Rozprawy doktorskie na temat „Extractive Question-Answering”

The amount of data available and consumed by people globally is growing. To reduce mental fatigue and increase the general ability to gain insight into complex texts or documents, we have developed an application to aid in this task. The application allows users to upload documents and ask domain-specific questions about them using our web application. A summarized version of each document is presented to the user, which could further facilitate their understanding of the document and guide them towards what types of questions could be relevant to ask. Our application allows users flexibility with the types of documents that can be processed, it is publicly available, stores no user data, and uses state-of-the-art models for its summaries and answers. The result is an application that yields near human-level intuition for answering questions in certain isolated cases, such as Wikipedia and news articles, as well as some scientific texts. The application shows a decrease in reliability and its prediction as to the complexity of the subject, the number of words in the document, and grammatical inconsistency in the questions increases. These are all aspects that can be improved further if used in production.
Mängden data som är tillgänglig och konsumeras av människor växer globalt. För att minska den mentala trötthet och öka den allmänna förmågan att få insikt i komplexa, massiva texter eller dokument, har vi utvecklat en applikation för att bistå i de uppgifterna. Applikationen tillåter användare att ladda upp dokument och fråga kontextspecifika frågor via vår webbapplikation. En sammanfattad version av varje dokument presenteras till användaren, vilket kan ytterligare förenkla förståelsen av ett dokument och vägleda dem mot vad som kan vara relevanta frågor att ställa. Vår applikation ger användare möjligheten att behandla olika typer av dokument, är tillgänglig för alla, sparar ingen personlig data, och använder de senaste modellerna inom språkbehandling för dess sammanfattningar och svar. Resultatet är en applikation som når en nära mänsklig intuition för vissa domäner och frågor, som exempelvis Wikipedia- och nyhetsartiklar, samt viss vetensaplig text. Noterade undantag för tillämpningen härrör från ämnets komplexitet, grammatiska korrekthet för frågorna och dokumentets längd. Dessa är områden som kan förbättras ytterligare om den används i produktionen.

