Using a Dialogue Manager to Improve Semantic Web Search

Question Answering systems that resort to the Semantic Web as a knowledge base can go well beyond the usual matching words in documents and, preferably, find a precise answer, without requiring user help to interpret the documents returned. In this paper, the authors introduce a Dialogue Manager that, through the analysis of the question and the type of expected answer, provides accurate answers to the questions posed in Natural Language. The Dialogue Manager not only represents the semantics of the questions, but also represents the structure of the discourse, including the user intentions and the questions context, adding the ability to deal with multiple answers and providing justified answers. The authors’ system performance is evaluated by comparing with similar question answering systems. Although the test suite is slight dimension, the results obtained are very promising.

Knowledge Extraction for Question Titling.

This article describes the work performed over the database of questions belonging to the different opinion polls carried during the last 50 years in Spain. Approximately half of the questions are provided with a title while the other half remain untitled. The work and implemented techniques in order to automatically generate the titles for untitled questions are described. This process is performed over very short texts and generated titles are subject to strong stylistic conventions and should be fully grammatical pieces of Spanish

An authoring tool for decision support systems in context questions of ecological knowledge

Decision support systems (DSS) support business or organizational decision-making activities, which require the access to information that is internally stored in databases or data warehouses, and externally in the Web accessed by Information Retrieval (IR) or Question Answering (QA) systems. Graphical interfaces to query these sources of information ease to constrain dynamically query formulation based on user selections, but they present a lack of flexibility in query formulation, since the expressivity power is reduced to the user interface design. Natural language interfaces (NLI) are expected as the optimal solution. However, especially for non-expert users, a real natural communication is the most difficult to realize effectively. In this paper, we propose an NLI that improves the interaction between the user and the DSS by means of referencing previous questions or their answers (i.e. anaphora such as the pronoun reference in “What traits are affected by them?”), or by eliding parts of the question (i.e. ellipsis such as “And to glume colour?” after the question “Tell me the QTLs related to awn colour in wheat”). Moreover, in order to overcome one of the main problems of NLIs about the difficulty to adapt an NLI to a new domain, our proposal is based on ontologies that are obtained semi-automatically from a framework that allows the integration of internal and external, structured and unstructured information. Therefore, our proposal can interface with databases, data warehouses, QA and IR systems. Because of the high NL ambiguity of the resolution process, our proposal is presented as an authoring tool that helps the user to query efficiently in natural language. Finally, our proposal is tested on a DSS case scenario about Biotechnology and Agriculture, whose knowledge base is the CEREALAB database as internal structured data, and the Web (e.g. PubMed) as external unstructured information.

MixKMeans: Clustering Question-Answer Archives

Community-driven Question Answering (CQA) systems that crowdsource experiential information in the form of questions and answers and have accumulated valuable reusable knowledge. Clustering of QA datasets from CQA systems provides a means of organizing the content to ease tasks such as manual curation and tagging. In this paper, we present a clustering method that exploits the two-part question-answer structure in QA datasets to improve clustering quality. Our method, {\it MixKMeans}, composes question and answer space similarities in a way that the space on which the match is higher is allowed to dominate. This construction is motivated by our observation that semantic similarity between question-answer data (QAs) could get localized in either space. We empirically evaluate our method on a variety of real-world labeled datasets. Our results indicate that our method significantly outperforms state-of-the-art clustering methods for the task of clustering question-answer archives.

Evaluation of complex temporal questions in CLEF-QA

This paper presents the evaluation of a QA system for the treatment of complex temporal questions. The system was implemented in a multilayered architecture where complex temporal questions are first decomposed into simple questions, according to the temporal relations expressed in the original question. These simple questions are then processed independently by our standard Question Answering engine and their respective answers are filtered to satisfy the temporal restrictions of each simple question. The answers to the simple decomposed questions are then combined, according to the temporal relations extracted from the original complex question, to give the final answer. This evaluation was performed as a pilot task in the Spanish QA Track of the Cross Language Evaluation Forum 2004.

