William W. Cohen's Papers: Explanation-Based Learning

1. Haitian Sun, William W. Cohen, Ruslan Salakhutdinov (2023): Scenario-based Question Answering with Interacting Contextual Properties in ICLR-2023.
2. Wenhu Chen, Pat Verga, Michiel de Jong, John Wieting, William W. Cohen (2022): Augmenting Pre-trained Language Models with QA-Memory for Open-Domain Question Answering in EACL-2022.
   
   • Extends the techniques of Mention Memory in several important ways. (1) The memory is a memory of generated question-answer pairs, which is more interpretable than neural entity-mention encodings; (2) it is based on pre-trained T5, not a custom Transformer; and (3) it allows use of the token-level encoding of retrieved QA pairs as well as neural encodings of them for reasoning. Using QA pairs instead of passages allows a clever pre-training trick for learning to retrieve, and the model greatly outperfoms a prior similar model (i.e., RePAQ) on smaller QA benchmarks.
3. Yi Tay, Vinh Q. Tran, Mostafa Dehghani, Jianmo Ni, Dara Bahri, Harsh Mehta, Zhen Qin, Kai Hui, Zhe Zhao, Jai Gupta, Tal Schuster, William W. Cohen and Donald Metzler (2022): Transformer Memory as a Differentiable Search Index in NeurIPS 2022.
4. Siddhant Arora, Danish Pruthi, Norman Sadeh, William W. Cohen, Zachary C. Lipton, Graham Neubig (2022): Explain, Edit, and Understand: Rethinking User Study Design for Evaluating Model Explanations in AAAI 2022.
5. Danish Pruthi, Bhuwan Dhingra, Livio Baldini Soares, Michael Collins, Zachary C. Lipton, Graham Neubig, William W. Cohen (2020): Evaluating Explanations: How Much Do Explanations From the Teacher Aid Students? in preparation.
6. William Yang Wang, Kathryn Mazaitis, and William W. Cohen (2015): A Soft Version of Predicate Invention Based on Structured Sparsity in IJCAI-2015.
7. William Yang Wang, Kathryn Mazaitis, Ni Lao, Tom Mitchell, and William W. Cohen (2015): Efficient Inference and Learning in a Large Knowledge Base: Reasoning with Extracted Information using a Locally Groundable First-Order Probabilistic Logic in Machine Learning, 2015.
8. William Yang Wang, Kathryn Mazaitis, William W. Cohen (2013): Programming with Personalized PageRank: A Locally Groundable First-Order Probabilistic Logic in CIKM-2013.
   
   • Honorable Mention for Best Paper at CIKM-2013
9. William Yang Wang, Kathryn Mazaitis, William W. Cohen (2013): Programming with Personalized PageRank: A Locally Groundable First-Order Probabilistic Logic in arxiv 1305.2254.
10. William Yang Wang, Kathryn Mazaitis, William W. Cohen (2013): Programming with Personalized PageRank: A Locally Groundable First-Order Probabilistic Logic in ICML 2103 Workshop on Inferning.
11. William W. Cohen, Russell Greiner, and Dale Schuurmans (1994): Probabilistic hill-climbing in Computational learning theory and natural learning systems (Volume II), MIT Press..
12. William W. Cohen (1994): Incremental abductive EBL in Machine Learning 15(1): 5-24 (1994).
13. William W. Cohen (1994): Grammatically biased learning: learning logic programs using an explicit antecedent description language in Artif. Intell. 68(2): 303-366 (1994).
14. William W. Cohen (1992): Using distribution-free learning theory to analyze solution path caching mechanisms in Computational Intelligence 8: 336-375 (1992).
15. William W. Cohen (1992): Desiderata for generalization-to-n algorithms in AII 1992: 140-150.
16. William W. Cohen (1992): Compiling prior knowledge into an explicit bias in ICML 1992: 102-110.
17. William W. Cohen (1992): Abductive explanation based learning: A solution to the multiple inconsistent explanation problem in Machine Learning 8: 167-219 (1992).
18. William W. Cohen (1993): A Review of `Creating a Memory of Causal Relationships' by Michael Pazzani in Machine Learning (1993).
19. William W. Cohen (1991): The generality of overgenerality in ICML 1991: 490-494.
20. William W. Cohen (1990): Learning from textbook knowledge: A case study in AAAI 1990: 743-748.
21. William W. Cohen (1990): Learning approximate control rules of high utility in ICML 1990: 268-276.
22. William W. Cohen (1990): An analysis of representation shift in concept learning in ICML 1990: 104-112.
23. William W. Cohen (1990): Learning from Examples and an "Abductive Theory" in Proc. of the 1990 AAAI Spring Symposium on Abduction.
24. William W. Cohen (1988): Generalizing number and learning from multiple examples in explanation-based learning in ICML 1988: 256-269.
25. William W. Cohen, Jack Mostow & Alex Borgida (1988): Generalizing number in explanation-based learning in Proc. of the 1988 AAAI Spring Symposium on Explanation-Based Learning.

[Selected papers| By topic: GNAT System| Retrieval Augmented LMs| Applications| Collaborative Filtering| Intelligent Tutoring| Explanation-Based Learning| Formal Results| Learning in Graphs| Inductive Logic Programming| Neural Knowledge Representation| Topic Modeling| Matching/Data Integration| Deep Learning| Prediction-powered inference| Rule Learning| Text Categorization| Info Extraction/Reading/QA| By year: All papers]