Articles

Paraphrase generation is widely used for various natural language processing (NLP) applications such as question answering, multi-document summarization, and machine translation. In this study, we identify the problems occurring in the process of applying existing probabilistic model-based methods to agglutinative languages, and provide solutions by reflecting the inherent characteristics of …...

We paraphrase nouns along the contexts of sentence input on the basis of a variety of contexts obtained from a large-scale corpus. The proposed method only uses the number of types of context, not word frequency or co- occurrence frequency features. This method is based on the notion that paraphrase …...

. This article relates work done in order to expand the performance of a commercial French grammar checker. We try to achieve the correction of errors only detectable when an anaphora pronoun is linked with its antecedent. The algorithm searches for the antecedent within the same sentence as the pronoun …...

. Relations annotation and inference in a lexical-semantic network : application to radiology Domain spe- cific ontologies are invaluable despite many challenges associated with their development. In most cases, domain know- ledge bases are built with very limited scope without considering the benefits of plunging domain knowledge to a general …...

. Analysing lexical complexity is a task that has mainly attracted the attention of psycholinguists and language teachers. More recently, this issue has seen a growing interest in the field of Natural Language Processing (NLP) and, in particular, that of automatic text simplification. The aim of this task is to …...

. We introduce a new approach for manually constructing broad-coverage lexical ressources based on a specific type of lexical network called lexical system. Drawing on experience gained from the construction of the French Lexical Network (fr-LN), we begin by formally characterizing lexical systems as “small-world” graphs of lexical units that …...

We propose and assess the novel idea of using automatically induced constructions as a unit of analysis for corpus-based discourse analysis. Automated techniques are needed in order to elucidate important characteristics of corpora for social science research into topics, framing and argument structures. Compared with cur- rent techniques (keywords, n-grams, …...

: This paper investigates the transitive uses of the verb fan „annoy; be annoyed; bother to do‟, which exhibit both similarities and disparities between Beijing Mandarin and Taiwan Mandarin, as far as the data from Gigaword corpus, containing data from Mainland China (XIN) and Taiwan (CNA), are concerned. In terms …...

. Robust statistical NLP tools, and in particular pos-taggers, often use knowledge-poor features, which are easily applicable to any language but do not look beyond 1 or 2 tokens to the right and left and do not make use of syntactic equivalence classes. Although pos-tagging tends to get high accuracy …...

This corpus-based study analyzes meanings of khɨn3 ‘ascend’ and loŋ1 ‘descend’ in Thai in comparison with up and down in English. Data came from three corpora: the Thai National Corpus (TNC) (Aroonmanakun et al., 2009), the British National Corpus (BNC), and the English-Thai Parallel Concordance (Aroonmanakun, 2009). Results of the …...

This paper analyzes four kinds of Cantonese polar questions, HO2, ME1, AA4 and A-NOT- A questions in the framework of radical in- quisitive semantics (Groenendijk & Roelof- sen, 2010; Aher, 2012; Sano, 2014). HO2, ME1 and A-NOT-A questions have multi- dimensional semantics. In addition to their primary speech act of …...

For textual entailment recognition systems, it is often important to correctly handle Gen- eralized quantifiers (GQ). In this paper, we explore ways of encoding GQs in a recent framework of Dependency-based Composi- tional Semantics, especially aiming to cor- rectly handle linguistic knowledge like hy- ponymy when GQs are involved. We …...

In parsing, a phrase is more likely to be associated with an adjacent word than to a non-adjacent one.� Instances of adjacency violation pose a challenge to researchers but also an opportunity to better understand how people process sentences and to improve parsing algorithms by, for example, suggesting new features …...

This paper aims to investigate the subtle nuances of meaning of two Chinese particles “guo1” and “guo2” as well as their different functions in Chinese temporal system. Two technical terms, “tense” and “aspect”, in traditional Chinese grammar are reconsidered in terms of the nature of these two concepts and the …...

In English text, independent clauses should be demarcated with full-stops (periods), or linked together with conjunctions. Non-native speak- ers are often prone to linking them improp- erly with commas instead of conjunctions, producing comma splices. This paper de- scribes a method to detect comma splices us- ing Conditional Random Fields …...

Using instant messenger in real time commu- nication is widespread worldwide. However, in the communication of using cross-language (Japanese - other languages) instant messag- ing, the use of colloquial expressions usually degrades the efficiency of communication. The contributions of our research can be split into two parts: (1) we analyzed …...

This paper addresses the influences of common ground, context and information structure on the linguistic production and interpretation processes with a special reference to counter-expectation in Thai. It presents, first of all, a fresh view on the operation of the particle lɛɛw45 as a marker of counter-expectation. It also indicates …...

. We present DYALOG-SR, a statistical dependency parser developed for the SPRML 2013 shared task over 9 very different languages. DYALOG-SR implements a shift-reduce parsing algorithm (a la MALT), extended with beams and dynamic programming techniques. One of the specificities of DYALOG-SR is its ability to handle word lattices as …...

This paper argues in favor of Haiman’s (1978) idea that conditionals and topics are analo- gous. The evidence comes from exhaustifi- cation over topicalized questions, which have the same semantics as conditional questions (Isaacs & Rawlins, 2008). 1...

Chinese radicals are linguistic elements smaller than Chinese characters1. Normally, a radical is a semantic category and almost all characters contain radicals or are radicals themselves. In subjectivity classification on sentences, we can use radicals to represent characters, which reduce the scale of word space while keep the subjectivity information. …...