Sitemap
A list of all the posts and pages found on the site. For you robots out there is an XML version available for digesting as well.
Pages
Posts
portfolio
publications
Natural perturbation for robust question answering
Published in CoRR, abs, 2004
How Creative is Your Writing?
Published in Proceedings of the workshop on computational approaches to linguistic creativity, 2009
Some new directions in graph-based semi-supervised learning
Published in 2009 IEEE International Conference on Multimedia and Expo, 2009
Adaptive Filetype Aware Prefetching
Published in Department of Computer Sciences, University of Wisconsin: Madison, WI, USA, 2010
Boosting relational dependency networks
Published in Proc. of the Int. Conf. on Inductive Logic Programming (ILP), 2010
Clustering Twitter feeds using word cooccurrence
Published in University of Wisconsin, 2010
Exploiting causal independence in Markov logic networks: Combining undirected and directed models
Published in Machine Learning and Knowledge Discovery in Databases: European Conference, ECML PKDD 2010, Barcelona, Spain, September 20-24, 2010, Proceedings, Part II 21, 2010
Learning markov logic networks via functional gradient boosting
Published in 2011 IEEE 11th international conference on data mining, 2011
A machine learning pipeline for three-way classification of Alzheimer patients from structural magnetic resonance images of the brain
Published in 2012 11th International Conference on Machine Learning and Applications, 2012
Gradient-based boosting for statistical relational learning: The relational dependency network case
Published in Machine Learning, 2012
Learning Relational Structure for Temporal Relation Extraction.
Published in StarAI@ UAI, 2012
Structure learning with hidden data in relational domains
Published in Proceedings of ICML Workshop on Statistical Relational Learning, 2012
Bootstrapping Knowledge Base Acceleration.
Published in TREC, 2013
Learning relational probabilistic models from partially observed data-opening the closed-world assumption
Published in Proceedings of the 23rd International Conference on Inductive Logic Programming (ILP-13), 2013
Using commonsense knowledge to automatically create (noisy) training examples from text
Published in Workshops at the Twenty-Seventh AAAI Conference on Artificial Intelligence, 2013
Accelerating imitation learning in relational domains via transfer by initialization
Published in Inductive Logic Programming: 23rd International Conference, ILP 2013, Rio de Janeiro, Brazil, August 28-30, 2013, Revised Selected Papers 23, 2014
Classification from one class of examples for relational domains
Published in Workshops at the Twenty-Eighth AAAI Conference on Artificial Intelligence, 2014
Learning from imbalanced data in relational domains: A soft margin approach
Published in 2014 IEEE International Conference on Data Mining, 2014
Relational learning helps in three-way classification of Alzheimer patients from structural magnetic resonance images of the brain
Published in International Journal of Machine Learning and Cybernetics, 2014
Relational one-class classification: A non-parametric approach
Published in Proceedings of the AAAI Conference on Artificial Intelligence, 2014
Anomaly detection in text: The value of domain knowledge
Published in The Twenty-Eighth International Flairs Conference, 2015
Effectively creating weakly labeled training examples via approximate domain knowledge
Published in Inductive Logic Programming: 24th International Conference, ILP 2014, Nancy, France, September 14-16, 2014, Revised Selected Papers, 2015
Exploring Markov Logic Networks for Question Answering
Published in Empirical Methods in Natural Language Processing, 2015
Extracting adverse drug events from text using human advice
Published in Artificial Intelligence in Medicine: 15th Conference on Artificial Intelligence in Medicine, AIME 2015, Pavia, Italy, June 17-20, 2015. Proceedings 15, 2015
Gradient-based boosting for statistical relational learning: the Markov logic network and missing data cases
Published in Machine Learning, 2015
Graph-based approximate counting for relational probabilistic models
Published in Working Notes of the 5th International Workshop on Statistical Relational AI (StarAI@ UAI), 2015
Knowledge-based probabilistic logic learning
Published in Proceedings of the AAAI Conference on Artificial Intelligence, 2015
Learning probabilistic logic models with human advice
Published in 2015 AAAI Spring Symposium Series, 2015
Statistical relational learning for handwriting recognition
Published in Inductive Logic Programming: 24th International Conference, ILP 2014, Nancy, France, September 14-16, 2014, Revised Selected Papers, 2015
Combining retrieval, statistics, and inference to answer elementary science questions
Published in Proceedings of the AAAI conference on artificial intelligence, 2016
Inductive logic programming meets relational databases: An application to statistical relational learning
Published in Inductive Logic Programming (ILP), 2016
Learning continuous-time Bayesian networks in relational domains: A non-parametric approach
