Predicting answering behaviour in online question answering communities

The value of Question Answering (Q&A) communities is dependent on members of the community finding the questions they are most willing and able to answer. This can be difficult in communities with a high volume of questions. Much previous has work attempted to address this problem by recommending questions similar to those already answered. However, this approach disregards the question selection behaviour of the answers and how it is affected by factors such as question recency and reputation. In this paper, we identify the parameters that correlate with such a behaviour by analysing the users' answering patterns in a Q&A community. We then generate a model to predict which question a user is most likely to answer next. We train Learning to Rank (LTR) models to predict question selections using various user, question and thread feature sets. We show that answering behaviour can be predicted with a high level of success, and highlight the particular features that inuence users' question selections.

Domain-specific question answering system : an application to the construction sector

Mémoire numérisé par la Direction des bibliothèques de l'Université de Montréal.

Domain-specific question answering system : an application to the construction sector

Mémoire numérisé par la Direction des bibliothèques de l'Université de Montréal.

Edge-aware Graph Attention Networks: Joint Reasoning On Text and Knowledge Graphs for Biomedical Question Answering

Much of the real-world dataset, including textual data, can be represented using graph structures. The use of graphs to represent textual data has many advantages, mainly related to maintaining a more significant amount of information, such as the relationships between words and their types. In recent years, many neural network architectures have been proposed to deal with tasks on graphs. Many of them consider only node features, ignoring or not giving the proper relevance to relationships between them. However, in many node classification tasks, they play a fundamental role. This thesis aims to analyze the main GNNs, evaluate their advantages and disadvantages, propose an innovative solution considered as an extension of GAT, and apply them to a case study in the biomedical field. We propose the reference GNNs, implemented with methodologies later analyzed, and then applied to a question answering system in the biomedical field as a replacement for the pre-existing GNN. We attempt to obtain better results by using models that can accept as input both node and edge features. As shown later, our proposed models can beat the original solution and define the state-of-the-art for the task under analysis.

Bio-QA-GNN: Reasoning with Language Models and Knowledge Graphs for Interpretable Biomedical Question Answering

Nowadays the idea of injecting world or domain-specific structured knowledge into pre-trained language models (PLMs) is becoming an increasingly popular approach for solving problems such as biases, hallucinations, huge architectural sizes, and explainability lack—critical for real-world natural language processing applications in sensitive fields like bioinformatics. One recent work that has garnered much attention in Neuro-symbolic AI is QA-GNN, an end-to-end model for multiple-choice open-domain question answering (MCOQA) tasks via interpretable text-graph reasoning. Unlike previous publications, QA-GNN mutually informs PLMs and graph neural networks (GNNs) on top of relevant facts retrieved from knowledge graphs (KGs). However, taking a more holistic view, existing PLM+KG contributions mainly consider commonsense benchmarks and ignore or shallowly analyze performances on biomedical datasets. This thesis start from a propose of a deep investigation of QA-GNN for biomedicine, comparing existing or brand-new PLMs, KGs, edge-aware GNNs, preprocessing techniques, and initialization strategies. By combining the insights emerged in DISI's research, we introduce Bio-QA-GNN that include a KG. Working with this part has led to an improvement in state-of-the-art of MCOQA model on biomedical/clinical text, largely outperforming the original one (+3.63\% accuracy on MedQA). Our findings also contribute to a better understanding of the explanation degree allowed by joint text-graph reasoning architectures and their effectiveness on different medical subjects and reasoning types. Codes, models, datasets, and demos to reproduce the results are freely available at: \url{https://github.com/disi-unibo-nlp/bio-qagnn}.

iMap : um mecanismo de inferência para mapas conceituais

Mapas Conceituais são representações gráficas do conhecimento de uma pessoa num dado momento e área de conhecimento. Por sua natureza investigativa, são utilizados como ferramentas de apoio em abordagens pedagógicas que objetivam promover a aprendizagem significativa. No entanto, o processo de avaliação de um mapa tende a ser custoso pois acarreta uma pesada carga de processamento cognitivo por parte do avaliador, já que este precisa mapear os conceitos e relações em busca de nuances de conhecimento alí presentes. Essa pesquisa tem por objetivo aumentar o nível de abstração nas interações entre o avaliador e os mapas conceituais fornecendo uma camada intermediária de inteligência computacional que favoreça a comunicação por meio de perguntas e respostas em linguagem natural, fornecendo ao avaliador ferramentas que lhe permita examinar o conteúdo do mapa conceitual sem exigir deste o mapeamento visual dos conceitos e relações presentes nos mapas avaliados. Uma ferramenta é prototipada e uma prova de conceito apresentada. A análise da arquitetura proposta permitiu definir uma arquitetura final com características que permitem potencializar o uso de mapas conceituais e facilitar diversas operações pedagógicas com estes. Essa pesquisa situa-se na área de investigação de sistemas de perguntas e resposta, aplicando técnicas de processamento de linguagem natural para análise da pergunta e interpretação do mapa conceitual e aplica técnica de inteligência artificial para inferir respostas às perguntas.

