Articles

In this paper, we experiment with the task of contextual synonym expansion, and com- pare the benefits of combining multiple lexical resources using both unsupervised and super- vised approaches. Overall, the results obtained through the combination of several resources ex- ceed the current state-of-the-art when selecting the best synonym for …...

We present a method for extracting verb- centered constructions (VCCs) from corpora. In our framework, simple and multiword verbs, with or without valence are all VCCs. They are treated uniformly, from e.g. to breathe till e.g. to take something into consideration. In order to extract VCCs we represent the corpus …...

We explore the performance of the Vector Space Model (VSM) in finding verb synonyms in Por- tuguese by analyzing the impact of three oper- ating parameters: (i) the weighting function, (ii) the context window used for automatically ex- tracting features, and (iii) the minimum num- ber of vector features. We …...

We introduce a formal framework that allows the cal- culation of new purely statistical confidence measures for parsing, which are estimated from posterior proba- bility of constituents. These measures allow us to mark each constituent of a parse tree as correct or incor- rect. Experimental assessment using the Penn Tree- …...

This paper addresses the problem of semantic relation identification for a set of relations difficult to differen- tiate: near-misses and overlaps. Based on empirical observations on a fairly large dataset of such exam- ples we provide an analysis and a taxonomy of such cases. Using this taxonomy we create various …...

This paper studies the application of text simi- larity methods to disambiguate ambiguous links between WordNet nouns and Wikipedia cate- gories. The methods range from word overlap between glosses, random projections, WordNet- based similarity, and a full-fledged textual en- tailment system. Both unsupervised and super- vised combinations have been tried. …...

In this paper we propose a methodology for sen- timent analysis of figurative language which ap- plies Word Sense Disambiguation and, through an n-gram graph based method, assigns polar- ity to word senses. Polarity assigned to senses, combined with contextual valence shifters, is exploited for further assigning polarity to sen- …...

In the task of semantic category labeling, given a text, every word in it has to be assigned a semantic category. Our language of interest is Hindi. We use the ontolog- ical categories defined in Hindi Wordnet as semantic category inventories. In this paper we present two un- supervised approaches …...

We describe a novel language-independent ap- proach to the task of determining the polarity, positive or negative, of the author’s opinion on a specific topic in natural language text. In partic- ular, weights are assigned to attributes, individ- ual words or word bi-grams, based on their posi- tion and on …...

In this paper, we use corpus-based measures for constructing phylogenetic trees and try to ad- dress some questions about the validity of do- ing this and applicability to linguistic areas as against language families. We experiment with four corpus based distance measures for con- structing phylogenetic trees. Three of these …...

The goal of this paper is to compare a set of dis- tance/similarity measures, some motivated sta- tistically, others motivated stylistically, regard- ing their ability to reflect stylistic similarity between texts. To assess the ability of these distance/similarity functions to capture stylistic similarity between texts, we have tested them in …...

We present a fairly complete grammar of inter- rogative and relative clauses in French, written in the formalism of Interaction Grammars. Interac- tion Grammars combine two key ideas: a gram- mar is viewed as a constraint system which is expressed through the notion of tree description, and the resource sensitivity …...

Evaluation of word space models is usually local in the sense that it only considers words that are deemed very similar by the model. We propose a global evaluation scheme based on clustering of the words. A clustering of high quality in an external evaluation against a semantic resource, such …...

This paper addresses the problem of scientific research analysis. We use the topic model Latent Dirichlet Allocation [2] and a novel classifier to classify re- search papers based on topic and language. Moreover, we show various insightful statistics and correlations within and across three research fields: Linguistics, Computational Linguistics, and …...

State-of-the-art Machine Translation (MT) sys- tems are still far from being perfect. An alterna- tive is the so-called Interactive Machine Transla- tion (IMT) framework. In this framework, the knowledge of a human translator is combined with a MT system. We present a new tech- nique for IMT which is based …...

Document Planning - the task of deciding which content messages should be realised in a target document based on raw data provided by an underlying application, and how these messages should be structured - is arguably one of the most crucial tasks in Natural Language Generation (NLG). In this work …...

In order to produce efficient Natural Language Pro- cessing (NLP) tools, reliable linguistic resources are a preliminary requirement. When available for a given language, the resources are generally far below the ex- pectations in terms of quality, coverage or usability. This paper presents a project whose ambition is to en- …...

This paper presents a semi-supervised model for generating a table-of-contents as an in- dicative summarization. We mainly focus on using word cluster-based information derived from a large amount of unannotated data by an unsupervised algorithm. We integrate word cluster-based features into a discrimina- tive structured learning model, and show that …...

This paper addresses question analysis in the framework of Question Answering over struc- tured data. The problem is set as a relation extraction task, where all the relations of inter- est in a given domain have to be extracted from natural language questions. The proposed ap- proach applies the notion …...

False friends are pairs of words in two languages that are perceived as similar, but have different meanings, e.g., Gift in German means poison in English. In this paper, we present several un- supervised algorithms for acquiring such pairs from a sentence-aligned bi-text. First, we try dif- ferent ways of …...