Articles

This paper discusses theoretical and implementational challenges in developing a deep grammar of Indonesian (IndoGram) within the lexical-functional grammar (LFG)-based Parallel Grammar (ParGram) framework, using the Xerox Linguistic Environment (XLE) parser. The ParGram project involves developing and processing computational grammars in parallel to test the LFG’s theoretical claims of language …...

This is a short story of how we have evolved over the last 40 years, doing semantics. could partially overlap with a history ofIt PACLIC which is commemorating the 25th year or a quarter of a century of its founding. The story tells how we semanticists of natu- ral language …...

This paper attempts to argue that the so-called gapless relative clause (GRC) in Korean (Chinese and Japanese as well) can best be dealt with by the Generative Lexicon Theory (GLT) put forward in Pustejovsky (1995). There arises a superficial conflict in the construction: the GRC, with no apparent gap, contains …...

This paper suggests that Generative Lexicon Theory (Pustejovsky, 1995, 2006, 2011) offers a new analysis of numeral classifiers, focusing on Japanese having various kinds of classifiers. It is often said that classifiers agree with quantified nouns, that is, the nouns have to match the semantic requirements of the classifiers. This …...

Unlike its English equivalent after, which often takes NP complement, Chinese temporal connective hou tends to take VP complement. In terms of type coercion, while after seems to generally license event coercion, Chinese hou does not (with a few exceptions), as in most cases the presence of a verb is …...

Natural and non-natural kinds have significant differences. This paper explores the subclasses of each kind and establishes the type system for event nouns. These nouns are divided into natural types, artifactual types, complex types (including natural complex types and artifactual complex types). This new classification not only enriches the Generative …...

We present larger-scale evidence overturning pre- vious results, showing that among the many al- ternative phrasal lexical similarity measures based on word vectors, the Jaccard coefficient most in- creases the robustness of MEANT, the recently in- troduced, fully-automatic, state-of-the-art semantic MT evaluation metric. MEANT critically depends on phrasal lexical similarity …...

This paper is concerned with characterizing psych-predicates in Korean and possibly in Japanese in the GL spirit. We focus on the the status of the Experiencer (or ‘judge’) in relation to other arguments and examine the first- person subjectivity data (constraint). The relevant cause and effect relation and consequent coerced …...

The Constituent-Context Model (CCM) achieves promising results for unsupervised grammar induction. However, its performance drops for longer sentences. In this paper, we describe a general feature-based model for CCM, in which linguistic knowledge can be easily integrated as features. Features take the log-linear form with local normalization, so the Expectation-Maximization …...

There are many languages considered to be low-density languages, either because the population speaking the language is not very large, or because insufficient digitized text material is available in the language even though millions of people speak the language. Bangla is one of the latter ones. Readabil- ity classification is …...

In these days, semantic analysis has been ac- tively studied in natural language processing. For the study of semantic analysis, corpora with semantic annotations are essential. Al- though there are such corpora annotated on newspaper articles, there are various genres and styles, including linguistic expressions that are not found in …...

Most set expansion algorithms assume to acquire new instances of different seman- tic categories independently even when we have seed instances of multiple semantic cat- egories. However, in the setting of set ex- pansion with multiple semantic categories, we might leverage other types of prior knowl- edge about semantic categories. …...

In our paper we focus on analysing textual information usage (selected politeness factors of speech act) in mother tongue and in foreign language to identify phenomena of a language consciousness transfer from the mother tongue into a foreign language communication – transference phenomena – and their impact on textual structures …...

This paper presents a conditional random fields based labeling approach to Chinese punctuation prediction. To this end, we first reformulate Chinese punctuation prediction as a multiple-pass labeling task on a sequence of words, and then explore various features from three linguistic levels, namely words, phrase and functional chunks for punctuation …...

Among various types of recent information explosion, that in news stream is also a kind of serious problems. This paper studies is- sues regarding topic modeling of information flow in multilingual news streams. If some- one wants to find differences in the topics of Japanese news and Chinese news, it …...

This study aims to propose a novel pipeline architecture in building and analyzing large- scaled linguistic data on the cloud-based envi- ronment, an experimental survey on Chinese Polarity Lexicon will be taken as an exam- ple. In this experiment, data are evaluated and tagged by applying crowd sourcing ap- proach …...

Understanding and interpretation of nominal compounds has been a long-standing area of interest in NLP research for various rea- sons. (1) Nominal compounds occur fre- quently in most languages. (2) Compound- ing is an extremely productive word formation phenomenon. (3) Compounds contain implicit semantic relations between their constituent nouns. Most …...

We present a case study on applying com- mon methods for the prediction of lexical properties to a low-resource language, namely Wambaya. Leveraging a small corpus leads to a typical high-precision, low-recall system; using the Web as a corpus has no utility for this language, but a machine learning approach …...

This paper proposes a syntax-semantics correspondence of locative expressions: This proposal is based on the syntactic hierarchy among three locative structures (PPs, VPs, and verbal affixes) and the semantic hierarchy among four locative arguments (Goal, Source, Symmetric Path, Stative Location). As for the syntactic hierarchy, the verbal affixes are closer …...

We consider the task of classifying chat con- tributions by dialogue act in a multi-party set- ting. This extends the problem significantly over the 1-1 chat scenario due to the semi- asynchronous and “entangled” nature of the contributions by chat participants. We ex- periment with a number of machine learning …...