present study examined the acoustic cues of sarcasm in Thai. Four Thai speakers par- ticipated in two reading tasks: neutrality and sarcasm reading. Speech rate, F0 mean, F0 range, amplitude mean, amplitude range, F0 slope, and F0 intercept were measured and analyzed. The results indicated that sarcasm was produced …...

Herein, we study infants’ reactions associated with the ordering of development mediated by picture books. We propose an approach that detects evidence on infants’ reaction types from reviews of picture books. Existing devel- opmental psychology research reports that in- fants’ development occurs in a specific order; i.e., infants react according …...

Text classification is a popular topic of natural language processing, which has currently at- tracted numerous research efforts worldwide. The significant increase of data in social me- dia requires the vast attention of researchers to analyze such data. There are various stud- ies in this field in many languages but …...

This research explores the intense con- flict of the legalization of same-sex mar- riage in Taiwan by studying how the near-synonyms denoting homosexual, 同 志 tóngzhì and 同性戀 tóngxìngliàn, are used by the opposing stances. Two re- search questions related to lexical seman- tics are addressed, i.e., what the seman- …...

This study conducted an experiment to com- pare the word embeddings of a compound word and a word in Japanese on the same vec- tor space using bilingual word embeddings. Because Japanese does not have word delim- iters between words; thus various word defi- nitions exist according to dictionaries and …...