No description available.

Data labelling for question answering tasks (QA) is a costly procedure that requires oracles to read lengthy excerpts of texts and reason to extract an answer for a given question from within the text. QA is a task in natural language processing (NLP), where a majority of recent advancements have come from leveraging the vast corpora of unlabelled and unstructured text available online. This work aims to extend this trend in the efficient use of unlabelled text data to the problem of selecting which subset of samples to label in order to maximize performance. This practice of selective labelling is called active learning (AL).  Recent developments in AL for NLP have introduced the use of self-supervised learning on large corpora of text in the labelling process of samples for classification problems. This work adapts this research to the task of question answering and performs an initial exploration of expected performance.  The methods covered in this work use uncertainty estimates obtained from neural networks to guide an incremental labelling process. These estimates are obtained from transformer-based models, previously trained in a self-supervised manner, by calculating the entropy of the confidence scores or with an approximation of Bayesian uncertainty obtained through Monte Carlo dropout. These methods are evaluated on two different benchmarking QA datasets: SQuAD v1 and TriviaQA.  Several factors are observed to influence the behaviour of these uncertainty-based acquisition functions, including the choice of language model used, the presence of unanswered questions and the acquisition size used in the incremental process. The study produces no evidence to support that averaging or selecting maximal uncertainty values between the classification of an answer’s starting and ending positions affects sample acquisition quality. However, language model choice, the presence of unanswerable questions and acquisition size are all identified as key factors affecting consistency between runs and degree of success.

In recent years, deep learning based sequence modeling (neural sequence modeling) techniques have made substantial progress in many tasks, including information retrieval, question answering, information extraction, machine translation, etc. Benefiting from the highly scalable attention-based Transformer architecture and enormous open access online data, large-scale pre-trained language models have shown great modeling and generalization capacity for sequential data. However, not all domains benefit equally from the rapid development of neural sequence modeling. Domains like healthcare and software engineering have vast amounts of sequential data containing rich knowledge, yet remain under-explored due to a number of challenges: 1) the distribution of the sequences in specific domains is different from the general domain; 2) the effective comprehension of domain-specific data usually relies on domain knowledge; and 3) the labelled data is usually scarce and expensive to get in domain-specific settings. In this thesis, we focus on the research problem of applying neural sequence modeling methods to address both common and domain-specific challenges from the healthcare and software engineering domains. We systematically investigate neural-based machine learning approaches to address the above challenges in three research directions: 1) learning with long sequences, 2) learning from domain knowledge and 3) learning under limited supervision. Our work can also potentially benefit more domains with large amounts of sequential data. / Doctor of Philosophy / In the last few years, computer programs that learn and understand human languages (an area called machine learning for natural language processing) have significantly improved. These advances are visible in various areas such as retrieving information, answering questions, extracting key details from texts, and translating between languages. A key to these successes has been the use of a type of neural network structure known as a "Transformer", which can process and learn from lots of information found online. However, these successes are not uniform across all areas. Two fields, healthcare and software engineering, still present unique challenges despite having a wealth of information. Some of these challenges include the different types of information in these fields, the need for specific expertise to understand this information, and the shortage of labeled data, which is crucial for training machine learning models. In this thesis, we focus on the use of machine learning for natural language processing methods to solve these challenges in the healthcare and software engineering fields. Our research investigates learning with long documents, learning from domain-specific expertise, and learning when there's a shortage of labeled data. The insights and techniques from our work could potentially be applied to other fields that also have a lot of sequential data.

[pt] Perguntas e Respostas (Question Answering - QA) é um campo de estudo dedicado à construção de sistemas que respondem automaticamente a perguntas feitas em linguagem natural. A tradução de uma pergunta feita em linguagem natural em uma consulta estruturada (SQL ou SPARQL) em um banco de dados também é conhecida como Interface de Linguagem Natural para Bancos de Dados (Natural Language Interface to Database - NLIDB). Os sistemas NLIDB geralmente não lidam com agregações, que podem ter os seguintes elementos: funções de agregação (como contagem, soma, média, mínimo e máximo), uma cláusula de agrupamento (GROUP BY) e uma cláusula HAVING. No entanto, eles fornecem bons resultados para consultas normais. Esta dissertação aborda a criação de um módulo genérico, para ser utilizado em sistemas NLIDB, que permite a tais sistemas realizar consultas com agregações, desde que os resultados da consulta que o NLIDB retorna sejam, ou possam ser transformados, em um resultado no formato tabular. O trabalho cobre agregações com especificidades como ambiguidades, diferenças de escala de tempo, agregações em atributos múltiplos, o uso de adjetivos superlativos, reconhecimento básico de unidade de medida, agregações em atributos com nomes compostos e subconsultas com funções de agregação aninhadas em até dois níveis. / [en] Question Answering (QA) is a field of study dedicated to building systems that automatically answer questions asked in natural language. The translation of a question asked in natural language into a structured query (SQL or SPARQL) in a database is also known as Natural Language Interface to Database (NLIDB). NLIDB systems usually do not deal with aggregations, which can have the following elements: aggregation functions (as count, sum, average, minimum and maximum), a grouping clause (GROUP BY) and a having clause (HAVING). However, they deliver good results for normal queries. This dissertation addresses the creation of a generic module, to be used in NLIDB systems, that allows such systems to perform queries with aggregations, on the condition that the query results the NLIDB return are, or can be transformed into, a result set in the form of a table. The work covers aggregations with specificities such as ambiguities, timescale differences, aggregations in multiple attributes, the use of superlative adjectives, basic unit measure recognition, aggregations in attributes with compound names and subqueries with aggregation functions nested up to two levels.

