This work is focused on research in machine learning for coreference resolution. Coreference resolution is a natural language processing task that consists of determining the expressions in a discourse that refer to the same entity. The main contributions of this article are (i) a new approach to coreference resolution based on constraint satisfaction, using a hypergraph to represent the problem and solving it by relaxation labeling; and (ii) research towards improving coreference resolution performance using world knowledge extracted from Wikipedia. The developed approach is able to use an entity-mention classification model with more expressiveness than the pair-based ones, and overcome the weaknesses of previous approaches in the state of the art such as linking contradictions, classifications without context, and lack of information evaluating pairs. Furthermore, the approach allows the incorporation of new information by adding constraints, and research has been done in order to use world knowledge to improve performances. RelaxCor, the implementation of the approach, achieved results at the state-of-the-art level, and participated in international competitions: SemEval-2010 and CoNLL-2011. RelaxCor achieved second place in CoNLL-2011.

In this article, we present a factoid question-answering system, Sibyl, specifically tailored for question answering (QA) on spoken-word documents. This work explores, for the first time, which techniques can be robustly adapted from the usual QA on written documents to the more difficult spoken document scenario. More specifically, we study new information retrieval (IR) techniques designed or speech, and utilize several levels of linguistic information for the speech-based QA task. These include named-entity detection with phonetic information, syntactic parsing applied to speech transcripts, and the use of coreference resolution. Sibyl is largely based on supervised machine-learning techniques, with special focus on the answer extraction step, and makes little use of handcrafted knowledge. Consequently, it should be easily adaptable to other domains and languages. Sibyl and all its modules are extensively evaluated on the European Parliament Plenary Sessions English corpus, comparing manual with automatic transcripts obtained by three different automatic speech recognition (ASR) systems that exhibit significantly different word error rates. This data belongs to the CLEF 2009 track for QA on speech transcripts. The main results confirm that syntactic information is very useful for learning to rank question candidates, improving results on both manual and automatic transcripts, unless the ASR quality is very low. At the same time, our experiments on coreference resolution reveal that the state-of-the-art technology is not mature enough to be effectively exploited for QA with spoken documents. Overall, the performance of Sibyl is comparable or better than the state-of-the-art on this corpus, confirming the validity of our approach.

This paper presents our experiments in question answering for speech corpora. These experiments focus on improving the answer extraction step of the QA process. We present two approaches to answer extraction in question answering for speech corpora that apply machine learning to improve the coverage and precision of the extraction. The first one is a reranker that uses only lexical information, the second one uses dependency parsing to score robust similarity between syntactic structures. Our experimental results show that the proposed learning models improve our previous results using only hand-made ranking rules with small syntactic information. Moreover, this results show also that a dependency parser can be useful for speech transcripts even if it was trained with written text data from a\nnews collection. We evaluate the system on manual transcripts of speech from EPPS English corpus and a set of questions transcribed from spontaneous oral questions. This data belongs to the CLEF 2009 track on QA on speech transcripts (QAst).

The goal of Information Extraction is to automatically generate structured pieces of information from the relevant information contained in text documents. Machine Learning techniques have been applied to reduce the cost of Information Extraction system adaptation. However, elements of human supervision strongly bias the learning process. Unsupervised learning approaches can avoid these biases. In this paper, we propose an unsupervised approach to learning for Relation Detection, based on the use of massive clustering ensembles. The results obtained on the ACE Relation Mention Detection task outperform in terms of F1 score by 5 points the state of the art of unsupervised techniques for this evaluation framework, in addition to being simpler and more flexible.

Proper recognition and handling of temporal information contained in a text is key to understanding the flow of events depicted in the text and their accompanying circumstances. Consequently, time expression recognition and representation of the time information they convey in a suitable normalized form is an important task relevant to several problems in Natural Language Processing. In particular, such an analysis is largely significant for Information Extraction (IE), Question Answering (QA) and Automatic Summarization (AS). The most common approach to time expression recognition in the past has been the use of handmade extraction rules (grammars), which also served as the basis for normalization. Our aim is to explore the possibilities afforded by applying machine learning techniques to the recognition of time expressions. We focus on recognizing the appearances of time expressions in text (not normalization) and transform the problem into one of chunking, where the aim is to correctly assign Begin, Inside or Outside (BIO) tags to tokens. In this paper, we explain the knowledge representation used and compare the results obtained in our experiments with two different methods, one statistical (support vector machines) and one of rule induction (FOIL). Our empirical analysis shows that SVMs are superior.

This paper presents an unsupervised method for clustering spontaneous speech documents. The approach uses a hierarchical algorithm to automatically determine the number of clusters and a starting model for a subsequent iterative algorithm. We have evaluated this method on the Switchboard corpus and compared it to a set of supervised and other unsupervised methods. The results show that our method significantly outperforms the rest of the approaches. 1.

This paper presents an analysis of named entity recognition and classification in spontaneous speech transcripts. We annotated a significant fraction of the Switchboard corpus with six named entity classes and investigated a battery of machine learning models that include lexical, syntactic, and semantic attributes. The best recognition and classification model obtains promis-ing results, approaching within 5 % a system evaluated on clean textual data. 1.

We propose a hybrid, unsupervised document clustering approach that combines a hierarchical clustering algorithm with Expectation Maximization. We developed several heuristics to automatically select a subset of the clusters generated by the first algorithm as the initial points of the second one. Furthermore, our initialization algorithm generates not only an initial model for the iterative refinement algorithm but also an estimate of the model dimension, thus eliminating another important element of human supervision. We have evaluated the proposed system on five real-world document collections. The results show that our approach generates clustering solutions of higher quality than both its individual components.

The growing availability of textual sources has lead to an increase in the use of automatic knowledge acquisition approaches from textual data, as in Information Extraction (IE). Most IE systems use knowledge explicitly represented as sets of IE rules usually manually acquired. Recently, however, the acquisition of this knowledge has been faced by applying a huge variety of Machine Learning (ML) techniques. Within this framework, new problems arise in relation to the way of selecting and annotating positive examples, and sometimes negative ones, in supervised approaches, or the way of organizing unsupervised or semi-supervised approaches. This paper presents a new IE-rule learning system that deals with these training set problems and describes a set of experiments for testing this capability of the new learning approach.