Combining Retrieval, Statistics, and Inference to Answer Elementary Science Questions
Open accessThe DOI matches its Crossref record; 4 of the 4 references it cites were found in a registry or an index.
Abstract
What capabilities are required for an AI system to pass standard 4th Grade Science Tests? Previous work has examined the use of Markov Logic Networks (MLNs) to represent the requisite background knowledge and interpret test questions, but did not improve upon an information retrieval (IR) baseline. In this paper, we describe an alternative approach that operates at three levels of representation and reasoning: information retrieval, corpus statistics, and simple inference over a semi-automatically constructed knowledge base, to achieve substantially improved results. We evaluate the methods on six years of unseen, unedited exam questions from the NY Regents Science Exam (using only non-diagram, multiple choice questions), and show that our overall system’s score is 71.3%, an improvement of 23.8% (absolute) over the MLN-based method described in previous work. We conclude with a detailed analysis, illustrating the complementary strengths of each method in the ensemble. Our datasets are being released to enable further research.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
A relational model of data for large shared data banks
Codd, E. F. (1970) · Communications of the ACM · doi:10.1145/362384.362685 · Cited by 5,547
Recurrent neural network based language model
Mikolov, T., Karafiát, M., Burget, L., Černocký, J., & Khudanpur, S. (2010) · Interspeech 2010 · doi:10.21437/interspeech.2010-343 · Cited by 5,390 · cited 2×
“The embeddings are learned using the recurrent neural network language model (RNNLM) (Mikolov et al. 2010; 2013).”
MethodRichardson, M., & Domingos, P. (2006) · Machine Learning · doi:10.1007/s10994-006-5833-1 · Cited by 2,676
Word association norms, mutual information, and lexicography
Church, K. W., & Hanks, P. (1989) · Proceedings of the 27th annual meeting on Association for Computational Linguistics - · doi:10.3115/981623.981633 · Cited by 1,094
Cited by
Jin, D., Pan, E., Oufattole, N., Weng, W.-H., Fang, H., & Szolovits, P. (2021) · doi:10.20944/preprints202105.0498.v1 · Cited by 718
Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering
Mihaylov, T., Clark, P., Khot, T., & Sabharwal, A. (2018) · Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d18-1260 · Cited by 649
Self-citationJin, D., Pan, E., Oufattole, N., Weng, W.-H., Fang, H., & Szolovits, P. (2021) · Applied Sciences · doi:10.3390/app11146421 · Cited by 718
UNIFIEDQA: Crossing Format Boundaries with a Single QA System
Khashabi, D., Min, S., Khot, T., Sabharwal, A., Tafjord, O., Clark, P., & Hajishirzi, H. (2020) · Findings of the Association for Computational Linguistics: EMNLP 2020 · doi:10.18653/v1/2020.findings-emnlp.171 · Cited by 514
Self-citationThink you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge
Clark, P., Cowhey, I., Etzioni, O., Khot, T., Sabharwal, A., Schoenick, C., & Tafjord, O. (2018) · arXiv · doi:10.48550/arxiv.1803.05457 · Cited by 462
“Datasets based on human standardized tests have also been used in AI for several years (e.g. Clark et al., 2016; Seo et al., 2014; Fujita et al., 2014; Strickland, 2013), and as part of the NTCIR QALab (NII, 2017), and for the 2016 Allen AI Science Challenge described in the Introduction (Schoenick…”
MethodInfluentialSelf-citationConstructing Datasets for Multi-hop Reading Comprehension Across Documents
Welbl, J., Stenetorp, P., & Riedel, S. (2018) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00021 · Cited by 456
SciTaiL: A Textual Entailment Dataset from Science Question Answering
Khot, T., Sabharwal, A., & Clark, P. (2018) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v32i1.12022 · Cited by 411
Self-citationDROP: A Reading Comprehension Benchmark Requiring Discrete Reasoning Over Paragraphs
Dua, D., Wang, Y., Dasigi, P., Stanovsky, G., Singh, S., & Gardner, M. (2019) · Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers) · doi:10.18653/v1/n19-1246 · Cited by 393
“also contain similar phenomena to what is in DROP (Koncel-Kedziorski et al., 2015; Kushman et al., 2014; Hosseini et al., 2014; Clark et al., 2016; Ling et al., 2017).”
BackgroundDon’t Take the Easy Way Out: Ensemble Based Methods for Avoiding Known Dataset Biases
Clark, C., Yatskar, M., & Zettlemoyer, L. (2019) · Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) · doi:10.18653/v1/d19-1418 · Cited by 381
“Additional examples include story completion (Schwartz et al., 2017) and multiple choice questions (Clark et al., 2016, 2018).”
BackgroundLooking Beyond the Surface: A Challenge Set for Reading Comprehension over Multiple Sentences
Khashabi, D., Chaturvedi, S., Roth, M., Upadhyay, S., & Roth, D. (2018) · Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers) · doi:10.18653/v1/n18-1023 · Cited by 370
Self-citationDROP: A Reading Comprehension Benchmark Requiring Discrete Reasoning Over Paragraphs
Dua, D., Wang, Y., Dasigi, P., Stanovsky, G., Singh, S., & Gardner, M. (2019) · arXiv · doi:10.48550/arxiv.1903.00161 · Cited by 238
Seeing Things from a Different Angle:Discovering Diverse Perspectives about Claims
Chen, S., Khashabi, D., Yin, W., Callison-Burch, C., & Roth, D. (2019) · Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers) · doi:10.18653/v1/n19-1053 · Cited by 104
“This baseline has been successfully used for related tasks like Question Answering (Clark et al., 2016).”
MethodSelf-citationQASC: A Dataset for Question Answering via Sentence Composition
Khot, T., Clark, P., Guerquin, M., Jansen, P., & Sabharwal, A. (2020) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v34i05.6319 · Cited by 20
Self-citationEfficient Fine-Tuning Large Language Models for Knowledge-Aware Response Planning
Nguyen, M., Kishan, K. C., Nguyen, T., Chadha, A., & Vu, T. (2023) · Lecture Notes in Computer Science · doi:10.1007/978-3-031-43415-0_35 · Cited by 8
Metadata
- Authors
- Clark, P., Etzioni, O., Khot, T., Sabharwal, A., Tafjord, O., Turney, P., & Khashabi, D.
- Venue
- Proceedings of the AAAI Conference on Artificial Intelligence
- Published
- 2016-03-05
- Volume
- 30
- Issue
- 1
- ISSN
- 2159-5399 (ISSN-L)
- 2374-3468
- OpenAlex
- W2547185913
- Cited by
- 138
- References
- 4
- FWCI
- 24.50
- Type
- conference paper
- Language
- en
- Open access
- diamond
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.