Since the proposal of hypertext by Tim Berners-Lee to his employer CERN on March 12, 1989 the World Wide Web has grown to more than one billion Web pages and still grows. With the later proposed Semantic Web vision,Berners-Lee et al. suggested an extension of the existing (Document) Web to allow better reuse, sharing and understanding of data. Both the Document Web and the Web of Data (which is the current implementation of the Semantic Web) grow continuously. This is a mixed blessing, as the two forms of the Web grow concurrently and most commonly contain different pieces of information. Modern information systems must thus bridge a Semantic Gap to allow a holistic and unified access to information about a particular information independent of the representation of the data. One way to bridge the gap between the two forms of the Web is the extraction of structured data, i.e., RDF, from the growing amount of unstructured and semi-structured information (e.g., tables and XML) on the Document Web. Note, that unstructured data stands for any type of textual information like news, blogs or tweets. While extracting structured data from unstructured data allows the development of powerful information system, it requires high-quality and scalable knowledge extraction frameworks to lead to useful results. The dire need for such approaches has led to the development of a multitude of annotation frameworks and tools. However, most of these approaches are not evaluated on the same datasets or using the same measures. The resulting Evaluation Gap needs to be tackled by a concise evaluation framework to foster fine-grained and uniform evaluations of annotation tools and frameworks over any knowledge bases. Moreover, with the constant growth of data and the ongoing decentralization of knowledge, intuitive ways for non-experts to access the generated data are required. Humans adapted their search behavior to current Web data by access paradigms such as keyword search so as to retrieve high-quality results. Hence, most Web users only expect Web documents in return. However, humans think and most commonly express their information needs in their natural language rather than using keyword phrases. Answering complex information needs often requires the combination of knowledge from various, differently structured data sources. Thus, we observe an Information Gap between natural-language questions and current keyword-based search paradigms, which in addition do not make use of the available structured and unstructured data sources. Question Answering (QA) systems provide an easy and efficient way to bridge this gap by allowing to query data via natural language, thus reducing (1) a possible loss of precision and (2) potential loss of time while reformulating the search intention to transform it into a machine-readable way. Furthermore, QA systems enable answering natural language queries with concise results instead of links to verbose Web documents. Additionally, they allow as well as encourage the access to and the combination of knowledge from heterogeneous knowledge bases (KBs) within one answer. Consequently, three main research gaps are considered and addressed in this work: First, addressing the Semantic Gap between the unstructured Document Web and the Semantic Gap requires the development of scalable and accurate approaches for the extraction of structured data in RDF. This research challenge is addressed by several approaches within this thesis. This thesis presents CETUS, an approach for recognizing entity types to populate RDF KBs. Furthermore, our knowledge base-agnostic disambiguation framework AGDISTIS can efficiently detect the correct URIs for a given set of named entities. Additionally, we introduce REX, a Web-scale framework for RDF extraction from semi-structured (i.e., templated) websites which makes use of the semantics of the reference knowledge based to check the extracted data. The ongoing research on closing the Semantic Gap has already yielded a large number of annotation tools and frameworks. However, these approaches are currently still hard to compare since the published evaluation results are calculated on diverse datasets and evaluated based on different measures. On the other hand, the issue of comparability of results is not to be regarded as being intrinsic to the annotation task. Indeed, it is now well established that scientists spend between 60% and 80% of their time preparing data for experiments. Data preparation being such a tedious problem in the annotation domain is mostly due to the different formats of the gold standards as well as the different data representations across reference datasets. We tackle the resulting Evaluation Gap in two ways: First, we introduce a collection of three novel datasets, dubbed N3, to leverage the possibility of optimizing NER and NED algorithms via Linked Data and to ensure a maximal interoperability to overcome the need for corpus-specific parsers. Second, we present GERBIL, an evaluation framework for semantic entity annotation. The rationale behind our framework is to provide developers, end users and researchers with easy-to-use interfaces that allow for the agile, fine-grained and uniform evaluation of annotation tools and frameworks on multiple datasets. The decentral architecture behind the Web has led to pieces of information being distributed across data sources with varying structure. Moreover, the increasing the demand for natural-language interfaces as depicted by current mobile applications requires systems to deeply understand the underlying user information need. In conclusion, the natural language interface for asking questions requires a hybrid approach to data usage, i.e., simultaneously performing a search on full-texts and semantic knowledge bases. To close the Information Gap, this thesis presents HAWK, a novel entity search approach developed for hybrid QA based on combining structured RDF and unstructured full-text data sources.

Question answering (QA) stands squarely along the path from document retrieval to text understanding. As an area of research interest, it serves as a proving ground where strategies for document processing, knowledge representation, question analysis, and answer extraction may be evaluated in real world information extraction contexts. The task is to go beyond the representation of text documents as "bags of words" or data blobs that can be scanned for keyword combinations and word collocations in the manner of internet search engines. Instead, the goal is to recognize and extract the semantic content of the text, and to organize it in a manner that supports reasoning about the concepts represented. The issue presented is how to obtain and query such a structure without either a predefined set of concepts or a predefined set of relationships among concepts. This research investigates a means for acquiring from text documents both the underlying concepts and their interrelationships. Specifically, a syntax-based formalism for representing atomic propositions that are extracted from text documents is presented, together with a method for constructing a network of concept nodes for indexing such logical forms based on the discourse entities they contain. It is shown that meaningful questions can be decomposed into Boolean combinations of question patterns using the same formalism, with free variables representing the desired answers. It is further shown that this formalism can be used for robust question answering using the concept network and WordNet synonym, hypernym, hyponym, and antonym relationships. This formalism was implemented in the Semantic Extractor (SEMEX) research tool and was tested against the factoid questions from the 2005 Text Retrieval Conference (TREC), which operated upon the AQUAINT corpus of newswire documents. After adjusting for the limitations of the tool and the document set, correct answers were found for approximately fifty percent of the questions analyzed, which compares favorably with other question answering systems.
Ph.D.
School of Computer Science
Engineering and Computer Science
Computer Science

