One of the emerging research trends in natural language understanding is machine reading comprehension (MRC) which is the task to find answers to human questions based on textual data. Existing Vietnamese datasets for MRC research concentrate solely on answerable questions. However, in reality, questions can be unanswerable for which the correct answer is not stated in the given textual data. To address the weakness, we provide the research community with a benchmark dataset named UIT-ViQuAD 2.0 for evaluating the MRC task and question answering systems for the Vietnamese language. We use UIT-ViQuAD 2.0 as a benchmark dataset for the challenge on Vietnamese MRC at the Eighth Workshop on Vietnamese Language and Speech Processing (VLSP 2021). This task attracted 77 participant teams from 34 universities and other organizations. In this article, we present details of the organization of the challenge, an overview of the methods employed by shared-task participants, and the results. The highest performances are 77.24% in F1-score and 67.43% in Exact Match on the private test set. The Vietnamese MRC systems proposed by the top 3 teams use XLM-RoBERTa, a powerful pre-trained language model based on the transformer architecture. The UIT-ViQuAD 2.0 dataset motivates researchers to further explore the Vietnamese machine reading comprehension task and related tasks such as question answering, question generation, and natural language inference.

Memorization of the relation between entities in a dataset can lead to privacy issues when using a trained model for question answering. We introduce Relational Memorization (RM) to understand, quantify and control this phenomenon. While bounding general memorization can have detrimental effects on the performance of a trained model, bounding RM does not prevent effective learning. The difference is most pronounced when the data distribution is long-tailed, with many queries having only few training examples: Impeding general memorization prevents effective learning, while impeding only relational memorization still allows learning general properties of the underlying concepts. We formalize the notion of Relational Privacy (RP) and, inspired by Differential Privacy (DP), we provide a possible definition of Differential Relational Privacy (DrP). These notions can be used to describe and compute bounds on the amount of RM in a trained model. We illustrate Relational Privacy concepts in experiments with large-scale models for Question Answering.

Next time your power stays on during a severe weather event, you may have a machine learning model to thank. Researchers at the MIT-IBM Watson AI Lab are using artificial intelligence to solve power grid failures. The manager of the MIT-IBM Watson AI Lab, Jie Chen, and his colleagues have developed a machine learning model that works to analyze data collected from hundreds of thousands of sensors located across the U.S. power grid. The sensors, components of what is known as synchrophasor technology, compile vast amounts of real-time data related to electric current and voltage in order to monitor the health of the grid and locate anomalies that could cause outages. Synchrophasor analysis requires intensive computational resources due to the size and real-time nature of the data streams the sensors produce.

Subsequent time your energy stays on throughout a extreme climate occasion, you could have a machine studying mannequin to thank. Researchers on the MIT-IBM Watson AI Lab are utilizing synthetic intelligence to resolve energy grid failures. The supervisor of the MIT-IBM Watson AI Lab, Jie Chen, and his colleagues have developed a machine studying mannequin that works to investigate knowledge collected from tons of of 1000's of sensors situated throughout the U.S. energy grid. The sensors, parts of what's referred to as synchrophasor expertise, compile huge quantities of real-time knowledge associated to electrical present and voltage in an effort to monitor the well being of the grid and find anomalies that would trigger outages. Synchrophasor evaluation requires intensive computational sources as a result of dimension and real-time nature of the info streams the sensors produce.

Next time your power stays on during a severe weather event, you may have a machine learning model to thank. Researchers at the MIT-IBM Watson AI Lab are using artificial intelligence to solve power grid failures. The manager of the MIT-IBM Watson AI Lab, Jie Chen, and his colleagues have developed a machine learning model that works to analyze data collected from hundreds of thousands of sensors located across the U.S. power grid. The sensors, components of what is known as synchrophasor technology, compile vast amounts of real-time data related to electric current and voltage in order to monitor the health of the grid and locate anomalies that could cause outages. Synchrophasor analysis requires intensive computational resources due to the size and real-time nature of the data streams the sensors produce.

We consider entailment problems involving powerful constraint languages such as frontier-guarded existential rules in which we impose additional semantic restrictions on a set of distinguished relations. We consider restricting a relation to be transitive, restricting a relation to be the transitive closure of another relation, and restricting a relation to be a linear order. We give some natural variants of guardedness that allow inference to be decidable in each case, and isolate the complexity of the corresponding decision problems. Finally we show that slight changes in these conditions lead to undecidability.

We investigate practical algorithms for inconsistency-tolerant query answering over prioritized knowledge bases, which consist of a logical theory, a set of facts, and a priority relation between conflicting facts. We consider three well-known semantics (AR, IAR and brave) based upon two notions of optimal repairs (Pareto and completion). Deciding whether a query answer holds under these semantics is (co)NP-complete in data complexity for a large class of logical theories, and SAT-based procedures have been devised for repair-based semantics when there is no priority relation, or the relation has a special structure. The present paper introduces the first SAT encodings for Pareto- and completion-optimal repairs w.r.t. general priority relations and proposes several ways of employing existing and new encodings to compute answers under (optimal) repair-based semantics, by exploiting different reasoning modes of SAT solvers. The comprehensive experimental evaluation of our implementation compares both (i) the impact of adopting semantics based on different kinds of repairs, and (ii) the relative performances of alternative procedures for the same semantics.

Multi-hop question generation (MQG) aims to generate complex questions which require reasoning over multiple pieces of information of the input passage. Most existing work on MQG has focused on exploring graph-based networks to equip the traditional Sequence-to-sequence framework with reasoning ability. However, these models do not take full advantage of the constraint between questions and answers. Furthermore, studies on multi-hop question answering (QA) suggest that Transformers can replace the graph structure for multi-hop reasoning. Therefore, in this work, we propose a novel framework, QA4QG, a QA-augmented BART-based framework for MQG. It augments the standard BART model with an additional multi-hop QA module to further constrain the generated question. Our results on the HotpotQA dataset show that QA4QG outperforms all state-of-the-art models, with an increase of 8 BLEU-4 and 8 ROUGE points compared to the best results previously reported. Our work suggests the advantage of introducing pre-trained language models and QA module for the MQG task.

It includes 80,000 questions along with their answers, with 25% of the questions being adversarially unanswerable. We examine various properties of the dataset to show the diversity and the level of its difficulty as a MRC benchmark. By releasing this dataset, we aim to ease research on Persian reading comprehension and development of persian question answering systems. Our experiments on different state-of-the-art pre-trained contextualized language models shows 74.8% Exact Match (EM) and 87.6% F1-score that can be used as the baseline results for further research on Persian QA.

「IBM Watson Assistant」を搭載した人工知能（AI）ベースの新しいバーチャルアシスタントがTD Securitiesの貴金属事業のデジタルストアで利用可能になっている。