Intranets documentales

Resumen de la sesión organizada por Socadi (Sociedad Catalana de Documentación e Información) a finales de enero pasado en Barcelona sobre intranets, o sea, sobre los sistemas que aplican la tecnología web para gestionar información, documentación y comunicación en una organización.

Knowing What to Respond in the Future Does Not Cancel the Influence of Past Events

Everyday tasks seldom involve isolate actions but sequences of them. We can see whether previous actions influence the current one by exploring the response time to controlled sequences of stimuli. Specifically, depending on the response-stimulus temporal interval (RSI), different mechanisms have been proposed to explain sequential effects in two-choice serial response tasks. Whereas an automatic facilitation mechanism is thought to produce a benefit for response repetitions at short RSIs, subjective expectancies are considered to replace the automatic facilitation at longer RSIs, producing a cost-benefit pattern: repetitions are faster after other repetitions but they are slower after alternations. However, there is not direct evidence showing the impact of subjective expectancies on sequential effects. By using a fixed sequence, the results of the reported experiment showed that the repetition effect was enhanced in participants who acquired complete knowledge of the order. Nevertheless, a similar cost-benefit pattern was observed in all participants and in all learning blocks. Therefore, results of the experiment suggest that sequential effects, including the cost-benefit pattern, are the consequence of automatic mechanisms which operate independently of (and simultaneously with) explicit knowledge of the sequence or other subjective expectancies.

The Semantics and Typology of Yes/No Particles (A Cross-Linguistic Study)

Taking the three basic systems of Yes/No particles the group looked at the relative deep and surface structures, and asked what types of systems are present in the Georgian, Polish and Armenian languages. The choice of languages was of particular interest as the Caucasian and Indo-European languages usually have different question-answering systems, but Georgian (Caucasian) and Polish (Indo-European) in fact share the same system. The Armenian language is Indo-European, but the country is situated in the southern Caucasus, on Georgia's southern border, making it worth analysing Armenian in comparison with Georgian (from the point of view of language interference) and with Polish (as two relative languages). The group identified two different deep structures, tracing the occurrence of these in different languages, and showed that one is more natural in the majority of languages. They found no correspondence between relative languages and their question-answer systems and demonstrated that languages in the same typological class may show different systems, as with Georgian and the North Caucasian languages. It became clear that Georgian, Armenian and Polish all have an agree/disagree question-answering system defined by the same deep structure. From this they conclude that the lingual mentalities of Georgians, Armenians and Poles are more oriented to the communicative act. At the same time the Yes/No system, in which a positive particle stands for a positive answer and a negative particle for a negative answer, also functions in these languages, indicating that the second deep structure identified also functions alongside the first.

Event ordering through temporal expression resolution

In this paper a multilingual method for event ordering based on temporal expression resolution is presented. This method has been implemented through the TERSEO system which consists of three main units: temporal expression recognizing, resolution of the coreference introduced by these expressions, and event ordering. By means of this system, chronological information related to events can be extracted from documental databases. This information is automatically added to the documental database in order to allow its use by question answering systems in those cases referring to temporality. The system has been evaluated obtaining results of 91 % precision and 71 % recall. For this, a blind evaluation process has been developed guaranteing a reliable annotation process that was measured through the kappa factor.

Creación automática de sistemas de búsqueda de respuestas en dominios restringidos

Los sistemas de búsqueda de respuestas (BR) se pueden considerar como potenciales sucesores de los buscadores tradicionales de información en la Web. Para que sean precisos deben adaptarse a dominios concretos mediante el uso de recursos semánticos adecuados. La adaptación no es una tarea trivial, ya que deben integrarse e incorporarse a sistemas de BR existentes varios recursos heterogéneos relacionados con un dominio restringido. Se presenta la herramienta Maraqa, cuya novedad radica en el uso de técnicas de ingeniería del software, como el desarrollo dirigido por modelos, para automatizar dicho proceso de adaptación a dominios restringidos. Se ha evaluado Maraqa mediante una serie de experimentos (sobre el dominio agrícola) que demuestran su viabilidad, mejorando en un 29,5% la precisión del sistema adaptado.