Nowadays, the effective management of information is extremely important for all spheres of our lives and applications such as search engines and question answering systems help users to find the information that they need. However, even when assisted by these various applications, people sometimes struggle to find what they want. For example, when choosing a product customers can be confused by the need to consider many features before they can reach a decision. Interactive question answering (IQA) systems can help customers in this process, by answering questions about products and initiating a dialogue with the customers when their needs are not clearly defined. The focus of this thesis is how to design an interactive question answering system that will assist users in choosing a product they are looking for, in an optimal way, when a large number of similar products are available. Such an IQA system will be based on selecting a set of characteristics (also referred to as product features in this thesis), that describe the relevant product, and narrowing the search space. We believe that the order in which these characteristics are presented in terms of these IQA sessions is of high importance. Therefore, they need to be ranked in order to have a dialogue which selects the product in an efficient manner. The research question investigated in this thesis is whether product characteristics mentioned in user reviews are important for a person who is likely to purchase a product and can therefore be used when designing an IQA system. We focus our attention on products such as mobile phones; however, the proposed techniques can be adapted for other types of products if the data is available. Methods from natural language processing (NLP) fields such as coreference resolution, relation extraction and opinion mining are combined to produce various rankings of phone features. The research presented in this thesis employs two corpora which contain texts related to mobile phones specifically collected for this thesis: a corpus of Wikipedia articles about mobile phones and a corpus of mobile phone reviews published on the Epinions.com website. Parts of these corpora were manually annotated with coreference relations, mobile phone features and relations between mentions of the phone and its features. The annotation is used to develop a coreference resolution module as well as a machine learning-based relation extractor. Rule-based methods for identification of coreference chains describing the phone are designed and thoroughly evaluated against the annotated gold standard. Machine learning is used to find links between mentions of the phone (identified by coreference resolution) and phone features. It determines whether some phone feature belong to the phone mentioned in the same sentence or not. In order to find the best rankings, this thesis investigates several settings. One of the hypotheses tested here is that the relatively low results of the proposed baseline are caused by noise introduced by sentences which are not directly related to the phone and phone feature. To test this hypothesis, only sentences which contained mentions of the mobile phone and a phone feature linked to it were processed to produce rankings of the phones features. Selection of the relevant sentences is based on the results of coreference resolution and relation extraction. Another hypothesis is that opinionated sentences are a good source for ranking the phone features. In order to investigate this, a sentiment classification system is also employed to distinguish between features mentioned in positive and negative contexts. The detailed evaluation and error analysis of the methods proposed form an important part of this research and ensure that the results provided in this thesis are reliable.

Nos ambientes médico e de saúde, especificamente no tratamento clínico do paciente, o papel da informação descrita nos prontuários médicos é registrar o estado de saúde do paciente e auxiliar os profissionais diretamente ligados ao tratamento. A investigação dessas informações de estado clínico em pesquisas científicas na área de biomedicina podem suportar o desenvolvimento de padrões de prevenção e tratamento de enfermidades. Porém, ler artigos científicos é uma tarefa que exige tempo e disposição, uma vez que realizar buscas por informações específicas não é uma tarefa simples e a área médica e de saúde está em constante atualização. Além disso, os profissionais desta área, em sua grande maioria, possuem uma rotina estressante, trabalhando em diversos empregos e atendendo muitos pacientes em um único dia. O objetivo deste projeto é o desenvolvimento de um Framework de Question Answering (QA) para suportar o desenvolvimento de sistemas de QA, que auxiliem profissionais da área da saúde na busca rápida por informações, especificamente, em epigenética e doenças crônicas. Durante o processo de construção do framework, estão sendo utilizados dois frameworks desenvolvidos anteriormente pelo grupo de pesquisa da mestranda: o SisViDAS e o FREDS, além de desenvolver os demais módulos de processamento de pergunta e de respostas. O QASF foi avaliado por meio de uma coleção de referências e medidas estatísticas de desempenho e os resultados apontam valores de precisão em torno de 0.7 quando a revocação era 0.3, para ambos o número de artigos recuperados e analisados eram 200. Levando em consideração que as perguntas inseridas no QASF são longas, com 70 termos por pergunta em média, e complexas, o QASF apresentou resultados satisfatórios. Este projeto pretende contribuir na diminuição do tempo gasto por profissionais da saúde na busca por informações de interesse, uma vez que sistemas de QA fornecem respostas diretas e precisas sobre uma pergunta feita pelo usuário
The medical record describes health conditions of patients helping experts to make decisions about the treatment. The biomedical scientific knowledge can improve the prevention and the treatment of diseases. However, the search for relevant knowledge may be a hard task because it is necessary time and the healthcare research is constantly updating. Many healthcare professionals have a stressful routine, because they work in different hospitals or medical offices, taking care many patients per day. The goal of this project is to design a Question Answering Framework to support faster and more precise searches for information in epigenetic, chronic disease and thyroid images. To develop the proposal, we are reusing two frameworks that have already developed: SisViDAS and FREDS. These two frameworks are being exploited to compose a document processing module. The other modules (question and answer processing) are being completely developed. The QASF was evaluated by a reference collection and performance measures. The results show 0.7 of precision and 0.3 of recall for two hundred articles retrieved. Considering that the questions inserted on the framework have an average of seventy terms, the QASF shows good results. This project intends to decrease search time once QA systems provide straight and precise answers in a process started by a user question in natural language