A knowledge-based textual entailment approach applied to the QA answer validation at CLEF 2006

The Answer Validation Exercise (AVE) is a pilot track within the Cross-Language Evaluation Forum (CLEF) 2006. The AVE competition provides an evaluation frame- work for answer validations in Question Answering (QA). In our participation in AVE, we propose a system that has been initially used for other task as Recognising Textual Entailment (RTE). The aim of our participation is to evaluate the improvement our system brings to QA. Moreover, due to the fact that these two task (AVE and RTE) have the same main idea, which is to find semantic implications between two fragments of text, our system has been able to be directly applied to the AVE competition. Our system is based on the representation of the texts by means of logic forms and the computation of semantic comparison between them. This comparison is carried out using two different approaches. The first one managed by a deeper study of the Word- Net relations, and the second uses the measure defined by Lin in order to compute the semantic similarity between the logic form predicates. Moreover, we have also designed a voting strategy between our system and the MLEnt system, also presented by the University of Alicante, with the aim of obtaining a joint execution of the two systems developed at the University of Alicante. Although the results obtained have not been very high, we consider that they are quite promising and this supports the fact that there is still a lot of work on researching in any kind of textual entailment.

TEXT-MESS: Intelligent, Interactive and Multilingual Text Mining based on Human Language Technologies, TIN2006-15265-C06

The goal of the project is to analyze, experiment, and develop intelligent, interactive and multilingual Text Mining technologies, as a key element of the next generation of search engines, systems with the capacity to find "the need behind the query". This new generation will provide specialized services and interfaces according to the search domain and type of information needed. Moreover, it will integrate textual search (websites) and multimedia search (images, audio, video), it will be able to find and organize information, rather than generating ranked lists of websites.

Application of Text Summarization techniques to the Geographical Information Retrieval task

Automatic Text Summarization has been shown to be useful for Natural Language Processing tasks such as Question Answering or Text Classification and other related fields of computer science such as Information Retrieval. Since Geographical Information Retrieval can be considered as an extension of the Information Retrieval field, the generation of summaries could be integrated into these systems by acting as an intermediate stage, with the purpose of reducing the document length. In this manner, the access time for information searching will be improved, while at the same time relevant documents will be also retrieved. Therefore, in this paper we propose the generation of two types of summaries (generic and geographical) applying several compression rates in order to evaluate their effectiveness in the Geographical Information Retrieval task. The evaluation has been carried out using GeoCLEF as evaluation framework and following an Information Retrieval perspective without considering the geo-reranking phase commonly used in these systems. Although single-document summarization has not performed well in general, the slight improvements obtained for some types of the proposed summaries, particularly for those based on geographical information, made us believe that the integration of Text Summarization with Geographical Information Retrieval may be beneficial, and consequently, the experimental set-up developed in this research work serves as a basis for further investigations in this field.

Automatic identification of best answers in online enquiry communities

Online communities are prime sources of information. The Web is rich with forums and Question Answering (Q&A) communities where people go to seek answers to all kinds of questions. Most systems employ manual answer-rating procedures to encourage people to provide quality answers and to help users locate the best answers in a given thread. However, in the datasets we collected from three online communities, we found that half their threads lacked best answer markings. This stresses the need for methods to assess the quality of available answers to: 1) provide automated ratings to fill in for, or support, manually assigned ones, and; 2) to assist users when browsing such answers by filtering in potential best answers. In this paper, we collected data from three online communities and converted it to RDF based on the SIOC ontology. We then explored an approach for predicting best answers using a combination of content, user, and thread features. We show how the influence of such features on predicting best answers differs across communities. Further we demonstrate how certain features unique to some of our community systems can boost predictability of best answers.

Cross ontology query answering on the semantic web:an initial evaluation

PowerAqua is a Question Answering system, which takes as input a natural language query and is able to return answers drawn from relevant semantic resources found anywhere on the Semantic Web. In this paper we provide two novel contributions: First, we detail a new component of the system, the Triple Similarity Service, which is able to match queries effectively to triples found in different ontologies on the Semantic Web. Second, we provide a first evaluation of the system, which in addition to providing data about PowerAqua's competence, also gives us important insights into the issues related to using the Semantic Web as the target answer set in Question Answering. In particular, we show that, despite the problems related to the noisy and incomplete conceptualizations, which can be found on the Semantic Web, good results can already be obtained.

PowerAqua:fishing the semantic web

The Semantic Web (SW) offers an opportunity to develop novel, sophisticated forms of question answering (QA). Specifically, the availability of distributed semantic markup on a large scale opens the way to QA systems which can make use of such semantic information to provide precise, formally derived answers to questions. At the same time the distributed, heterogeneous, large-scale nature of the semantic information introduces significant challenges. In this paper we describe the design of a QA system, PowerAqua, designed to exploit semantic markup on the web to provide answers to questions posed in natural language. PowerAqua does not assume that the user has any prior information about the semantic resources. The system takes as input a natural language query, translates it into a set of logical queries, which are then answered by consulting and aggregating information derived from multiple heterogeneous semantic sources.

