Articles

In this paper, we propose a novel way to include unsupervised feature selection meth- ods in probabilistic taxonomy learning mod- els. We leverage on the computation of logistic regression to exploit unsupervised feature se- lection of singular value decomposition (SVD). Experiments show that this way of using SVD for feature …...

In this paper, we present a novel approach for automatic summarization. CBSEAS, the sys- tem implementing this approach, integrates a method to detect redundancy at its very core, in order to produce more expressive summaries than previous approaches. The evaluation of our system during TAC 2008 —the Text Analysis Conference— …...

Discourse theories claim that text gets meaning in context. Most summarization systems do not take advantage of this. They assess the rele- vance of each passage individually rather than modeling the way context affects the relevance of passages. This paper presents a framework for graph-based summarization in order to model …...

This paper explores the influence of text pre- processing techniques on plagiarism detection. We examine stop-word removal, lemmatization, number replacement, synonymy recognition, and word generalization. We also look into the in- fluence of punctuation and word-order within N-grams. All these techniques are evaluated according to their impact on F1-measure and …...

This paper presents a set of experiments performed on parsing the Basque Dependency Treebank. We have concentrated on treebank transformations, maintaining the same basic parsing algorithm across the experiments. The experiments can be classified in two groups: 1) feature optimization, which is important mainly due to the fact that Basque …...

A novel method for unsupervised acquisition of knowledge for taxonomies of concepts from raw Wikipedia text is presented. We assume that the concepts classified under the same node in a taxonomy are described in a comparable way in Wikipedia. The concepts in 6 tax- onomies extracted from WordNet are mapped …...

Feature norms can be regarded as repositories of common sense knowledge for basic level con- cepts. We acquire from very large corpora feature-norm-like concept descriptions using a combination of a weakly supervised method and an unsupervised method. The success in iden- tifying the specific properties listed in the fea- ture …...

The development of the Web 2.0 led to the birth of new textual genres such as blogs, reviews or forum entries. The increasing number of such texts and the highly diverse topics they discuss make blogs a rich source for analysis. This paper presents a comparative study on open domain …...

In this paper we extend a shallow parser [6] with prepositional phrase attachment. Although the PP attachment task is a well-studied task in a discriminative learning context, it is mostly ad- dressed in the context of artificial situations like the quadruple classification task [18] in which only two possible attachment …...

This paper presents a novel approach to au- tomatic captioning of toponym-referenced im- ages. The automatic captioning procedure works by summarizing multiple web-documents that contain information related to an image’s lo- cation. Our summarizer can generate both query-based and language model-biased multi- document summaries. The models are created from large …...

In this paper, we investigate an unsupervised approach to Relation Extraction to be applied in the context of automatic generation of multiple-choice questions (MCQs). The approach aims to identify the most important semantic relations in a document without assigning explicit labels to them in order to ensure broad coverage, unrestricted …...

The Edlin toolkit provides a machine learning framework for linear models, designed to be easy to read and un- derstand. The main goal is to provide easy to edit working examples of im- plementations for popular learning algo- rithms. The toolkit consists of 27 Java classes with a total of …...

In this paper, we introduce our Recognizing Textual Entailment (RTE) system developed on the basis of Lexical Entailment between two text excerpts, namely the hypothesis and the text. To extract atomic parts of hypotheses and texts, we carry out syntactic parsing on the sentences. We then utilize WordNet and FrameNet …...

Despite their prevalence in the English language, multiword expressions like verb-particle constructions (VPCs) are of- ten poorly handled by NLP systems. This problem is partly due to inadequacies in existing corpora; the primary corpus for CCG-oriented work, CCGbank, does not account for VPCs at all, and is inconsis- tent in …...

RWTH participated in the System Combi- nation task of the Fourth Workshop on Sta- tistical Machine Translation (WMT 2009). Hypotheses from 9 German→English MT systems were combined into a consen- sus translation. This consensus transla- tion scored 2.1% better in BLEU and 2.3% better in TER (abs.) than the best …...

In the application of robots in healthcare, where there is a requirement to communicate vocally with non-expert users, a capacity to generate intelligible and expressive speech is needed. The Festival Speech Synthesis System is used as a framework for speech generation on our healthcare robot. Ex- pression is added to …...

The accuracy of named entity recognition sys- tems relies heavily upon the volume and qual- ity of available training data. Improving the process of automatically producing such train- ing data is an important task, as manual ac- quisition is both time consuming and expen- sive. We explore the use of …...

Information Extraction, from the electronic clinical record is a comparatively new topic for computational linguists. In order to utilize the records to improve the efficiency and quality of health care, the knowledge content should be automatically encoded; however this poses a number of challenges for Natural Language Processing (NLP). In …...

Domain-specific terms provide vital se- mantic information for many natural lan- guage processing (NLP) tasks and appli- cations, but remain a largely untapped re- source in the field. In this paper, we pro- pose an unsupervised method to extract domain-specific terms from the Reuters document collection using term frequency and …...

Financial investors trade on the basis of infor- mation, and in particular, on the likelihood that a piece of information will impact the mar- ket. The ability to predict this within millisec- onds of the information being released would be useful in applications such as algorithmic trading. We present a …...