This project focuses on a system that answers questions formulated in natural language. Firstly, the report discusses problems associated with question answering systems and some commonly employed approaches. Emphasis is laid on shallow methods, which do not require many linguistic resources. The second part describes our work on a system that answers factoid questions, utilizing Czech Wikipedia as a source of information. Answer extraction is partly based on specific features of Wikipedia and partly on pre-defined patterns. Results show that for answering simple questions, the system provides significant improvements in comparison with a standard search engine.

In this work we present a system for information extraction from Learning Management Systems. This system is ontology-based. It retrieves information according to the structure of the ontology to populate the ontology. We graphically present statistics about the ontology data. These statistics present latent knowledge which is difficult to see in the traditional Learning Management System. To answer questions about the ontology, a question answering system was developed using Natural Language Processing in the conversion of the natural language question into an ontology query language; Sumário: Extração de Informação de Sistemas de Gestão para Educação Usando Ontologias Neste dissertação apresentamos um sistema de extracção de informação de sistemas de gestão para educação (Learning Management Systems). Este sistema é baseado em ontologias e extrai informação de acordo com a estrutura da ontologia para a popular. Também permite apresentar graficamente algumas estatísticas sobre os dados da ontologia. Estas estatísticas revelam o conhecimento latente que é difícil de ver num sistema tradicional de gestão para a educação. Para poder responder a perguntas sobre os dados da ontologia, um sistema de resposta automática a perguntas em língua natural foi desenvolvido usando Processamento de Língua Natural para converter as perguntas para linguagem de interrogação de ontologias.

La recherche de réponses précises à des questions formulées en langue naturelle renouvelle le champ de la recherche d'information. De nombreux travaux ont eu lieu sur la recherche de réponses à des questions factuelles en domaine ouvert. Moins de travaux ont porté sur la recherche de réponses en domaine de spécialité, en particulier dans le domaine médical ou biomédical. Plusieurs conditions différentes sont rencontrées en domaine de spécialité comme les lexiques et terminologies spécialisés, les types particuliers de questions, entités et relations du domaine ou les caractéristiques des documents ciblés. Dans une première partie, nous étudions les méthodes permettant d'analyser sémantiquement les questions posées par l'utilisateur ainsi que les textes utilisés pour trouver les réponses. Pour ce faire nous utilisons des méthodes hybrides pour deux tâches principales : (i) la reconnaissance des entités médicales et (ii) l'extraction de relations sémantiques. Ces méthodes combinent des règles et patrons construits manuellement, des connaissances du domaine et des techniques d'apprentissage statistique utilisant différents classifieurs. Ces méthodes hybrides, expérimentées sur différents corpus, permettent de pallier les inconvénients des deux types de méthodes d'extraction d'information, à savoir le manque de couverture potentiel des méthodes à base de règles et la dépendance aux données annotées des méthodes statistiques. Dans une seconde partie, nous étudions l'apport des technologies du web sémantique pour la portabilité et l'expressivité des systèmes de questions-réponses. Dans le cadre de notre approche, nous exploitons les technologies du web sémantique pour annoter les informations extraites en premier lieu et pour interroger sémantiquement ces annotations en second lieu. Enfin, nous présentons notre système de questions-réponses, appelé MEANS, qui utilise à la fois des techniques de TAL, des connaissances du domaine et les technologies du web sémantique pour répondre automatiquement aux questions médicales.

