[Google Scholar] [dblp] [Semantic Scholar]
Preprints
- Parker-Holder, Jiang, Dennis, Samvelyan, Foerster, Grefenstette and Rocktäschel. Evolving Curricula with Regret-Based Environment Design. preprint. 2022 [bib] [pdf] [demo] preprint
- Mu, Zhong, Raileanu, Jiang, Goodman, Rocktäschel and Grefenstette. Improving Intrinsic Exploration with Language Abstractions. preprint. 2022 [bib] [pdf] preprint
- Mahajan, Samvelyan, Gupta, Ellis, Sun, Rocktäschel and Whiteson. Generalization in Cooperative Multi-Agent Systems. preprint. 2022 [bib] [pdf] preprint
- Kirk, Zhang, Grefenstette and Rocktäschel. A Survey of Generalisation in Deep Reinforcement Learning. preprint. 2021 [bib] [pdf] preprint
2021
- Parker-Holder, Jiang, Dennis, Samvelyan, Foerster, Grefenstette and Rocktäschel. That Escalated Quickly: Compounding Complexity by Editing Levels at the Frontier of Agent Capabilities. in: DeepRL. 2021 [bib] [pdf] workshop
- Jiang, Dennis, Parker-Holder, Lupu, Küttler, Grefenstette, Rocktäschel and Foerster. Grounding Aleatoric Uncertainty in Unsupervised Environment Design. in: DeepRL. 2021 [bib] [pdf] workshop
- Jiang, Zhang, Kirk, Rocktäschel and Grefenstette. Graph Backup: Data Efficient Backup Exploiting Markovian Data. in: DeepRL. 2021 [bib] [pdf] workshop
- Korshunova, Jiang, Parker-Holder, Rocktäschel and Grefenstette. Return Dispersion as an Estimator of Learning Potential for Prioritized Level Replay. in: DeepRL. 2021 [bib] [pdf] workshop
- Jiang, Dennis, Parker-Holder, Foerster, Grefenstette and Rocktäschel. Replay-Guided Adversarial Environment Design. in: NeurIPS. 2021 [bib] [pdf] [code] conference
- Samvelyan, Kirk, Kurin, Parker-Holder, Jiang, Hambro, Petroni, Küttler, Grefenstette and Rocktäschel. MiniHack the Planet: A Sandbox for Open-Ended Reinforcement Learning Research. in: NeurIPS. 2021 [bib] [pdf] [code] [blog] conference
- Rothermel, Li, Rocktäschel and Foerster. Don’t Sweep your Learning Rate under the Rug: A Closer Look at Cross-modal Transfer of Pretrained Transformers. in: ICMLSSL. 2021 [bib] [pdf] workshop
- Jiang, Grefenstette and Rocktäschel. Prioritized Level Replay. in: ICML. 2021 [bib] [pdf] [code] conference
- Ammanabrolu, Urbanek, Li, Szlam, Rocktäschel and Weston. How to Motivate Your Dragon: Teaching Goal-Driven Agents to Speak and Act in Fantasy Worlds. in: NAACL-HLT. 2021 [bib] [pdf] conference
- Petroni, Piktus, Fan, Lewis, Yazdani, De Cao, Thorne, Jernite, Karpukhin, Maillard, Plachouras, Rocktäschel and Riedel. KILT: a Benchmark for Knowledge Intensive Language Tasks. in: NAACL-HLT. 2021 [bib] [pdf] conference
- Campero, Raileanu, Küttler, Tenenbaum, Rocktäschel and Grefenstette. Learning with AMIGo: Adversarially Motivated Intrinsic Goals. in: ICLR. 2021 [bib] [pdf] conference
- Kurin, Igl, Rocktäschel, Boehmer and Whiteson. My Body is a Cage: the Role of Morphology in Graph-Based Incompatible Control. in: ICLR. 2021 [bib] [pdf] conference
- Jiang, Minervini, Jiang and Rocktäschel. Grid-to-Graph: Flexible Spatial Relational Inductive Biases for Reinforcement Learning. in: AAMAS. 2021 [bib] [pdf] conference
2020