Published in Proceedings of the AAAI Conference on Artificial Intelligence, 2016
Learning with privileged information: Decision-trees and boosting
Published in Proc. Int. Joint Conf. Artif. Intell. Workshop, 2016
Question answering via integer programming over semi-structured knowledge
Published in IJCAI, 2016
Scaling lifted probabilistic inference and learning via graph databases
Published in Proceedings of the 2016 SIAM International Conference on Data Mining, 2016
Answering Complex Questions Using Open Information Extraction
Published in ACL, 2017
Inductive logic programming meets relational databases: Efficient learning of Markov logic networks
Published in Inductive Logic Programming: 26th International Conference, ILP 2016, London, UK, September 4-6, 2016, Revised Selected Papers 26, 2017
Learning what is essential in questions
Published in Proceedings of the 21st Conference on Computational Natural Language Learning (CoNLL 2017), 2017
Markov logic networks for adverse drug event extraction from text
Published in Knowledge and information systems, 2017
Adventure: Adversarial training for textual entailment with knowledge-guided examples
Published in Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2018
Bridging knowledge gaps in neural entailment via symbolic models
Published in Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, 2018
Can a suit of armor conduct electricity? a new dataset for open book question answering
Published in Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, 2018
Exploiting explicit paths for multi-hop reading comprehension
Published in arXiv preprint arXiv:1811.01127, 2018
Human-in-the-loop learning for probabilistic programming
Published in Proceedings of the Inaugural International Conference on Probabilistic Programming, 2018
Question answering as global reasoning over semantic abstractions
Published in Proceedings of the AAAI Conference on Artificial Intelligence, 2018
Relational restricted boltzmann machines: A probabilistic logic learning approach
Published in Inductive Logic Programming: 27th International Conference, ILP 2017, Orl'eans, France, September 4-6, 2017, Revised Selected Papers 27, 2018
Scitail: A textual entailment dataset from science question answering
Published in Proceedings of the AAAI conference on artificial intelligence, 2018
Think you have solved question answering? try ARC, the AI2 reasoning challenge
Published in arXiv preprint arXiv:1803.05457, 2018
Exploiting explicit paths for multi-hop reading comprehension
Published in Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, 2019
On the capabilities and limitations of reasoning for natural language understanding
Published in arXiv preprint arXiv:1901.02522, 2019
On the Possibilities and Limitations of Multi-hop Reasoning Under Linguistic Imperfections
Published in arXiv preprint arXiv:1901.02522, 2019
Repurposing entailment for multi-hop question answering tasks
Published in 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), 2019
What's missing: A knowledge gap guided approach for multi-hop question answering
Published in Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), 2019
A simple yet strong pipeline for hotpotqa
Published in Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), 2020
From ‘F’to ‘A’on the NY regents science exams: An overview of the aristo project
Published in Ai Magazine, 2020
IIRC: A dataset of incomplete information reading comprehension questions
Published in Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), 2020
Is Multihop QA in DiRe Condition? Measuring and Reducing Disconnected Reasoning
Published in Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), 2020
Measuring and reducing non-multifact reasoning in multi-hop question answering
Published in arXiv preprint arXiv:2005.00789, 2020
More bang for your buck: Natural perturbation for robust question answering
Published in Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), 2020
Qasc: A dataset for question answering via sentence composition
Published in Proceedings of the AAAI Conference on Artificial Intelligence, 2020
ReadOnce transformers: Reusable representations of text for transformers
Published in Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), 2020
Temporal reasoning on implicit events from distant supervision
Published in Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 2020
Text modular networks: Learning to decompose tasks in the language of existing models
Published in Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 2020
UNQOVERing Stereotyping Biases via Underspecified Questions
Published in Findings of EMNLP, 2020
Unifiedqa: Crossing format boundaries with a single qa system
Published in Findings of the Association for Computational Linguistics: EMNLP 2020, 2020
Did aristotle use a laptop? a question answering benchmark with implicit reasoning strategies
Published in Transactions of the Association for Computational Linguistics, 2021
Ethical-advice taker: Do language models understand natural language interventions?