No description available.

No description available.

[Background]: The advent of bidirectional encoder representation from trans- formers (BERT) language models (Devlin et al., 2018) and MS Marco, a large scale human-annotated dataset for machine reading comprehension (Bajaj et al., 2016) that made publicly available, led the field of information retrieval (IR) to experience a revolution (Lin et al., 2020). The retrieval model based on BERT of Nogueira and Cho (2019), by the time they published their paper, became the top entry in the MS Marco passage-reranking leaderboard, surpassing the previous state of the art by 27% in MRR@10. However, training such neural IR models for different domains than MS Marco is still hard because neural approaches often require a vast amount of training data to perform effectively, which is not always available. To address the problem of the shortage of labelled data a new line of research emerged, training neural models with weak supervision. In weak supervision, given an unlabelled dataset labels are generated automatically using an existing model and then a machine learning model is trained upon the artificial “weak“ data. In case of weak supervision for IR, the training dataset comes in the form of a tuple (query, passage). Dehghani et al. (2017) in their work used the AOL query logs (Pass et al., 2006), which is a set of millions of real web queries, and BM25 to retrieve the relevant passages for each of the user queries. A drawback with this approach is that it is hard to obtain query logs for every single different domain. [Objective]: This thesis proposes an intuitive approach for addressing the shortage of data in domains with limited or no data at all through transfer learning in the context of IR. We leverage Wikipedia’s structure for creating a Wikipedia-based generic IR training dataset for zero-shot neural models. [Method]: We create the “pseudo-queries“ by concatenating the titles of Wikipedia’s articles along with each of their title sections and we consider the associated section’s passage as the relevant passage of the pseudo-queries. All of our experiments are evaluated on a standard collection: MS Marco, which is a large scale web collection. For our zero-shot experiments, our proposed model, called “Wiki“, is a BERT model trained on the artificial Wikipedia-based dataset and the baseline is a default BERT model without any additional training. In our second line of experiments, we explore the benefits gained by pre-fine- tuning on the Wikipedia-based IR dataset and further fine-tuning on in-domain data. Our proposed model, "Wiki+Ma", is a BERT model pre-fine-tuned in the Wikipedia-based dataset and further fine-tuned in MS Marco, while the baseline is a BERT model fine-tuned only in MS Marco. [Results]: Results regarding our first experiments show that our BERT model trained on the Wikipedia-based IR dataset, called "Wiki", achieves a performance of 0.197 in MRR@10, which is about +10 points more in comparison to a BERT model with default weights; in addition, results in the development set indicate that the “Wiki“ model performs better than BERT model trained on in-domain data when the data is between 10k-50k instances. Results regarding our second line of experiments show that pre-fine-tuning on the Wikipedia-based IR dataset benefits later fine-tuning steps on in-domain data in terms of stability. [Conclusion]: Our findings suggest that transfer learning for IR tasks by leveraging the generic knowledge incorporated in Wikipedia is possible, though more experimentation is needed to understand its limitations in comparison with the traditional approaches such as the BM25.

No description available.

Northvolt is a Swedish battery manufacturing company that specializes in the production of sustainable lithium-ion batteries for electric vehicles and energy storage systems. Established in 2016, the company has experienced significant growth in recent years. This growth has presented a major challenge for the IT Support team, as they face a substantial volume of ITrelated inquiries. To address this challenge and allow the IT Support team to concentrate on more complex support tasks, a question-answering chatbot has been implemented as part of this thesis project. The chatbot has been developed using the Microsoft Bot Framework and leverages Microsoft cloud services, specifically Azure Cognitive Services, to provide intelligent and cognitive capabilities for answering employee questions directly within Microsoft Teams. The chatbot has undergone testing by a diverse group of employees from various teams within the organization and was evaluated based on three key metrics: effectiveness (including accuracy, precision, and intent recognition rate), efficiency (including response time and scalability), and satisfaction. The test results indicate that the accuracy, precision, and intent recognition rate fall below the required thresholds for production readiness. However, these metrics can be improved by expanding the knowledge base of the bot. The chatbot demonstrates impressive efficiency in terms of response time and scalability, and its user-friendly nature contributes to a positive user experience. Users express high levels of satisfaction with their interactions with the bot, and the majority would recommend it to their colleagues, recognizing it as a valuable service solution that will benefit all employees at Northvolt in the future. Moving forward, the primary focus should be on expanding the knowledge base and effectively communicating the bot’s purpose and scope to enhance effectiveness and satisfaction. Additionally, integrating the bot with advanced AI features, such as OpenAI’s language models available within Microsoft’s ecosystem, would elevate the bot to the next level.

No description available.