Articles

The notion of logophoricity has long played a crucial role in understanding the co-referential relations between certain anaphoric expres- sions cross-linguistically, especially for long- distance anaphors violating a locality con- straint and syntactic prominence conditions within the framework of pure syntactic ac- counts. However, Pan (2001) has shown that the …...

This paper argues that the Invertible Construction (IC) in Chinese is a kind of distributive construction. What appears to be an inversion of word order is best understood as the division of the theme NP to be acted upon by a number of agents for an embedded event. This analysis …...

Document sentiment classification is of- ten processed by applying machine learn- ing techniques, in particular supervised learning which consists basically of two major steps: feature extraction and train- ing the learning model. In the literature, most existing researches rely on n-grams as selected features, and on a simple basic classifier …...

Thai stock brokers issue daily stock news for their customers. One broker labels these news with plus, minus and zero sign to indicate the type of recommendation. This paper proposed to classify Thai stock news by extracting important texts from the news. The extracted text is in a form of …...

Sentiment Analysis of tweets is a complex task, because these short messages employ unconventional language to increase the ex- pressiveness. This task becomes even more difficult when people use figurative language (e.g. irony, sarcasm and metaphors) because it causes a mismatch between the literal mean- ing and the actual expressed …...

High dimension of bag-of-words vectors poses a serious challenge from sparse data, overfitting, irrelevant features to document classification. Filter feature selection is one of effective methods for dimensionality reduction by removing irrelevant features from feature set. This paper focuses on two main problems of filter feature selection which are the …...

Traditional sentiment classification methods often require polarity dictionaries or crafted features to utilize machine learning. How- ever, those approaches incur high costs in the making of dictionaries and/or features, which hinder generalization of tasks. Ex- amples of these approaches include an ap- proach that uses a polarity dictionary that can- …...

Identification of prepositional phrases (PP) has been an issue in the field of Natural Language Processing (NLP). In this paper, towards Chinese patent texts, we present a rule-based method and a CRF-based method to identify the PPs. In the rule-based method, according to the special features and expressions of PPs, …...

Japanese is prescriptively said to be verb-final, but it exhibits postposing in colloquial register, where an element is placed after a verb. Based on narrative data, we show that the syntactic type of postposed element is quite diverse and that, contrary to the prevalent, opposing view, Japanese postposing is not …...

In this work, we present a novel way of using neural network for graph-based dependency parsing, which fits the neural network into a simple probabilistic model and can be further- more generalized to high-order parsing. In- stead of the sparse features used in traditional methods, we utilize distributed dense feature …...

The high-dimensionality of lexical features in parsing can be memory consuming and cause over-fitting problems. We propose a general framework to replace all lexical feature tem- plates by low-dimensional features induced from word embeddings. Applied to a near state-of-the-art dependency parser (Huang et al., 2012), our method improves the baseline, …...

A common approach to unsupervised relation extraction builds clusters of patterns express- ing the same relation. In order to obtain clus- ters of relational patterns of good quality, we have two major challenges: the semantic rep- resentation of relational patterns and the scal- ability to large data. In this paper, …...

Wikipedia is supposed to be supporting the “Neutral Point of View”. Instead of accept- ing this statement as a fact, the current paper analyses its veracity by specifically analysing a typically controversial (negative) topic, such as war, and answering questions such as “Are there sentiment differences in how Wikipedia articles …...

In this paper, we propose a novel approach to induce automatically a Part-Of-Speech (POS) tagger for resource-poor languages (languages that have no labeled training data). This ap- proach is based on cross-language projection of linguistic annotations from parallel cor- pora without the use of word alignment infor- mation. Our approach …...

AbstractType theory has played an important role in specifying the formal connection between syntactic structure and semantic interpretation within the history of formal semantics. In recent years rich type theories developed for the semantics of programming languages have become influential in the semantics of natural language. The use of probabilistic …...

AbstractThis paper focuses on the question of what kind of data needs to be recorded about figurative language, in order to capture the essential meaning of the text and to enable us to re-create a synonymous text, based on that data. A short review of the best known systems of …...

. One of the recurring questions in natural language processing is the models’s ability to account for the reality of language ability. Chomsky’s Generative Theory and Minimalism are interested in understanding human language as a cognitive process, which is especially highlighted in the latest proposals by the principle of derivation …...

. We show that every set of productions of every natural language can be described as a three-dimensional space: the syntagmatic axis is the axis of combinations of signs within the text, the paradigmatic axis is the axis of commutations in each position in the text, and the semiotic axis …...

. Robust statistical NLP tools, such as pos-taggers and syntax parsers, often use knowledge-poor features, which can easily be applied to any language, but which do not take into account language specifics. In this study, we attempt to improve analysis for two French phenomena by injecting richer knowledge: pos-tagging of …...

. This article presents the work of Gabriel G. Bès, with extends from the 60s to the 2000s, from structuralism to industrial language analysis. The work of Gabriel G. Bès is marked throughout by the epistemological question and the will to put into practice linguistics as an empirical science. The …...