Science Question Answering using Instructional Materials

By Mrinmaya Sachan, Kumar Avinava Dubey, Eric P. Xing. 2016

25 citations recorded by the source corpus.

We provide a solution for elementary science test using instructional materials. We posit that there is a hidden structure that explains the correctness of an answer given the question and instructional materials and present a unified max-margin framework that learns to find these hidden structures (given a corpus of question-answer pairs and instructional materials), and uses what it learns to answer novel elementary science questions. Our evaluation shows that our framework outperforms several strong baselines.

Subfields: Natural Language Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Natural Language Processing

Citations in the corpus

Improving Question Answering with External Knowledge (2019, background): “, 2018) or existing external general knowledge graphs (Li and Clark, 2015; Sachan et al., 2016; Wang et al., 2018a,c; Zhong et al., 2018; Musa et al., 2018) such as ConceptNet (Speer et al.”
Crowdsourcing Multiple Choice Science Questions (2017, methodology): “The method described by Li and Clark (2015) evaluates the coherence of a scene constructed from the question enriched with background KB information, while Sachan et al. (2016) train an entailment model that derives the correct answer from background knowledge aligned with a max-margin ranker.”
Batch Policy Gradient Methods for Improving Neural Conversation Models (2017, methodology): “Besides chatbots, this framework also ﬁnds applications in tasks such as question answering (Fer-rucci et al., 2010; Hermann et al., 2015; Sachan et al., 2016), generating image descriptions (Karpa-thy & Fei-Fei, 2015) and machine translation (Bahdanau et al., 2014) where a human labeller can…”
Self-Training for Jointly Learning to Ask and Answer Questions (2018, background): “Various approaches (Sachan et al., 2015; Wang et al., 2015; Sachan and Xing, 2016b; Sachan et al., 2016; Narasimhan and Barzilay, 2015) have been proposed for solving this task.”
Easy Questions First? A Case Study on Curriculum Learning for Question Answering (2016, methodology): “Here, ψ ( h, z ) is a task-dependent feature map (see Sachan et al. (2015) and Sachan et al. (2016) for details).”
From Textbooks to Knowledge: A Case Study in Harvesting Axiomatic Knowledge from Textbooks to Solve Geometry Problems (2017, background): “…tests such as reading comprehensions (Richardson et al., 2013; Sachan et al., 2015, inter alia), science question answering (Schoenick et al., 2016; Sachan et al., 2016, inter alia), algebra word problems (Kushman et al., 2014, inter alia), geometry problems (Seo et al., 2015), pre-university…”
Analysis of Wikipedia-based Corpora for Question Answering (2018, background): “Recently, various QA tasks that are not selection-based have been proposed (Reddy and Bandyopadhyay, 2006; Hosseini et al., 2014; Jauhar et al., 2016; Sachan et al., 2016); however, selection-based QA remains still important because of its practical value to real applications (e.”