- Küttler, Nardelli, Miller, Raileanu, Selvatici, Grefenstette and Rocktäschel. The NetHack Learning Environment. in: NeurIPS. 2020 [bib] [pdf] [code] [blog] [talk] [interview] conference
- Lewis, Perez, Piktus, Petroni, Karpukhin, Goyal, Küttler, Lewis, Yih, Rocktäschel, Riedel and Kiela. Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks. in: NeurIPS. 2020 [bib] [pdf] conference
- Stacey, Minervini, Dubossarsky, Riedel and Rocktäschel. Avoiding the Hypothesis-Only Bias in Natural Language Inference via Ensemble Adversarial Training. in: EMNLP. 2020 [bib] conference
- Massarelli, Petroni, Piktus, Ott, Rocktäschel, Plachouras, Silvestri and Riedel. How Decoding Strategies Affect the Verifiability of Generated Text. Findings of ACL: EMNLP. 2020 [bib] journal
- Jiang, Luketina, Nardelli, Minervini, Torr, Whiteson and Rocktäschel. WordCraft: An Environment for Benchmarking Commonsense Agents. in: LaReL. 2020 [bib] workshop
- Minervini, Riedel, Stenetorp, Grefenstette and Rocktäschel. Learning Reasoning Strategies in End-to-End Differentiable Proving. in: ICML. 2020 [bib] [pdf] conference
- Petroni, Lewis, Piktus, Rocktäschel, Wu, Miller and Riedel. How Context Affects Language Models’ Factual Predictions. in: AKBC. 2020 [bib] [pdf] [talk] conference
Best Paper Award. - Raileanu and Rocktäschel. RIDE: Rewarding Impact-Driven Exploration for Procedurally-Generated Environments. in: ICLR. 2020 [bib] [pdf] [code] conference
- Zhong, Rocktäschel and Grefenstette. RTFM: Generalising to New Environment Dynamics via Reading. in: ICLR. 2020 [bib] [pdf] conference
- Minervini, Bosnjak, Rocktäschel, Riedel and Grefenstette. Differentiable Reasoning on Large Knowledge Bases and Natural Language. in: AAAI. 2020 [bib] [pdf] conference
- Fan, Urbanek, Ringshia, Dinan, Qian, Karamcheti, Prabhumoye, Kiela, Rocktäschel, Szlam and Weston. Generating Interactive Worlds with Text. in: AAAI. 2020 [bib] [pdf] [code] conference
2019
- Küttler, Nardelli, Lavril, Selvatici, Sivakumar, Rocktäschel and Grefenstette. TorchBeast: A PyTorch Platform for Distributed RL. Technical Report arXiv:1910.03552. 2019 [bib] [pdf] [code] techreport
- Sivakumar, Rocktäschel, Miller, Küttler, Nardelli, Rabbat, Pineau and Riedel. mvfst-rl: An Asynchronous RL Framework for Congestion Control with Delayed Actions. in: ML for Systems. 2019 [bib] [pdf] [code] workshop
- Petroni, Rocktäschel, Lewis, Bakhtin, Wu, Miller and Riedel. Language Models as Knowledge Bases?. in: EMNLP. 2019 [bib] [pdf] [code] conference
- Urbanek, Fan, Karamcheti, Jain, Humeau, Dinan, Rocktäschel, Kiela, Szlam and Weston. Learning to Speak and Act in a Fantasy Text Adventure Game. in: EMNLP. 2019 [bib] [pdf] conference
- Weber, Münchmeyer, Rocktäschel, Habibi and Leser. HUNER: Improving Biomedical NER with Pretraining. Bioinformatics. 2019 [bib] journal
- Cowen-Rivers, Minervini, Riedel, Rocktäschel, Wang and Bosnjak. Neural Variational Inference for Estimating Knowledge Graph Embedding Uncertainty. in: NeSy. 2019 [bib] [pdf] workshop
- Weber, Minervini, Münchmeyer, Leser and Rocktäschel. NLProlog: Reasoning with Weak Unification for Question Answering in Natural Language. in: ACL. 2019 [bib] [pdf] conference
