Borja Navarro

UA-ZBSA: A Headline Emotion Classification through Web Information

This paper presents a headline emotion classification approach based on frequency and co-occurrence information collected from the World Wide Web. The content words of a headline (nouns, verbs, adverbs and adjectives) are extracted in order to form different bag of word pairs with the joy, disgust, fear, anger, sadness and surprise emotions. For each pair, we compute the Mutual Information Score which is obtained from the web occurrences of an emotion and the content words. Our approach is based on the hypothesis that group of words which co-occur together across many documents with a given emotion are highly probable to express the same emotion.

Corpus-based semantic role approach in information retrieval

In this paper, a method to determine the semantic role for the constituents of a sentence is presented. This method, named SemRol, is a corpus-based approach that uses two different statistical models, conditional Maximum Entropy (ME) Probability Models and the TiMBL program, a Memory-based Learning. It consists of three phases that make use of features using words, lemmas, PoS tags and shallow parsing information. Our method introduces a new phase in the Semantic Role Labeling task which has usually been approached as a two phase procedure consisting of recognition and labeling arguments. From our point of view, firstly the sense of the verbs in the sentences must be disambiguated. That is why depending on the sense of the verb a different set of roles must be considered. Regarding the labeling arguments phase, a tuning procedure is presented. As a result of this procedure one of the best sets of features for the labeling arguments task is detected. With this set, that is different for TiMBL and ME, precisions of 76.71% for TiMBL or 70.55% for ME, are obtained. Furthermore, the semantic role information provided by our SemRol method could be used as an extension of Information Retrieval or Question Answering systems. We propose using this semantic information as an extension of an Information Retrieval system in order to reduce the number of documents or passages retrieved by the system.

Spanish all-words semantic class disambiguation using Cast3LB corpus

In this paper, an approach to semantic disambiguation based on machine learning and semantic classes for Spanish is presented. A critical issue in a corpus-based approach for Word Sense Disambiguation (WSD) is the lack of wide-coverage resources to automatically learn the linguistic information. In particular, all-words sense annotated corpora such as SemCor do not have enough examples for many senses when used in a machine learning method. Using semantic classes instead of senses allows to collect a larger number of examples for each class while polysemy is reduced, improving the accuracy of semantic disambiguation. Cast3LB, a SemCor-like corpus, manually annotated with Spanish WordNet 1.5 senses, has been used in this paper to perform semantic disambiguation based on several sets of classes: lexicographer files of WordNet, WordNet Domains, and SUMO ontology.

GPLSIUA: Combining Temporal Information and Topic Modeling for Cross-Document Event Ordering

Building unified timelines from a collection of written news articles requires cross-document event coreference resolution and temporal relation extraction. In this paper we present an approach event coreference resolution according to: a) similar temporal information, and b) similar semantic arguments. Temporal information is detected using an automatic temporal information system (TIPSem), while semantic information is represented by means of LDA Topic Modeling. The evaluation of our approach shows that it obtains the highest Micro-average F-score results in the SemEval2015 Task 4: “TimeLine: Cross-Document Event Ordering” (25.36% for TrackB, 23.15% for SubtrackB), with an improvement of up to 6% in comparison to the other systems. However, our experiment also showed some drawbacks in the Topic Modeling approach that degrades performance of the system.

Syntax-motivated context windows of morpho-lexical features for recognizing time and event expressions in natural language

We present an analysis of morpho-lexical features to learn SVM models for recognizing TimeML time and event expressions. We evaluate over the TempEval-2 data, the features: word, lemma, and PoS in isolation, in different size static-context windows, and in a syntax-motivated dynamic-context windows defined in this paper. The results show that word, lemma, and PoS introduce complementary advantages and their combination achieves the best performance; this performance is improved using context, and, with dynamic-context, timex recognition is improved to reach state-of-art performance. Although more complex approaches improve the efficacy, the morpho-lexical features can be obtained more efficiently and show a reasonable efficacy.

Semantic annotation of a natural language corpus for knowledge extraction

Knowledge management (ontologies development, disambiguation of words, semantic web, etc.) must extract knowledge from somewhere. The main source of knowledge are natural language texts, in which humans express how they view and conceptualize the world. However, the automatic extraction of knowledge from texts is not a trivial task. In this paper we present a semantic annotated corpus as a source for knowledge extraction. Semantic is the bridge between linguistic input and knowledge (concepts, real world). A corpus with semantic information annotated is a useful resource to extract knowledge from a real context: it is a semi-structured database that offers deep information about human knowledge, concepts and relations between them.

“How much context do you need?”: an experiment about the context size in interactive cross-language question answering

The main topic of this paper is the context size needed for an efficient Interactive Cross-language Question Answering system. We compare two approaches: the first one (baseline system) shows the user whole passages (maximum context: 10 sentences). The second one (experimental system) shows only a clause (minimum context). As cross-language system, the main problem is that the language of the question (Spanish) and the language of the answer context (English) are different. The results show that large context is better. However, there are specific relations between the context size and the knowledge about the language of the answer: users with poor level of English prefer context with few words.

Time-Surfer: time-based graphical access to document content

This demonstration presents a novel interactive graphical interface to document content focusing on the time dimension. The objective of Time-Surfer is to let users search and explore information related to a specific period, event, or event participant within a document. The system is based on the automatic detection not only of time expressions, but also of events and temporal relations. Through a zoomable timeline interface, it brings users an dynamic picture of the temporal distribution of events within a document. Time-Surfer has been successfully applied to history and biographical articles from Wikipedia.

Temporal expression identification based on semantic roles

Following TimeML (TIMEX3) specifications, we present a study analyzing to what extent are semantic roles useful in temporal expression identification task, as well as, a list of the potential applications of this combination. For that purpose, two approaches of a temporal expression identification system based on semantic roles have been developed: (1) Baseline and (2) TIPSem-Full. The first approach is a direct conversion from a temporal semantic role to a temporal expression. The second one processes and converts all temporal roles into correct TIMEX3, using a set of transformation rules defined in this paper. These two approaches have been evaluated using TimeBank corpus. The evaluation results confirm that the application of semantic roles to temporal expression identification task can be valuable, obtaining, for TIPSem-Full, an 73.4% in F1 for relaxed span and a 65.9% in F1 for strict span.

Using semantic roles in information retrieval systems

It is well known that Information Retrieval Systems based entirely on syntactic contents have serious limitations. In order to achieve high precision Information Retrieval Systems the incorporation of Natural Language Processing techniques that provide semantic information is needed. For this reason, in this paper a method to determine the semantic role for the constituents of a sentence is presented. The goal of this is to integrate this method in an Information Retrieval System.