Published in Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021, 2021
GooAQ: Open question answering with diverse answer types
Published in Findings of the Association for Computational Linguistics: EMNLP 2021, 2021
Hey AI, Can You Solve Complex Tasks by Talking to Agents?
Published in arXiv preprint arXiv:2110.08542, 2021
Learning to solve complex tasks by talking to agents
Published in arXiv preprint arXiv:2110.08542, 2021
Prompt waywardness: The curious case of discretized interpretation of continuous prompts
Published in arXiv preprint arXiv:2112.08348, 2021
Structure learning for relational logistic regression: an ensemble approach
Published in Data Mining and Knowledge Discovery, 2021
Think you have solved direct-answer question answering? try arc-da, the direct-answer ai2 reasoning challenge
Published in arXiv preprint arXiv:2102.03315, 2021
Better retrieval may not lead to better question answering
Published in arXiv preprint arXiv:2205.03685, 2022
Beyond the imitation game: Quantifying and extrapolating the capabilities of language models
Published in Transactions on Machine Learning Research, 2022
Complexity-based prompting for multi-step reasoning
Published in The Eleventh International Conference on Learning Representations, 2022
Decomposed prompting: A modular approach for solving complex tasks
Published in The Eleventh International Conference on Learning Representations, 2022
Hey AI, Can You Solve Complex Tasks by Talking to Agents?
Published in Findings of the Association for Computational Linguistics: ACL 2022, 2022
♫ MuSiQue: Multihop Questions via Single-hop Question Composition
Published in Transactions of the Association for Computational Linguistics, 2022
Prompt waywardness: The curious case of discretized interpretation of continuous prompts
Published in Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 2022
Retrieval data augmentation informed by downstream question answering performance
Published in Proceedings of the Fifth Fact Extraction and VERification Workshop (FEVER), 2022
Teaching Broad Reasoning Skills via Decomposition-Guided Contexts
Published in Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, 2022
The Tail Wagging the Dog: Dataset Construction Biases of Social Bias Benchmarks
Published in arXiv preprint arXiv:2210.10040, 2022
Chain-of-Thought Hub: A Continuous Effort to Measure Large Language Models' Reasoning Performance
Published in arXiv preprint arXiv:2305.17306, 2023
How far can camels go? exploring the state of instruction tuning on open resources
Published in Advances in Neural Information Processing Systems, 2023
Improving language model negotiation with self-play and in-context learning from ai feedback
Published in arXiv preprint arXiv:2305.10142, 2023
Interleaving retrieval with chain-of-thought reasoning for knowledge-intensive multi-step questions
Published in Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2023
Specializing smaller language models towards multi-step reasoning
Published in International Conference on Machine Learning, 2023
Synergpt: In-context learning for personalized drug synergy prediction and drug design
Published in COLM, 2024
Bias runs deep: Implicit reasoning biases in persona-assigned llms
Published in The Twelfth International Conference on Learning Representations, 2024
Adapt: As-needed decomposition and planning with language models
Published in Findings of the Association for Computational Linguistics: NAACL 2024, 2024
DiscoveryBench: Towards Data-Driven Discovery with Large Language Models
Published in arXiv preprint arXiv:2407.01725, 2024
DiscoveryWorld: A Virtual Environment for Developing and Evaluating Automated Scientific Discovery Agents
Published in arXiv preprint arXiv:2406.06769, 2024
Husky: A Unified, Open-Source Language Agent for Multi-Step Reasoning
Published in arXiv preprint arXiv:2406.06469, 2024
AppWorld: A Controllable World of Apps and People for Benchmarking Interactive Coding Agents
Published in ACL, 2024
Olmo: Accelerating the science of language models
Published in ACL, 2024