Articles

. For some years, processing mass of multimedia documents has become a very crucial issue for applications like indexation or information retrieval. Among the focused information, speaker identity can be very useful for such applications. A huge collection of documents cannot be manually processed with a reasonable cost: only automatic …...

. This paper investigates the relation between TT-MCTAG, and RCG. RCG is known to describe exactly the class PTIME. TT-MCTAG has been proposed to model free word order languages. We show that TT-MCTAG with an additional limitation can be transformed into equivalent “simple” RCG. This result is interesting for theoretical …...

: Typed lexical relations between terms are indispensable for the tasks realized in NLP, but collecting lexical information is a difficult process. Indeed, when done manually, it requires the competence of experts and the duration can be prohibitive. When done automatically, the results can be biased by the chosen corpus …...

. This article presents SLAM, an Automatic Solver for Lexical Metaphors like “déshabiller* une pomme” (to undress* an apple). SLAM calculates a conventional solution for these productions. To carry on it, SLAM has to intersect the paradigmatic axis of the metaphorical verb “déshabiller*”, where “peler” (“to peel”) comes closer, with …...

. We propose D-STAG, a new formalism for the automatic analysis of the discourse structure of texts. The analyses computed by D-STAG are hierarchical discourse structures annotated with discourse relations, that are compatible with discourse structures computed in SDRT. The discourse analysis extends the sententiall analysis, without modifying it, which …...

. Named Entity metonymy resolution is a challenging natural langage processing task, which has been recently subject to a growing interest. In this paper, we describe the method we have developed in order to solve Named entity metonymy in the framework of the SemEval 2007 competition. In order to perform …...

. This paper describes the problem of monolingual alignment with search for displaced segments (hereafter called move search). It occurs in genetic criticism, a subfield of literary studies. Existing alignment applications fare poorly on this NP-hard problem. We propose to borrow a family of algorithms from bioinformatics and text algorithmics …...

. NLP is mainly focused on words and sentences even if most people agree that a better understanding of text structure could help extracting knowledge. In this article we show that, in certain domains, textual approaches are relevant for NLP, taking as an example a specific task related to the …...

Automatic Term Recognition systems extract domain-specific terms from text corpora. Un- fortunately current systems fail to capture the whole of the domain covered by a corpus. To address this problem, we present a novel term re-ranking method that generates term lists con- taining terms that are not only individually salient, …...

Instance sampling is a method to balance ex- tremely skewed training sets as they occur, for example, in machine learning settings for anaphora resolution. Here, the number of nega- tive samples (i.e. non-anaphoric pairs) is usually substantially larger than the number of positive samples. This causes classifiers to be biased …...

We investigate the problem of extracting synonyms from dictionary definitions. Our premise for using def- inition texts in dictionaries is that, in contrast to free- texts, their composition usually exhibits more regular- ities in terms of syntax and style and thus, will pro- vide a better controlled environment for synonym …...

This paper explores methods for increasing performance of CRF models, with a particular concern for transfer learning. We consider in particular the transfer case from political news to hard-to-tag business news, and show the effectiveness of several methods, including a novel semi-supervised approach. Keywords Entity extraction, machine learning, business intelligence. …...

We propose a new evaluation strategy for keyphrase extraction based on approximate keyphrase matching. It corresponds well with human judgments and is better suited to as- sess the performance of keyphrase extraction ap- proaches. Additionally, we propose a general- ized framework for comprehensive analysis of keyphrase extraction that subsumes most …...

The article presents two automatic methods that reduce the complexity of the ambiguous space in- troduced by the omission of the part of speech tagger from the architecture of a shallow machine translation system. The methods were imple- mented in a fully functional translation system for related languages. The language …...

In this paper we address the task of transfer- ring FrameNet annotations from an English cor- pus to an aligned Italian corpus. Experiments were carried out on an English-Italian bitext ex- tracted from the Europarl corpus and on a set of selected sentences from the English FrameNet corpus that have …...

An important part of a dialogue system is the correct labelling of turns with dialogue-related meaning. This meaning is usually represented by dialogue acts, which give the system seman- tic information about user intentions. Each di- alogue act gives the semantic of a segment of a turn, which can be …...

This paper presents Amharic part of speech tag- gers developed for factored language modeling. Hidden Markov Model (HMM) and Support Vec- tor Machine (SVM) based taggers have been trained using the TnT and SVMTool. The over- all accuracy of the best performing TnT- and SVM-based taggers is 82.99% and 85.50%, …...

We propose domain-independent language pat- terns that purposefully omit the affective words for the classification of opinions. The informa- tion extracted with those patterns is then used to analyze opinions expressed in the texts. Em- pirical evidence shows that opinions can be dis- covered without the use of affective words. …...

In this paper, we show that by integrating existing NLP techniques and Semantic Web tools in a novel way, we can provide a valuable contribution to the solution of the knowledge acquisition bottleneck problem. NLP tech- niques to create a domain ontology on the ba- sis of an open domain …...

Stemming refers to the grouping of morphologi- cally related words into so-called stem classes for the purpose of improving information retrieval performance. Traditional approaches to stem- ming are language-specific and require a sub- stantial amount of linguistic knowledge. A vi- able alternative is string distance-based stem- ming, in which stem …...