Identifying and translating a MultiWord Expression (MWE) in a text represents an issue for numerous applications in Natural Language Processing (NLP) as MWEs appear in all text genres and pose significant problems for every kind of NLP tasks. In this paper, we describe a hybrid approach for extracting contiguous MWEs and their translations in a FrenchEnglish parallel corpus. We evaluate both th...

The identification of discourse units is an essential step in discourse parsing, the automatic construction of a discourse structure from a text. We present a rule-based algorithm to identify elementary discourse units (EDUs) in Dutch written text. Contrary to approaches that focus on the determination of segment boundaries, we identify complete discourse units, which is especially helpful for ...

We propose a resource-based Named Entity Classification (NEC) system, which combines named entity extraction with simple language-independent heuristics. Large lists (gazetteers) of named entities are automatically extracted making use of semi-structured information from the Wikipedia, namely infoboxes and category trees. Languageindependent heuristics are used to disambiguate and classify enti...

Some document genres contain a large number of figures. This position paper outlines approaches to diagram summarization that can augment the many well-developed techniques of text summarization. We discuss figures as surrogates for entire documents, thumbnails, extraction, the relations between text and figures as well as how automation might be achieved. The focus is on diagrams (line drawing...

This paper discusses the classification of books purely based on cover image and title, without prior knowledge or context of author and origin. Several methods were implemented to assess the ability to distinguish books based on only these two characteristics. First we used a color-based distribution approach. Then we implemented transfer learning with convolutional neural networks on the cove...

This paper describes a Verb Phrase Ellipsis (VPE) detection system, built for robustness, accuracy and domain independence. The system is corpus-based, and uses a variety of machine learning techniques on free text that has been automatically parsed using two different parsers. Tested on a mixed corpus comprising a range of genres, the system achieves a 72% F1-score. It is designed as the first...

Lexicon is in important resource in any kind of language processing application. Corpus-based lexica have several advantages over other traditional approaches. The lexicon developed for Sinhala was based on the text obtained from a corpus of 10 million words drawn from diverse genres. The words extracted from the corpus have been labeled with parts of speech categories defined according to a no...

Arabic, Hebrew, and similar languages are typically written without diacritics, leading to ambiguity and posing a major challenge for core language processing tasks like speech recognition. Previous approaches to automatic diacritization employed a variety of machine learning techniques. However, they typically rely on existing tools like morphological analyzers and therefore cannot be easily e...

Abstract Prior research has examined the impact of different cognitive predictors on students’ expository and narrative text comprehension. It become apparent that some variables predict comprehension in both genres, while are genre-specific predictors. However, effect reading motivation remains unclear. Thus, aim was to investigate which reading-related motivational characteristics universal v...