NLProlog: Reasoning with Weak Unification for Question Answering in Natural Language
Open accessThe DOI matches its Crossref record; 11 of the 11 references it cites were found in a registry or an index.
Abstract
Rule-based models are attractive for various tasks because they inherently lead to interpretable and explainable decisions and can easily incorporate prior knowledge.However, such systems are difficult to apply to problems involving natural language, due to its linguistic variability.In contrast, neural models can cope very well with ambiguity by learning distributed representations of words and their composition from data, but lead to models that are difficult to interpret.In this paper, we describe a model combining neural networks with logic programming in a novel manner for solving multi-hop reasoning tasks over natural language.Specifically, we propose to use a Prolog prover which we extend to utilize a similarity function over pretrained sentence encoders.We fine-tune the representations for the similarity function via backpropagation.This leads to a system that can apply rulebased reasoning to natural language, and induce domain-specific rules from training data.We evaluate the proposed system on two different question answering tasks, showing that it outperforms two baselines -BIDAF (Seo et al., 2016a) and FASTQA (Weissenborn et al., 2017b) on a subset of the WIKIHOP corpus and achieves competitive results on the MEDHOP data set (Welbl et al., 2017).
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
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946
Lipton, Z. C. (2018) · Queue · doi:10.1145/3236386.3241340 · Cited by 5,427 · cited 2×
“However, in such models, explaining the reasoning steps leading to an answer and interpreting the model parameters to extrapolate new knowledge is a very challenging task (DoshiVelez and Kim, 2017; Lipton, 2018; Guidotti et al., 2019).”
BackgroundMethodDrugBank: a comprehensive resource for in silico drug discovery and exploration
Wishart, D. S. (2006) · Nucleic Acids Research · doi:10.1093/nar/gkj067 · Cited by 3,892
Towards A Rigorous Science of Interpretable Machine Learning
Doshi-Velez, F., & Kim, B. (2017) · arXiv · doi:10.48550/arxiv.1702.08608 · Cited by 3,121
Richardson, M., & Domingos, P. (2006) · Machine Learning · doi:10.1007/s10994-006-5833-1 · Cited by 2,676 · cited 2×
“Our work is very related to the integration of Markov Logic Networks (Richardson and Domingos, 2006) and Probabilistic Soft Logic (Bach et al., 2017) with word embeddings, which was applied to Recognizing Textual Entailment (RTE) and Semantic Textual Similarity (STS) tasks (Garrette et al., 2011, 2014; Beltagy et al.,…”
MethodWhat is the best multi-stage architecture for object recognition?
Jarrett, K., Kavukcuoglu, K., Ranzato, M. A., & LeCun, Y. (2009) · 2009 IEEE 12th International Conference on Computer Vision · doi:10.1109/iccv.2009.5459469 · Cited by 2,153
Hybrid computing using a neural network with dynamic external memory
Graves, A., Wayne, G., Reynolds, M., Harley, T., Danihelka, I., Grabska-Barwińska, A., Colmenarejo, S. G., Grefenstette, E., Ramalho, T., Agapiou, J., et al. (2016) · Nature · doi:10.1038/nature20101 · Cited by 1,412
Sukhbaatar, S., Szlam, A., Weston, J., & Fergus, R. (2015) · arXiv · doi:10.48550/arxiv.1503.08895 · Cited by 1,345
Muggleton, S. (1991) · New Generation Computing · doi:10.1007/bf03037089 · Cited by 1,044
Learning Explanatory Rules from Noisy Data
Evans, R., & Grefenstette, E. (2018) · Journal of Artificial Intelligence Research · doi:10.1613/jair.5714 · Cited by 426
Question answering by reasoning across documents with graph convolutional networks
De Cao, N., Aziz, W., & Titov, I. (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/n19-1240 · Cited by 54
Cited by
Neurosymbolic AI: the 3rd wave
Garcez, A. D., & Lamb, L. C. (2023) · Artificial Intelligence Review · doi:10.1007/s10462-023-10448-w · Cited by 503
Neuro-symbolic artificial intelligence: a survey
Bhuyan, B. P., Ramdane-Cherif, A., Tomar, R., & Singh, T. P. (2024) · Neural Computing and Applications · doi:10.1007/s00521-024-09960-z · Cited by 190
“Research by Weber et al. [188], which integrates Pro-log’s reasoning with natural language processing, and the comparative study by Ma et al. [281] on common-sense QA, further illustrate the diversity of strategies employed to enhance question understanding and answer generation.”
InfluentialTransformers as Soft Reasoners over Language
Clark, P., Tafjord, O., & Richardson, K. (2020) · Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2020/537 · Cited by 176
Neural probabilistic logic programming in DeepProbLog
Manhaeve, R., Dumančić, S., Kimmig, A., Demeester, T., & De Raedt, L. (2021) · Artificial Intelligence · doi:10.1016/j.artint.2021.103504 · Cited by 131
ProofWriter: Generating implications, proofs, and abductive statements over natural language
Tafjord, O., Dalvi, B., & Clark, P. (2021) · Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021 · doi:10.18653/v1/2021.findings-acl.317 · Cited by 122
Metadata
- Authors
- Weber, L., Minervini, P., Münchmeyer, J., Leser, U., & Rocktäschel, T.
- Venue
- Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
- Published
- 2019
- Pages
- 6151-6161
- OpenAlex
- W2950246755
- Cited by
- 77
- References
- 11
- FWCI
- 5.11
- Type
- conference paper
- Language
- en
- Open access
- hybrid
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.