For the last two years, from 2020 to 2021, COVID-19 has broken disease prevention measures in many countries, including Vietnam, and negatively impacted various aspects of human life and the social community. Besides, the misleading information in the community and fake news about the pandemic are also serious situations. Therefore, we present the first Vietnamese community-based question answering dataset for developing question answering systems for COVID-19 called UIT-ViCoV19QA. The dataset comprises 4,500 question-answer pairs collected from trusted medical sources, with at least one answer and at most four unique paraphrased answers per question. Along with the dataset, we set up various deep learning models as baseline to assess the quality of our dataset and initiate the benchmark results for further research through commonly used metrics such as BLEU, METEOR, and ROUGE-L. We also illustrate the positive effects of having multiple paraphrased answers experimented on these models, especially on Transformer - a dominant architecture in the field of study.

Existing video understanding datasets mostly focus on human interactions, with little attention being paid to the "in the wild" settings, where the videos are recorded outdoors. We propose WILDQA, a video understanding dataset of videos recorded in outside settings. In addition to video question answering (Video QA), we also introduce the new task of identifying visual support for a given question and answer (Video Evidence Selection). Through evaluations using a wide range of baseline models, we show that WILDQA poses new challenges to the vision and language research communities. The dataset is available at https://lit.eecs.umich.edu/wildqa/.

Multi-hop question answering (QA) requires reasoning over multiple documents to answer a complex question and provide interpretable supporting evidence. However, providing supporting evidence is not enough to demonstrate that a model has performed the desired reasoning to reach the correct answer. Most existing multi-hop QA methods fail to answer a large fraction of sub-questions, even if their parent questions are answered correctly. In this paper, we propose the Prompt-based Conservation Learning (PCL) framework for multi-hop QA, which acquires new knowledge from multi-hop QA tasks while conserving old knowledge learned on single-hop QA tasks, mitigating forgetting. Specifically, we first train a model on existing single-hop QA tasks, and then freeze this model and expand it by allocating additional sub-networks for the multi-hop QA task. Moreover, to condition pre-trained language models to stimulate the kind of reasoning required for specific multi-hop questions, we learn soft prompts for the novel sub-networks to perform type-specific reasoning. Experimental results on the HotpotQA benchmark show that PCL is competitive for multi-hop QA and retains good performance on the corresponding single-hop sub-questions, demonstrating the efficacy of PCL in mitigating knowledge loss by forgetting.

Question answering (QA) systems are among the most important and rapidly developing research topics in natural language processing (NLP). A reason, therefore, is that a QA system allows humans to interact more naturally with a machine, e.g., via a virtual assistant or search engine. In the last decades, many QA systems have been proposed to address the requirements of different question-answering tasks. Furthermore, many error scores have been introduced, e.g., based on n-gram matching, word embeddings, or contextual embeddings to measure the performance of a QA system. This survey attempts to provide a systematic overview of the general framework of QA, QA paradigms, benchmark datasets, and assessment techniques for a quantitative evaluation of QA systems. The latter is particularly important because not only is the construction of a QA system complex but also its evaluation. We hypothesize that a reason, therefore, is that the quantitative formalization of human judgment is an open problem.

In the era of loT (Internet of Things) we are surrounded by a plethora of Al enabled devices that can transcribe images, video, audio, and sensors signals into text descriptions. When such transcriptions are captured in activity reports for monitoring, life logging and anomaly detection applications, a user would typically request a summary or ask targeted questions about certain sections of the report they are interested in. Depending on the context and the type of question asked, a question answering (QA) system would need to automatically determine whether the answer covers single-span or multi-span text components. Currently available QA datasets primarily focus on single span responses only (such as SQuAD[4]) or contain a low proportion of examples with multiple span answers (such as DROP[3]). To investigate automatic selection of single/multi-span answers in the use case described, we created a new smart home environment dataset comprised of questions paired with single-span or multi-span answers depending on the question and context queried. In addition, we propose a RoBERTa[6]-based multiple span extraction question answering (MSEQA) model returning the appropriate answer span for a given question. Our experiments show that the proposed model outperforms state-of-the-art QA models on our dataset while providing comparable performance on published individual single/multi-span task datasets.

