Articles

Word problem solving has always been a challenging task as it involves reasoning across sentences, identification of operations and their order of application on relevant operands. Most of the earlier systems at- tempted to solve word problems with tailored features for handling each category of prob- lems. In this paper, …...

Currently, the biaffine classifier has been at- tracting attention as a method to introduce an attention mechanism into the modeling of bi- nary relations. For instance, in the field of dependency parsing, the Deep Biaffine Parser by Dozat and Manning has achieved state- of-the-art performance as a graph-based de- pendency …...

We attempted to generate a sentence by using the concept of core vocabulary whilst preserv- ing the original meaning of the sentence in the text simplification subtask. The correlation between word simplicity and frequency shows that many complex words are less frequently used. Hence, accurately simplifying sentences containing rare words …...

Sino-Korean words have their etymological roots in Chinese characters. Previous studies showed that the correspondent relation between Chinese and the Korean pronunciation of Chinese characters facilitates the reading of Sino-Korean words by Chinese learners of Korean as a second language (L2). This study quantifies such correspondence at the syllable level …...

“Two literacies and three languages” are used by Hong Kong people. In Hong Kong non- Chinese speaking students are trilingual speakers: they speak their mother language, English and Chinese (Cantonese or Putonghua). Since Urdu speakers make up a large portion of the population among non-Chinese speaking students, the study chose …...

Correcting spelling and grammatical errors of Japanese functional expressions shows practical usefulness for Japanese Second Language (JSL) learners. However, the collection of these types of error data is difficult because it relies on detecting Jap- anese functional expressions first. In this paper, we propose a framework to correct the spelling …...

This paper studies Heavy NP Shift (HNPS) from the perspective of parsing using Min- imalist Grammar. Based on memory usage of the MG parsers, processing difficulties of HNPS as derived by rightward movement, PP movement and remnant movement are each compared with a non-movement structure. A set of complexity metrics …...

This paper proposes a Distilled-Exposition Enhanced Matching Network (DEMN) for story-cloze test, which is still a challenging task in story comprehension. We divide a complete story into three narrative segments: an exposition, a climax, and an ending. The model consists of three modules: input mod- ule, matching module, and distillation …...

The purpose of entity relation extraction is to obtain the relation between named entities from the text. However，most of the researches fo- cus on the tourism, music, medical and other fields, seldom relate with entity relation extrac- tion in the military field. This paper preprocess- es military data sets, defines …...

One interesting linguistic question has been whether and how the characteristics of sandhied Tone 3 are similar to or different from an underlying Tone 2 in Mandarin. In this study, we took a micro view to investigate the vowel height, duration, and rime structure in syllables, and their influence on …...

This paper presents a method for Chinese spelling check that automatically learns to cor- rect a sentence with potential spelling errors. In our approach, a character-based neural ma- chine translation (NMT) model is trained to translate a potentially misspelled sentence into correct one, using right-and-wrong sentence pairs from newspaper edit …...

AbstractA rich literature explores unsupervised segmentation algorithms infants could use to parse their input, mainly focusing on English, an analytic language where word, morpheme, and syllable boundaries often coincide. Synthetic languages, where words are multi-morphemic, may present unique difficulties for segmentation. Our study tests corpora of two languages selected to …...

The surge of social media use has triggered huge demands of multilingual sentiment anal- ysis (MSA) for various purposes, such as unveiling cultural difference. So far, tradi- tional methods resorted to machine transla- tion (MT)—translating other languages to En- glish, then adopted the existing methods of English. However, this paradigm …...

This study is the first to examine the effect of perceptual training on Mandarin tone sandhi production by Cantonese speakers. Auditory and visual inputs of tone sandhi contrasts were included in a short-term laboratory training, and the training was followed by an identifica- tion test. Twenty-four native speakers of Can- …...

Studies on the second language (L2) writing from the angle of translation universals (TU) have substantial empirical research prospects, but as yet only limited literature explains what linguistic factors shape non-nativeness in L2 writing. This article claims to prove that key TU indices may predict non-nativeness, more particularly translationese in …...

Grapheme-to-phoneme models are key com- ponents in automatic speech recognition and text-to-speech systems. With low-resourced language pairs that do not have available and well-developed pronunciation lexicons, grapheme-to-phoneme models are particularly useful. The current work presents an approach that applies an alignment representation for in- put sequences and pre-trained source and …...

This paper examines the syntactic and semantic properties of the two understudied uses of wh-expressions in Cantonese, in the form of m-zi-wh ‘not-know-wh’ and wh-wh (wh-doublets). We argue that they are, respectively, Epistemic Indefinites (EIs) and Reportative Indefinites (RIs). We suggest that the speaker’s ignorance associated with EIs and reportative …...

This study aims at attesting and assessing the usage and functional shift of demonstratives in contemporary Hong Kong Cantonese. Preliminary results from a corpus-based comparison show that while demonstratives are still predominantly used for their deictic and anaphoric functions in face-to-face conversations, an obvious deviation is observed in public discussions …...

This paper examines the use of information-seeking questions and rhetorical questions in terms of event structures of emotion. An emotion is treated as a pivot event that links the emotion-inducing event (i.e. pre- event) and the event induced by emotion (i.e. post- event). We investigate the role information-seeking questions and …...

ive Text Summarization in Three Bullet Points Tomonori Kodaira kdktmk@gmail.com Graduate School of System Design Tokyo Metropolitan University Mamoru Komachi komachi@tmu.ac.jp Graduate School of System Design Tokyo Metropolitan University Abstract Neural network-based approaches have be- come widespread for abstractive text summa- rization. Though previously proposed models for abstractive text summarization …...