Articles

We propose a novel approach to Vietnamese word segmentation. Our approach is based on the Single Classification Ripple Down Rules methodology (Compton and Jansen, 1990), where rules are stored in an exception structure and new rules are only added to correct segmentation errors given by existing rules. Experimental results on …...

We explore the use of Convolutional Neural Networks (CNNs) for multi-label Authorship Attribution (AA) problems and propose a CNN specifically designed for such tasks. By averaging the author probability distributions at sentence level for the longer documents and treating smaller documents as sentences, our multi-label design adapts to single-label datasets …...

Wikipedia is a very popular source of encyclopedic knowledge which provides highly reliable articles in a variety of domains. This richness and popularity created a strong motivation among NLP researchers to develop relatedness measures between Wikipedia concepts. In this paper, we introduce WORD (Wikipedia Oriented Relatedness Dataset), a new type …...

It is proved that in text-based communication such as sms, messengers applications, misinterpretation of partner’s emotions are pretty common. In order to tackle this problem, we propose a new multilabel corpus named Emotional Movie Transcript Corpus (EMTC). Unlike most of the existing emotion corpora that are collected from Twitters and …...

Author profiling - the computational task of prediction author’s demographics from text - has been a popular research topic in the NLP field, and also the focus of a number of prominent shared tasks. Author profiling is a problem of growing importance, with applications in forensics, security, sales and many …...

Aspect identification in user generated texts by supervised text classification might suffer degradation in performance when changing to other domains than the one used for training. For referring to aspects such as quality, price or customer services the vocabulary might differ and affect performance. In this paper, we present an …...

In this paper, we present a gold standard corpus for Albanian part-of-speech tagging and perform evaluation experiments with different statistical taggers. The corpus consists of more than 31,000 tokens and has been manually annotated with a medium-sized tagset that can adequately represent the syntagmatic aspects of the language. We provide …...

This paper is a short empirical study of the performance of centrality and classification based iterative term set expansion methods for distributional semantic models. Iterative term set expansion is an interactive process using distributional semantics models where a user labels terms as belonging to some sought after term set, and …...

Hate speech has become a major issue that is currently a hot topic in the domain of social media. Simultaneously, current proposed methods to address the issue raise concerns about censorship. Broadly speaking, our research focus is the area human rights, including the development of new methods to identify and …...

This paper describes the development of an idiom-annotated corpus of Russian. The corpus is compiled from freely available resources online and contains texts of different genres. The idiom extraction, annotation procedure, and a pilot experiment using the new corpus are outlined in the paper. Considering the scarcity of publicly available …...

Collocations such as heavy rain or make [a] decision are combinations of two elements where one (the base) is freely chosen, while the choice of the other (collocate) is restricted by the base. Research has consistently shown that collocations present difficulties even to the most advanced language learners, so that …...

Complex nominals (CNs) (e.g. wind turbine) are very common in English specialized texts (Nakov, 2013). However, all too frequently they show similar external forms but encode different semantic relations because of noun packing. This paper describes the use of paraphrases that convey the conceptual content of English two-term CNs (Nakov …...

This paper presents Konbitzul, an online database of verb+noun MWEs in Spanish and Basque. It collects a list of MWEs with their translations, as well as linguistic information which is NLP-applicable: it helps to identify occurrences of MWEs in multiple morphosyn- tactic variants, and it is also useful for improving …...

Multiword expressions (MWEs) consist of groups of tokens, which should be treated as a single syntactic or semantic unit. In this work, we focus on verbal MWEs (VMWEs), whose accurate recognition is challenging because they could be discontinuous (e.g., take .. off). Since previous English VMWE annotations are relatively small-scale …...

In this paper we present a preliminary study on application of PARSEME guidelines of annotating mutiword expressions to Chinese language. We focus on one specific category - light verb constructions (LVCs). We make use of an existing resource containing Chinese light verbs and examine whether this resource fulfill the requirements …...

In this paper, we present a set of improvements introduced to MUMULS, a tagger for the automatic detection of verbal multiword expressions. Our tagger participated in the PARSEME shared task and it was the only one based on neural networks. We show that character-level embeddings can improve the performance, mainly …...

Humans naturally organise and classify the world into sets and categories. These categories expressed in natural language are present in all data artefacts from structured to unstructured data and play a fundamental role as tags, dataset predicates or ontology attributes. A better understanding of the category syntactic structure and how …...

In recent years, there has been a surge of interest in the natural language processing related to the real world, such as symbol grounding, language generation, and nonlinguistic data search by natural language queries. We argue that shogi (Japanese chess) commentaries, which are accompanied by game states, are an interesting …...

In this paper, we describe the LIDIOMS data set, a multilingual RDF representation of idioms currently containing five languages: English, German, Italian, Portuguese, and Russian. The data set is intended to support natural language processing applications by providing links between idioms across languages. The underlying data was crawled and integrated …...

This paper presents Tilde’s work on collecting language resources from government institutions and other public administrations in the Nordic and Baltic countries. We introduce the activities and results of the European Language Resources Coordination (ELRC) action in this region, provide a synopsis of ELRC workshops held in all countries of …...