Articles

The Encoder-Decoder model is widely used in natural language generation tasks. However, the model sometimes suffers from repeated re- dundant generation, misses important phrases, and includes irrelevant entities. Toward solv- ing these problems we propose a novel source- side token prediction module. Our method jointly estimates the probability distributions over …...

This study presents a long short-term memory (LSTM) neural network approach to Japanese word segmentation (JWS). Previous studies on Chinese word segmentation have succeeded in using recurrent neural networks such as LSTM and gated recurrent units. However, in contrast to Chinese, Japanese includes several character types such as hiragana, katakana, …...

Current research on variations in Mandarin often focuses on the comparisons between Mainland China Mandarin (MCM) and other non-MCM varieties, and less between various non-MCM varieties. This study seeks to compare Mandarin across more regions, in this case, Mainland China, Taiwan and Singapore. This paper presents part of the findings …...

Dialogue systems have been increasingly im- portant these days. In particular, non-task- oriented dialogue systems are studied because of the success of neural network approaches such as seq2seq models. However, these mod- els tend to generate simple responses such as “yes” and “ok.” To construct a dialogue sys- tem that …...

This paper proposes a model-theoretic ap- proach to incremental interpretation where all sentence prefixes have semantic values. The proposed semantics is based on Discourse Representation Theory (DRT), where seman- tic representations (called DRSs) are inter- preted as assignment updates. In our seman- tics, a partial DRS of a sentence prefix …...

Since the beginning of the 20th century, peo- ple have started studying the correlation be- tween language and culture. They observed how language is used in discourses to estab- lish power relations in the society. Eggins (2004) found that the link between language and the choice made by the speaker …...

This article presents a word-sense annotation for the Balanced Corpus of Contemporary Written Japanese: a mashed-up Japanese lexi- con based on the ‘Word List by Semantic Prin- ciples’ (WLSP). The WLSP is a large-scale Japanese thesaurus which includes 98,241 en- tries with syntactic and hierarchical seman- tic categories. We utilized …...

The coordinate compound is an indispensable part of Chinese. We divide the compound words into three types. They are synonymous compounds, related compounds and opposite compounds. Based on the previous researches, we use the method of word embedding to study them from diachronic and synchronic perspectives. First of all, the …...

Personality is the important internal framework that we use when we communicate with the others; thus, it is critical for vehicle-driver communication. Evaluating an individual’s personality requires associating behavior and subjectivity. To develop the vehicle-driver communication system that will be most applicable to actual driving settings, a corpus is necessary …...

The current study investigates approaches to automatic metaphor identification, the compu- tational task of identifying whether a word or phrase in a portion of text is an instance of metaphor. In addition to using the Skip-Gram and Continuous Bag-of-Words algorithms for word-level feature extraction, the Paragraph Vector is utilized for …...

Cross-linguistically, the way that focus is marked through prosody can depend on a variety of factors, including local constraints on prosodic organization or the position of a word within the larger focus constituent. Here we report on a production study that explores the possible influence of prosodic organization and position …...

This study reports a corpus-based analysis on the verb ARGUE in written texts. By adopting Frame Semantics, we analyzed 1385 instances from the corpus and investigated (a) the distribution of each semantic frame; (b) the patterns occurred in each semantic frame; and (c) the topics argued over by arguers. The …...

L1 Burkinabe speakers generally become native- level speakers of French by adulthood, as French is the official second language of their country and is used in their daily life, but learn English as a foreign language is later in their lives. However, as their L2 and L3 contain grammatical markings …...

Emotions are found to be frequently involved in the exclamative sentences. This paper aims to examine the interaction between exclama- tive sentences and emotions in Chinese social media. We propose that exclamative sentences can express all kinds of emotions besides sur- prise. Fear emotion is mostly expressed in ex- clamative …...

In a multilingual or sociolingual configura- tion Intra-sentential Code Switching (ICS) or Code Mixing (CM) is frequently observed nowadays. In the world most of the people know more than one language. The CM us- age is especially apparent in social media plat- forms. Moreover, ICS is particularly signifi- cant in …...

The use of a concept lattice for the vi- sual representation of knowledge has become very common in the data mining field. In- deed, the theory of Formal Concept Anal- ysis (FCA) gives the possibility of organiz- ing and making reasoning on the knowledge stored in the lattice. In this …...

Recently, many studies indicate that charac- ter language model can capture syntactic- semantic word features, resulting in state-of- the-art performance in typical NLP sequence labeling tasks. This paper shows the effective- ness of character language model for Viet- namese Named Entity Recognition by com- paring several methods. We evaluate the …...

When a human interacts with an information retrieval chat bot, he/she can ask multiple questions at the same time. Current question answering systems can’t handle this scenario effectively. In this paper we propose an ap- proach to identify question spans in a given utterance, by posing this as a sequence …...

Classifying the relationship between entities is an important natural language processing (NLP) task. Scientific Relation Classification aims at automatically categorizing scientific semantic relationships among entities in sci- entific documents. Conventionally, only task unspecific supersense, such as supersense (or hyernym) from WordNet (e.g., ANIMAL is the supersense of “dog”), is used …...

This study conducted a corpus analysis of the lexical and grammatical representation of the FEAR emotion in Taiwan Mandarin and Russian, focusing on four common fear words which mean ‘to fear’ and function as ‘predicate’. The dataset contains 4,433 instances of hàipà, 1,202 kĕpà instances, 733 bojat’sja instances, and 617 …...