In this paper we address the problem of accessing text information by text navigation. We present an approach to text navigation conceived as a cognitive process exploiting linguistic information present in texts. We claim that the navigational knowledge involved in this process can be modeled in a declarative way with the Sextant language. Since this language refers exhaustively to specific li...

We present the GRASP algorithm for automatically extracting patterns that characterize subtle linguistic phenomena. To that end, GRASP augments each term of input text with multiple layers of linguistic information. These different facets of the text terms are systematically combined to reveal rich patterns. We report highly promising experimental results in several challenging text analysis ta...

NooJ associates each text with a Text Annotation Structure, in which each recognized linguistic unit is represented by an annotation. Annotations store the position of the text units to be represented, their length, and linguistic information. NooJ can represent and process complex annotations, such as those that represent units inside word forms, as well as those that are discontinuous. We dem...

We present an approach to text navigation conceived as a cognitive process exploiting linguistic information present in texts. We claim that the navigational knowledge involved in this process can be modeled in a declarative way with the Sextant language. Since Sextant refers exhaustively to specific linguistic phenomena, we have defined a customized text representation. These different compone...

This paper describes a study on the contribution of linguistically-informed features to the task of quality estimation for machine translation at sentence level. A standard regression algorithm is used to build models using a combination of linguistic and non-linguistic features extracted from the input text and its machine translation. Experiments with EnglishSpanish translations show that lin...

Many experiments have shown that traditional approaches to bothNatural Language Processing (NLP) and Information Retrieval (IR) are not eeective enough to extract information from text; as a matter of fact shallow techniques (such as statistics, keyword analysis, etc.) tend to be imprecise, although eecient and transportable, whereas linguistic approaches tend to be very precise but not robust ...

This work proposes and evaluates the use of linguistic information in the pre-processing phase for text mining tasks applied to Portuguese texts. We present several experiments comparing our proposal to the usual techniques applied in the field. The results show that the use of linguistic information in the pre-processing phase brings some improvements for both text categorization and clustering.

Parallel corpora are considered an important resource for the development of linguistic tools. In this paper our main goal is the development of a bilingual lexicon of verbs. The construction of this lexicon is possible using two main resources: I) a parallel corpus (through the alignment); II) the linguistic tools developed for Spanish (which serve as a starting point for developing tools for ...

Prior research on text messaging has focused on its elliptical nature (e.g., acronyms, etc.). In contrast, the purpose of this research was to conduct an investigation of the type of words that tend to occur in text messages. Participants (N = 224) retrieved their most recent text messages which were then analyzed with the Linguistic Inquiry and Word Count (LIWC) program (Pennebaker et al., 200...

In online crowdfunding, individuals gather information from two primary sources, video pitches and text narratives. However, while the attributes of the attached video may have substantial effects on fundraising, previous literature has largely neglected effects of the video information. Therefore, this study focuses on speech information embedded in videos. Employing the machine learning techn...