Aplicaciones de procesamiento de lenguaje natural

El campo de procesamiento de lenguaje natural (PLN), ha tenido un gran crecimiento en los últimos años; sus áreas de investigación incluyen: recuperación y extracción de información, minería de datos, traducción automática, sistemas de búsquedas de respuestas, generación de resúmenes automáticos, análisis de sentimientos, entre otras. En este artículo se presentan conceptos y algunas herramientas con el fin de contribuir al entendimiento del procesamiento de texto con técnicas de PLN, con el propósito de extraer información relevante que pueda ser usada en un gran rango de aplicaciones. Se pueden desarrollar clasificadores automáticos que permitan categorizar documentos y recomendar etiquetas; estos clasificadores deben ser independientes de la plataforma, fácilmente personalizables para poder ser integrados en diferentes proyectos y que sean capaces de aprender a partir de ejemplos. En el presente artículo se introducen estos algoritmos de clasificación, se analizan algunas herramientas de código abierto disponibles actualmente para llevar a cabo estas tareas y se comparan diversas implementaciones utilizando la métrica F en la evaluación de los clasificadores.

The use of computers in literature searching and related reference activities in libraries : papers presented at the 1975 Clinic on Library Applications of Data Processing, April 27-30, 1975 /

Includes bibliographical references.

Statistical dialog management for health interventions

Research endeavors on spoken dialogue systems in the 1990s and 2000s have led to the deployment of commercial spoken dialogue systems (SDS) in microdomains such as customer service automation, reservation/booking and question answering systems. Recent research in SDS has been focused on the development of applications in different domains (e.g. virtual counseling, personal coaches, social companions) which requires more sophistication than the previous generation of commercial SDS. The focus of this research project is the delivery of behavior change interventions based on the brief intervention counseling style via spoken dialogue systems. ^ Brief interventions (BI) are evidence-based, short, well structured, one-on-one counseling sessions. Many challenges are involved in delivering BIs to people in need, such as finding the time to administer them in busy doctors' offices, obtaining the extra training that helps staff become comfortable providing these interventions, and managing the cost of delivering the interventions. Fortunately, recent developments in spoken dialogue systems make the development of systems that can deliver brief interventions possible. ^ The overall objective of this research is to develop a data-driven, adaptable dialogue system for brief interventions for problematic drinking behavior, based on reinforcement learning methods. The implications of this research project includes, but are not limited to, assessing the feasibility of delivering structured brief health interventions with a data-driven spoken dialogue system. Furthermore, while the experimental system focuses on harmful alcohol drinking as a target behavior in this project, the produced knowledge and experience may also lead to implementation of similarly structured health interventions and assessments other than the alcohol domain (e.g. obesity, drug use, lack of exercise), using statistical machine learning approaches. ^ In addition to designing a dialog system, the semantic and emotional meanings of user utterances have high impact on interaction. To perform domain specific reasoning and recognize concepts in user utterances, a named-entity recognizer and an ontology are designed and evaluated. To understand affective information conveyed through text, lexicons and sentiment analysis module are developed and tested.^

Statistical Dialog Management for Health Interventions

Research endeavors on spoken dialogue systems in the 1990s and 2000s have led to the deployment of commercial spoken dialogue systems (SDS) in microdomains such as customer service automation, reservation/booking and question answering systems. Recent research in SDS has been focused on the development of applications in different domains (e.g. virtual counseling, personal coaches, social companions) which requires more sophistication than the previous generation of commercial SDS. The focus of this research project is the delivery of behavior change interventions based on the brief intervention counseling style via spoken dialogue systems. Brief interventions (BI) are evidence-based, short, well structured, one-on-one counseling sessions. Many challenges are involved in delivering BIs to people in need, such as finding the time to administer them in busy doctors' offices, obtaining the extra training that helps staff become comfortable providing these interventions, and managing the cost of delivering the interventions. Fortunately, recent developments in spoken dialogue systems make the development of systems that can deliver brief interventions possible. The overall objective of this research is to develop a data-driven, adaptable dialogue system for brief interventions for problematic drinking behavior, based on reinforcement learning methods. The implications of this research project includes, but are not limited to, assessing the feasibility of delivering structured brief health interventions with a data-driven spoken dialogue system. Furthermore, while the experimental system focuses on harmful alcohol drinking as a target behavior in this project, the produced knowledge and experience may also lead to implementation of similarly structured health interventions and assessments other than the alcohol domain (e.g. obesity, drug use, lack of exercise), using statistical machine learning approaches. In addition to designing a dialog system, the semantic and emotional meanings of user utterances have high impact on interaction. To perform domain specific reasoning and recognize concepts in user utterances, a named-entity recognizer and an ontology are designed and evaluated. To understand affective information conveyed through text, lexicons and sentiment analysis module are developed and tested.