Articles

Natural Language Processing provides a very significant contribution to various research ar- eas such as the e-health, e-business, educa- tion and antiterrorism. However, understand- ing the meaning, scope and usage of linguis- tic knowledge is a tedious task for a hetero- geneity of potential users. Several approaches have been proposed …...

Reinforcement Learning is considered as the state of the art approach for dialogue policy optimization in task-oriented dialogue systems. However, these models demand a large cor- pus of dialogues to learn effectively. Train- ing Reinforcement Learning agent with low data amount tends to overfit the agent. Al- though synthesizing dialogue …...

Neural-based models have achieved outstand- ing performance on slot filling and intent clas- sification, when fairly large in-domain train- ing data are available. However, as new do- mains are frequently added, creating sizeable data is expensive. We show that lightweight augmentation, a set of augmentation meth- ods involving word span …...

A perceptual identification experiment has been designed to study the effects of vowel context in Mandarin speakers’ perceptual identification of L2 English fricatives and affricates. The identification task elicited the preferred Mandarin equivalent and a fitness rate of each of about 70 stimuli words with these English consonants from 67 …...

This paper examines gender and age salience and (stereo)typicality in British English talk with the aim to predict gender and age cat- egories based on lexical, phrasal and turn- taking features. We examine the SpokenBNC, a corpus of around 11.4 million words of British English conversations and identify be- havioural …...

Although some linguists (Rusmali et al., 1985; Crouch, 2009) have fairly attempted to de- fine the morphology and syntax of Minangk- abau, information processing in this language is still absent due to the scarcity of the an- notated resource. In this work, we release two Minangkabau corpora: sentiment analy- sis …...

For simultaneous interpretation, it is very important to identify appropriate segmentation boundaries so that the source text can be translated accurately and promptly. This paper proposes four different segmentation methods for a simultaneous interpretation system. These methods are designed considering the balance between translation accuracy and translation latency. They employ …...

We propose to study the automatic generation of descriptions from content editing activities in collaborative environments. We define such task as identifying the changes associated to two consecutive versions of a document, and then producing a message in natural language that explains it, which should provide a com- pact description …...

Word embeddings are used in various fields of natural language processing. The use of word embeddings and concept or word sense em- beddings demonstrated effectiveness in many tasks, such as machine translation and text summarization. However, it is difficult to ob- tain a sufficiently large concept-tagged cor- pus, as the …...

This paper investigates the syntax of Negative WH-Constructions (NWHCs) in Korean and argues, under Coniglio and Zegrean’s (2012) split-ForceP framework, that NWH-phrases like mwe-ka and ettehkey, which are base- generated above or at the edge of IP, undergo covert movement to the split-Force domain to reflect their sensitivity to clause …...

The present paper explored the focusing topics change and language change in Report on the Work of the Gov- ernment by Premiers of the People’s Republic of China (hereinafter Report texts). The text clustering and corre- spondence analysis showed the focusing topics change in selected three periods Report texts. The …...

Words are conventionalized symbols that pre- sent the function by which meaning is attached to form. The Word Sense Disambiguation, which has been taken as one of the core seman- tic processing tasks in the pipe-lined NLP ar- chitecture, aims to assign proper word sense to lemma form in varied …...

Question retrieval is an important task in ques- tion answering. This task is considered to be challenging due to the lexical gap issue, i.e., similar questions could be expressed in dif- ferent words or phrases. Although there are numerous researches conducted on question retrieval task in English, the corresponding problem …...

SeaNMF stands for the Semantics-assisted non-negative factorization. This approach is the current state-of-the-art method for topic modeling. In this study, we propose a new method (i.e., DML-SeaNMF) for improving the latent topic by utilizing the distance metric learning. The main idea is to iteratively learn the appropriate term-document and term-term …...

Diacritic restoration plays an important role in Natural Language Processing (NLP) for many diacritical languages such as Vietnamese, Czech, Hungarian, etc. With the develop- ment of deep neural network, this task could reach a good accuracy, i.e. F1-score is up to 97.7% for the state-of-the-art models. How- ever, the output …...

Metaphors are ubiquitous in human language, and there has been an increasing interest in metaphor processing and interpretation from the field of computational and cognitive linguistics. Although metaphors have been greatly researched, there remain certain kinds of metaphors that are under-researched. One of them is KIND metaphors. KIND metaphors are …...

AbstractNatural Language Processing (NLP) of textual data is usually broken down into a sequence of several subtasks, where the output of one the subtasks becomes the input to the following one, which constitutes an NLP pipeline. Many third-party NLP tools are currently available, each performing distinct NLP subtasks. However, it …...

AbstractThe development of effective NLP tools for the L2 classroom depends largely on the availability of large annotated corpora of language learner text. While annotated learner corpora of English are widely available, large learner corpora of Spanish are less common. Those Spanish corpora that are available do not contain the …...

AbstractPromoting interoperrable computational linguistics (CL) and natural language processing (NLP) application platforms and interchange-able data formats have contributed improving discoverabilty and accessbility of the openly available NLP software. In this paper, wediscuss the enhanced data visualization capabilities that are also enabled by inter-operating NLP pipelines and interchange formats. For adding …...

AbstractThis paper describes Contemplata, an annotation platform that offers a generic solution for treebank building as well as treebank enrichment with relations between syntactic nodes. Contemplata is dedicated to the annotation of constituency trees. The framework includes support for syntactic parsers, which provide automatic annotations to be manually revised. The …...