Articles

In internet advertising, negative key phrases are used in order to exclude the display of an advertisement to non-target audience. We describe a method for auto- matically identifying negative key phrases. We use Wikipedia as our sense inventory and as an annotated corpus from which we create context vectors and …...

Information extraction in specialized texts raises different problems related to the kind of searched information. In this pa- per, we are interested in relation identifi- cation between some concepts in medical reports, task that was evaluated in the i2b2 2010 challenge. As relations are expressed in natural language with a …...

We present a novel method for FrameNet- based semantic role labeling (SRL), fo- cusing on limitations posed by the limited coverage of available annotated data. Our SRL model is based on Bayesian cluster- ing and has the advantage of being very ro- bust in the face of unseen and incomplete …...

Machine translation (MT) technology is becoming more and more pervasive, yet the quality of MT output is still not ideal. Thus, human corrections are used to edit the output for further studies. However, how to judge the human correction might be tricky when the annotators are not experts. We present …...

Machine learning approaches for Information Extraction use different types of features to acquire semantically related terms from free text. These features may contain several kinds of linguistic knowledge: from orthographic or lexical to more complex features, like PoS- tags or syntactic dependencies. In this paper we select four main types …...

Based on the evidences of prever- bal conceptual development in infants, we adopt semantics-first approach for word-learning. We first cluster several perceptual categories from a complex visual interaction. Using a surveillance traffic video, we a) identify the mov- ing objects by separating these from a static background, and b) group …...

This paper, we propose an approach for event extrac- tion and corresponding event actor identification- within the TimeML framework. Firstly, for event ex- traction, we develop SVM based hybrid approach and for event actor identification the baseline model is developed based on the subject information of the dependency-parsed event sentences. …...

We propose the negation naive Bayes (NNB): a new method to categorize prod- uct pages on the Web depending on their information. It is a modified version of the naive Bayes (NB) and we got the idea from the complement naive Bayes (CNB). We compared the NNB with the NB …...

Incorporating distant information via manu- ally selected skip chain templates has been shown to be beneficial for the performance of conditional random field models in con- trast to a simple linear chain based structure (Sutton and McCallum, 2007; Galley, 2006; Liu et al., 2010). The set of properties to be …...

The paper proposes a treatment of relative sen- tences within the framework of Head-driven Phrase Structure Grammar (HPSG). Relative sentences are considered as a rather delicate linguistic phenomenon and not explored enough by Arabic researchers. In an attempt to deal with this phenomenon, we propose in this paper a study …...

We discuss a method for identifying se- mantic arguments of a verb from a sen- tence. It differs from existing methods by an unique feature that represents all se- mantic arguments of a verb in a syntactic parse tree. The feature is a path in which at least one of …...

We present the results of a project of build- ing a lexical-functional grammar of Ay- mara, an Amerindian language. There was almost no research on Aymara in compu- tational linguistics to date. The goal of the project is two-fold: First, we want to provide a formal description of the lan- …...

This paper discusses linguistic annotation issues, essential to a corpus-based ap- proach to modelling the language use of foreign language learners in various con- texts. We focus on learners of English and describe the corpora we use as well as the linguistic approach underlying their development. We present a scheme …...

In this paper we look at the conjugation of the Romanian verb, in particular, at its ir- regularities, from a machine learning point of view. Our attempt is to predict the pres- ence or absence of any alternation in the stem (apophony), using n-gram represen- tations of the infinitive. We …...

While the concept of similarity is well grounded in psychology, text similarity is less well-defined. Thus, we analyze text similarity with respect to its definition and the datasets used for evaluation. We for- malize text similarity based on the geo- metric model of conceptual spaces along three dimensions inherent to …...

Approaches based on machine learning, such as Support Vector Machines, are of- ten used to classify semantic relations be- tween entities. In such framework, classi- fication accuracy strongly depends on the set of features which are used to represent the input to the classifier. We are propos- ing here a …...

Current statistical machine translation (SMT) systems are stated to be dependent on the availability of a very large training data for producing the language and trans- lation models. Unfortunately, large paral- lel corpora are available for a limited set of language pairs and for an even more lim- ited set …...

Recognition and translation of named entities (NEs) are two current research topics with regard to the proliferation of electronic documents exchanged through the Internet. The need to assimilate these documents through NLP tools has become necessary and interesting. Moreover, the formal or semi- formal modeling of these NEs may intervene …...

Organizing data into category hierarchies (taxonomies) is useful for content discov- ery, search, exploration and analysis. In in- dustrial settings targeted taxonomies for spe- cific domains are mostly created manually, typically by domain experts, which is time consuming and requires a high level of ex- pertise. This paper presents an …...

We present a data-driven approach for rec- ognizing and classifying TimeML events in Italian. A high-performance state- of-the-art approach, TIPSem, is adopted and extended with Italian-specific seman- tic features from a lexical resource. The resulting approach has been evaluated over the official TempEval2 Italian test data. The analysis of the …...