A question of complexity:measuring the maturity of online enquiry communities

Online enquiry communities such as Question Answering (Q&A) websites allow people to seek answers to all kind of questions. With the growing popularity of such platforms, it is important for community managers to constantly monitor the performance of their communities. Although different metrics have been proposed for tracking the evolution of such communities, maturity, the process in which communities become more topic proficient over time, has been largely ignored despite its potential to help in identifying robust communities. In this paper, we interpret community maturity as the proportion of complex questions in a community at a given time. We use the Server Fault (SF) community, a Question Answering (Q&A) community of system administrators, as our case study and perform analysis on question complexity, the level of expertise required to answer a question. We show that question complexity depends on both the length of involvement and the level of contributions of the users who post questions within their community. We extract features relating to askers, answerers, questions and answers, and analyse which features are strongly correlated with question complexity. Although our findings highlight the difficulty of automatically identifying question complexity, we found that complexity is more influenced by both the topical focus and the length of community involvement of askers. Following the identification of question complexity, we define a measure of maturity and analyse the evolution of different topical communities. Our results show that different topical communities show different maturity patterns. Some communities show a high maturity at the beginning while others exhibit slow maturity rate. Copyright 2013 ACM.

Modelling question selection behaviour in online communities

Value of online Question Answering (QandA) communities is driven by the question-answering behaviour of its members. Finding the questions that members are willing to answer is therefore vital to the effcient operation of such communities. In this paper, we aim to identify the parameters that cor- relate with such behaviours. We train different models and construct effective predictions using various user, question and thread feature sets. We show that answering behaviour can be predicted with a high level of success.

Koherentziazko diskurtso erlazioen detekzio automatikoa patroien bidez, XMLko erlazio-egiturak oinarri hartuta

[EU]Hizkuntzaren prozesamenduan testu koherenteetan kausa taldeko erlazioak (KAUSA, ONDORIOA eta HELBURUA) automatikoki hautematea eta bereiztea erabilgarria da galdera-erantzun automatikoko sistemak eraikitzerako orduan. Horretarako Egitura Erretorikoaren Teoria (Rhetorical Structure Theory, aurrerantzean RST) eta bere erlazioak erabiliko ditugu, corpus bezala RST Treebank -a (Iruskieta et al., 2013) hartuta, zientziako laburpen-testuz osatutako corpusa, hain zuzen ere. Corpus hori XML formatuan deskargatu eta hortik XPATH tresnaren bidez informazio garrantzitsuena eskuratzen dugu. Lan honek 3 helburu nagusi ditu: lehendabizi, kausa taldeko erlazioak elkarren artean bereiztea, bigarrenez, kausa taldeko erlazio hauek beste erlazio guztiekin bereiztea, eta azkenik, EBALUAZIOA eta INTERPRETAZIOA erlazioak bereiztea sentimendu analisian aplikatu ahal izateko. Ataza horiek egiteko, RhetDB tresnarekin eskuratu diren patroi ensaguratsuenak erabili eta bi aplikazio garatu ditugu. Alde batetik, bilatu nahi ditugun patroiak adierazi eta erlazio-egitura duen edonolako testuetan bilaketak egiten dituen bilatzailea, eta bestetik, patroi esanguratsuenak emanda erlazioak etiketatzen dituen etiketatzailea. Bi aplikazio hauek gainera, ahalik eta modu parametrizagarrienean erabiltzeko garatu ditugu, kodea aldatu gabe edonork erabili ahal izateko antzeko atazak egiteko. Etiketatzaileak ebaluatu ondoren, identifikatzeko erlaziorik errazena HELBURUA erlazioa dela ikusi dugu eta KAUSA eta ONDORIOA bereizteko arazo gehiago dauzkagula ere ondorioztatu dugu. Modu berean, EBALUAZIOA eta INTERPRETAZIOA ere elkarren artean bereiz dezakegula ikusi dugu.

Arquitetura para aquisição de respostas a perguntas frequentes

Dissertação de natureza científica realizada para obtenção do grau de Mestre em Engenharia Informática e de Computadores