Today the pre-trained language models achieve great success for question generation (QG) task and significantly outperform traditional sequence-to-sequence approaches. However, the pre-trained models treat the input passage as a flat sequence and are thus not aware of the text structure of input passage. For QG task, we model text structure as answer position and syntactic dependency, and propose answer localness modeling and syntactic mask attention to address these limitations. Specially, we present localness modeling with a Gaussian bias to enable the model to focus on answer-surrounded context, and propose a mask attention mechanism to make the syntactic structure of input passage accessible in question generation process. Experiments on SQuAD dataset show that our proposed two modules improve performance over the strong pre-trained model ProphetNet, and combing them together achieves very competitive results with the state-of-the-art pre-trained model.

Explainability is one of the most pressing concerns in machine learning research and development. Although contemporary large-scale language models (LMs) have demonstrated impressive question-answering capabilities, their inherent opacity can conceal just how these models reach their final answers, making it difficult for users to spot any possible mistakes or justify the outputs. A DeepMind research team addresses this issue in the new paper Faithful Reasoning Using Large Language Models, proposing a forward-chaining selection-inference model that can perform faithful reasoning and provide a valid reasoning trace to improve reasoning quality and help users check and validate the final answers. The proposed approach is based on the idea that LMs can perform faithful multi-step reasoning if the underlying logical structure of a given problem can be mirrored by a causal structure. To realize this, the team developed selection-inference (SI) as their system's backbone, a novel architecture comprising two fine-tuned language models: one for selection and one for inference.

We describe the first steps in the development of an artificial agent focused on the Brazilian maritime territory, a large region within the South Atlantic also known as the Blue Amazon. The "BLue Amazon Brain" (BLAB) integrates a number of services aimed at disseminating information about this region and its importance, functioning as a tool for environmental awareness. The main service provided by BLAB is a conversational facility that deals with complex questions about the Blue Amazon, called BLAB-Chat; its central component is a controller that manages several task-oriented natural language processing modules (e.g., question answering and summarizer systems). These modules have access to an internal data lake as well as to third-party databases. A news reporter (BLAB-Reporter) and a purposely-developed wiki (BLAB-Wiki) are also part of the BLAB service architecture. In this paper, we describe our current version of BLAB's architecture (interface, backend, web services, NLP modules, and resources) and comment on the challenges we have faced so far, such as the lack of training data and the scattered state of domain information. Solving these issues presents a considerable challenge in the development of artificial intelligence for technical domains.

Have you ever wanted to try Question Answering (QA) models but felt restrained because you needed to write some code to set them up? Have you ever wanted to compare QA models, but a Jupyter Notebook is too inconvenient to compare them? Have you ever wanted to use explainability methods such as saliency maps to explain the outputs, but you don't even know where to start? We have been there too! That's why we built SQuARE: Software for Question Answering Research!

This paper presents Macquarie University's participation to the two most recent BioASQ Synergy Tasks (as per June 2022), and to the BioASQ10 Task~B (BioASQ10b), Phase~B. In these tasks, participating systems are expected to generate complex answers to biomedical questions, where the answers may contain more than one sentence. We apply query-focused extractive summarisation techniques. In particular, we follow a sentence classification-based approach that scores each candidate sentence associated to a question, and the $n$ highest-scoring sentences are returned as the answer. The Synergy Task corresponds to an end-to-end system that requires document selection, snippet selection, and finding the final answer, but it has very limited training data. For the Synergy task, we selected the candidate sentences following two phases: document retrieval and snippet retrieval, and the final answer was found by using a DistilBERT/ALBERT classifier that had been trained on the training data of BioASQ9b. Document retrieval was achieved as a standard search over the CORD-19 data using the search API provided by the BioASQ organisers, and snippet retrieval was achieved by re-ranking the sentences of the top retrieved documents, using the cosine similarity of the question and candidate sentence. We observed that vectors represented via sBERT have an edge over tf.idf. BioASQ10b Phase B focuses on finding the specific answers to biomedical questions. For this task, we followed a data-centric approach. We hypothesised that the training data of the first BioASQ years might be biased and we experimented with different subsets of the training data. We observed an improvement of results when the system was trained on the second half of the BioASQ10b training data.