Related papers: Science Question Answering using Instructional Mat…
Bridging the semantic gap between image and question is an important step to improve the accuracy of the Visual Question Answering (VQA) task. However, most of the existing VQA methods focus on attention mechanisms or visual relations for…
Materials science literature contains millions of materials synthesis procedures described in unstructured natural language text. Large-scale analysis of these synthesis procedures would facilitate deeper scientific understanding of…
This study aims at improving the performance of scoring student responses in science education automatically. BERT-based language models have shown significant superiority over traditional NLP models in various language-related tasks.…
Misleading or false information has been creating chaos in some places around the world. To mitigate this issue, many researchers have proposed automated fact-checking methods to fight the spread of fake news. However, most methods cannot…
In conversational question answering, users express their information needs through a series of utterances with incomplete context. Typical ConvQA methods rely on a single source (a knowledge base (KB), or a text corpus, or a set of…
Most learners fail to develop deep text comprehension when reading textbooks passively. Posing questions about what learners have read is a well-established way of fostering their text comprehension. However, many textbooks lack…
Open-domain question answering (QA) is an important problem in AI and NLP that is emerging as a bellwether for progress on the generalizability of AI methods and techniques. Much of the progress in open-domain QA systems has been realized…
This paper proposes a new problem of complementary evidence identification for open-domain question answering (QA). The problem aims to efficiently find a small set of passages that covers full evidence from multiple aspects as to answer a…
In this work, our aim is to provide a structured answer in natural language to a complex information need. Particularly, we envision using generative models from the perspective of data-to-text generation. We propose the use of a content…
Mathematical learning environments give domain-specific and immediate feedback to students solving a mathematical exercise. Based on a language for specifying strategies, we have developed a feedback framework that automatically calculates…
With the interactivity and multiple representation features, computer simulations lend itself to the guided inquiry learning. However, these simulations are usually designed for post-elementary students. Thus, the aim of this study is to…
This research investigate that science process skills significantly improve after doing some practicum activities. The research population are fifth semester physics education students and the research sample are fifth semester physics…
This paper addresses the generation of explanations with visual examples. Given an input sample, we build a system that not only classifies it to a specific category, but also outputs linguistic explanations and a set of visual examples…
Scientific knowledge discovery increasingly relies on large language models, yet many existing scholarly assistants depend on proprietary systems with tens or hundreds of billions of parameters. Such reliance limits reproducibility and…
One of the major challenges of an educational system is choosing appropriate content considering pupils' age and intellectual potential. In this article the experiment of primary school grades (from 1st to 4th grades) is considered for…
It is a mystery which input features contribute to a neural network's output. Various explanation (feature attribution) methods are proposed in the literature to shed light on the problem. One peculiar observation is that these explanations…
The need for discovering knowledge from XML documents according to both structure and content features has become challenging, due to the increase in application contexts for which handling both structure and content information in XML data…
We introduce an algebraic framework for interacting quantum systems that enables studying complex phenomena, characterized by the coexistence and competition of various broken symmetry states of matter. The approach unveils the hidden unity…
The rapid evolution of intelligent electronic devices makes information technology, computer science and electronics strongly related to the teaching of natural sciences. Today almost everybody has a smart phone that can convert light,…
Summarizing content contributed by individuals can be challenging, because people make different lexical choices even when describing the same events. However, there remains a significant need to summarize such content. Examples include the…