abstract: While in recent years deep learning (DL) based approaches have been the popular approach in developing end-to-end question answering (QA) systems, such systems lack several desired properties, such as the ability to do sophisticated reasoning with knowledge, the ability to learn using less resources and interpretability. In this thesis, I explore solutions that aim to address these drawbacks. Towards this goal, I work with a specific family of reading comprehension tasks, normally referred to as the Non-Extractive Reading Comprehension (NRC), where the given passage does not contain enough information and to correctly answer sophisticated reasoning and ``additional knowledge" is required. I have organized the NRC tasks into three categories. Here I present my solutions to the first two categories and some preliminary results on the third category. Category 1 NRC tasks refer to the scenarios where the required ``additional knowledge" is missing but there exists a decent natural language parser. For these tasks, I learn the missing ``additional knowledge" with the help of the parser and a novel inductive logic programming. The learned knowledge is then used to answer new questions. Experiments on three NRC tasks show that this approach along with providing an interpretable solution achieves better or comparable accuracy to that of the state-of-the-art DL based approaches. The category 2 NRC tasks refer to the alternate scenario where the ``additional knowledge" is available but no natural language parser works well for the sentences of the target domain. To deal with these tasks, I present a novel hybrid reasoning approach which combines symbolic and natural language inference (neural reasoning) and ultimately allows symbolic modules to reason over raw text without requiring any translation. Experiments on two NRC tasks shows its effectiveness. The category 3 neither provide the ``missing knowledge" and nor a good parser. This thesis does not provide an interpretable solution for this category but some preliminary results and analysis of a pure DL based approach. Nonetheless, the thesis shows beyond the world of pure DL based approaches, there are tools that can offer interpretable solutions for challenging tasks without using much resource and possibly with better accuracy.
Dissertation/Thesis
Doctoral Dissertation Computer Science 2019

