KG^2: Learning to Reason Science Exam Questions with Contextual Knowledge Graph Embeddings

By Yuyu Zhang, Hanjun Dai, Kamil Toraman, Le Song. 2018

28 citations recorded by the source corpus.

The AI2 Reasoning Challenge (ARC), a new benchmark dataset for question answering (QA) has been recently released. ARC only contains natural science questions authored for human exams, which are hard to answer and require advanced logic reasoning. On the ARC Challenge Set, existing state-of-the-art QA systems fail to significantly outperform random baseline, reflecting the difficult nature of this task. In this paper, we propose a novel framework for answering science exam questions, which mimics human solving process in an open-book exam. To address the reasoning challenge, we construct contextual knowledge graphs respectively for the question itself and supporting sentences. Our model learns to reason with neural embeddings of both knowledge graphs. Experiments on the ARC Challenge Set show that our model outperforms the previous state-of-the-art QA systems.

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

Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering (2018, positive): “The resulting system scores 33.87% on the Challenge Test set, which is 2.17% higher than the previous best score by Zhang et al. (2018).”
Improving Question Answering with External Knowledge (2019, background): “…indirectly use automatically constructed knowledge bases/graphs from reference corpora (Khot et al., 2017; Kwon et al., 2018; Khashabi et al., 2018; Zhang et al., 2018) or existing external general knowledge graphs (Li and Clark, 2015; Sachan et al., 2016; Wang et al., 2018a,c; Zhong et al., 2018;…”
Careful Selection of Knowledge to Solve Open Book Question Answering (2019, background): “Among these, the closest to our work is the work in (Devlin et al., 2018) which perform QA using fine tuned language model and the works of (Sun et al., 2018; Zhang et al., 2018) which performs QA using external knowledge.”
Answering Science Exam Questions Using Query Rewriting with Background Knowledge (2018, methodology): “Recently, the top performing systems for ARC use natural language inference (NLI) models to answer the questions (Zhang et al. 2018).”
Improving Retrieval-Based Question Answering with Deep Inference Models (2018, background): “KG2 [1] is a model that employs contextual knowledge graphs in order to find the correct answer to a question.”
Multi-domain Dialogue State Tracking as Dynamic Knowledge Graph Enhanced Question Answering (2019, methodology): “Zhang et al. (2018) propose to use Open IE to extract relation triples from context paragraphs and build a contextual knowledge graph with respect to the question and context paragraphs.”
Quick and (not so) Dirty: Unsupervised Selection of Justification Sentences for Multi-hop Question Answering (2019, methodology): “Unlike approaches that rely on structured KBs, which are expensive to create, (Khashabi et al., 2016; Khot et al., 2017; Zhang et al., 2018; Khashabi et al., 2018b; Cui et al., 2017; Bao et al., 2016), our method operates over KBs of only unstructured texts.”
Scalable Multi-Hop Relational Reasoning for Knowledge-Aware Question Answering (2020, background): “Recent success of pre-trained LMs motivates many (Pan et al., 2019; Ye et al., 2019; Zhang et al., 2018; Li et al., 2019; Banerjee et al., 2019) to probe LMs’ potential as latent knowledge bases.”