Since the proposal of hypertext by Tim Berners-Lee to his employer CERN on March 12, 1989 the World Wide Web has grown to more than one billion Web pages and still grows. With the later proposed Semantic Web vision,Berners-Lee et al. suggested an extension of the existing (Document) Web to allow better reuse, sharing and understanding of data. Both the Document Web and the Web of Data (which is the current implementation of the Semantic Web) grow continuously. This is a mixed blessing, as the two forms of the Web grow concurrently and most commonly contain different pieces of information. Modern information systems must thus bridge a Semantic Gap to allow a holistic and unified access to information about a particular information independent of the representation of the data. One way to bridge the gap between the two forms of the Web is the extraction of structured data, i.e., RDF, from the growing amount of unstructured and semi-structured information (e.g., tables and XML) on the Document Web. Note, that unstructured data stands for any type of textual information like news, blogs or tweets. While extracting structured data from unstructured data allows the development of powerful information system, it requires high-quality and scalable knowledge extraction frameworks to lead to useful results. The dire need for such approaches has led to the development of a multitude of annotation frameworks and tools. However, most of these approaches are not evaluated on the same datasets or using the same measures. The resulting Evaluation Gap needs to be tackled by a concise evaluation framework to foster fine-grained and uniform evaluations of annotation tools and frameworks over any knowledge bases. Moreover, with the constant growth of data and the ongoing decentralization of knowledge, intuitive ways for non-experts to access the generated data are required. Humans adapted their search behavior to current Web data by access paradigms such as keyword search so as to retrieve high-quality results. Hence, most Web users only expect Web documents in return. However, humans think and most commonly express their information needs in their natural language rather than using keyword phrases. Answering complex information needs often requires the combination of knowledge from various, differently structured data sources. Thus, we observe an Information Gap between natural-language questions and current keyword-based search paradigms, which in addition do not make use of the available structured and unstructured data sources. Question Answering (QA) systems provide an easy and efficient way to bridge this gap by allowing to query data via natural language, thus reducing (1) a possible loss of precision and (2) potential loss of time while reformulating the search intention to transform it into a machine-readable way. Furthermore, QA systems enable answering natural language queries with concise results instead of links to verbose Web documents. Additionally, they allow as well as encourage the access to and the combination of knowledge from heterogeneous knowledge bases (KBs) within one answer. Consequently, three main research gaps are considered and addressed in this work: First, addressing the Semantic Gap between the unstructured Document Web and the Semantic Gap requires the development of scalable and accurate approaches for the extraction of structured data in RDF. This research challenge is addressed by several approaches within this thesis. This thesis presents CETUS, an approach for recognizing entity types to populate RDF KBs. Furthermore, our knowledge base-agnostic disambiguation framework AGDISTIS can efficiently detect the correct URIs for a given set of named entities. Additionally, we introduce REX, a Web-scale framework for RDF extraction from semi-structured (i.e., templated) websites which makes use of the semantics of the reference knowledge based to check the extracted data. The ongoing research on closing the Semantic Gap has already yielded a large number of annotation tools and frameworks. However, these approaches are currently still hard to compare since the published evaluation results are calculated on diverse datasets and evaluated based on different measures. On the other hand, the issue of comparability of results is not to be regarded as being intrinsic to the annotation task. Indeed, it is now well established that scientists spend between 60% and 80% of their time preparing data for experiments. Data preparation being such a tedious problem in the annotation domain is mostly due to the different formats of the gold standards as well as the different data representations across reference datasets. We tackle the resulting Evaluation Gap in two ways: First, we introduce a collection of three novel datasets, dubbed N3, to leverage the possibility of optimizing NER and NED algorithms via Linked Data and to ensure a maximal interoperability to overcome the need for corpus-specific parsers. Second, we present GERBIL, an evaluation framework for semantic entity annotation. The rationale behind our framework is to provide developers, end users and researchers with easy-to-use interfaces that allow for the agile, fine-grained and uniform evaluation of annotation tools and frameworks on multiple datasets. The decentral architecture behind the Web has led to pieces of information being distributed across data sources with varying structure. Moreover, the increasing the demand for natural-language interfaces as depicted by current mobile applications requires systems to deeply understand the underlying user information need. In conclusion, the natural language interface for asking questions requires a hybrid approach to data usage, i.e., simultaneously performing a search on full-texts and semantic knowledge bases. To close the Information Gap, this thesis presents HAWK, a novel entity search approach developed for hybrid QA based on combining structured RDF and unstructured full-text data sources.

博士
元智大學
資訊工程學系
92
Traditional Chinese text retrieval systems return a ranked list of documents in response to a user’s request. While a ranked list of documents can be an appropriate response for the user, frequently it is not. Usually it would be better for the system to provide the answer itself instead of requiring the user to search for the answer in a set of documents. Since Chinese text retrieval has just been developed lately, and due to various specific characteristics of Chinese language, the approaches of its retrieval are quite different from those studies and researches proposed to deal with Western language. Thus, we proposed a document characterization model- EAVR, to solve the Chinese text retrieval problem. In the EAVR conceptual model, an information index structure that satisfies the requirements of information retrieval or information extraction is established during context analysis stage. Besides, the new type of concept tree allows document characteristics schema to be reorganized and reconstructed with the concept tree. We also developed an architecture that augments existing search engines so that they support Chinese natural language question answering. In this dissertation we describe a new approach to build Chinese question answering system, which we believe to be the first general-purpose, fully-automated Chinese question-answering system available on the web. In our approach, we attempt to represent Chinese text by its characteristics, and try to convert the Chinese text into ERE (E: entity， R: relation) relation data lists, and then, to answer the question through ERE relation model. Our system performs quite well in addition to the simplicity of the techniques being utilized. Experimental results show that question answering accuracy can be greatly improved by analyzing more and more matching ERE relation data lists. Simple ERE relation data extraction techniques work well in our system making it efficient to use with many backend retrieval engines.