- Luketina, Nardelli, Farquhar, Foerster, Andreas, Grefenstette, Whiteson and Rocktäschel. A Survey of Reinforcement Learning Informed by Natural Language. in: IJCAI. 2019 [bib] [pdf] conference
- Mao, Foerster, Rocktäschel, Al-Shedivat, Farquhar and Whiteson. A Baseline for Any Order Gradient Estimation in Stochastic Computation Graphs. in: ICML. 2019 [bib] [pdf] conference
- Letcher, Foerster, Balduzzi, Rocktäschel and Whiteson. Stable Opponent Shaping in Differentiable Games. in: ICLR. 2019 [bib] [pdf] conference
2018
- Camburu, Rocktäschel, Lukasiewicz and Blunsom. e-SNLI: Natural Language Inference with Natural Language Explanations. in: NeurIPS. 2018 [bib] [code] conference
- Saeidi, Bartolo, Lewis, Singh, Rocktäschel, Sheldon, Bouchard and Riedel. Interpretation of Natural Language Rules in Conversational Machine Reading. in: EMNLP. 2018 [bib] [pdf] [link] conference
- Minervini, Bosnjak, Rocktäschel and Riedel. Towards Neural Theorem Proving at Scale. in: NAMPI. 2018 [bib] [pdf] workshop
- Foerster, Farquhar, Al-Shedivat, Rocktäschel, Xing and Whiteson. DiCE: The Infinitely Differentiable Monte-Carlo Estimator. in: ICML. 2018 [bib] [pdf] [code] [pyro] conference
Also presented at the ICLR Workshop 2018 with minor changes. - Farquhar, Rocktäschel, Igl and Whiteson. TreeQN and ATreeC: Differentiable Tree-Structured Models for Deep Reinforcement Learning. in: ICLR. 2018 [bib] [pdf] [code] [slides] conference
- Weissenborn, Minervini, Dettmers, Augenstein, Welbl, Rocktäschel, Bosnjak, Mitchell, Demeester, Stenetorp and Riedel. Jack the Reader — A Machine Reading Framework. in: ACL Demo. 2018 [bib] [pdf] [code] demo
2017
- Rocktäschel and Riedel. End-to-end Differentiable Proving. in: NeurIPS. 2017 [bib] [pdf] [code] [talk] [slides] [poster] conference
NeurIPS oral presentation (1.2% acceptance rate). - Minervini, Demeester, Rocktäschel and Riedel. Adversarial Sets for Regularised Neural Link Predictors. in: UAI. 2017 [bib] [pdf] [code] conference
- Bosnjak, Rocktäschel, Naradowsky and Riedel. Programming with a Differentiable Forth Interpreter. in: ICML. 2017 [bib] [pdf] [code] conference
Also presented at the ICLR Workshop 2017 with minor changes. - Daniluk, Rocktäschel, Welbl and Riedel. Frustratingly Short Attention Spans in Neural Language Modeling. in: ICLR. 2017 [bib] [pdf] conference
- Rocktäschel. Combining Representation Learning with Logic for Language Processing. PhD Thesis. University College London. 2017 [bib] [pdf] thesis
2016
- Eisner, Rocktäschel, Augenstein, Bosnjak and Riedel. emoji2vec: Learning Emoji Representations from their Description. in: SocialNLP. 2016 [bib] [pdf] [code] workshop
Best Paper Award. - Demeester, Rocktäschel and Riedel. Lifted Rule Injection for Relation Embeddings. in: EMNLP. 2016 [bib] [pdf] conference
Also presented at the Dutch-Belgian Information Retrieval Workshop (DIR) 2016. - Augenstein, Rocktäschel, Vlachos and Bontcheva. Stance Detection with Bidirectional Conditional Encoding. in: EMNLP. 2016 [bib] [pdf] [code] conference
- Weissenborn and Rocktäschel. MuFuRU: The Multi-Function Recurrent Unit. in: RepL4NLP. 2016 [bib] [pdf] [code] workshop
- Thomas, Rocktäschel, Hakenberg, Lichtblau and Leser. SETH detects and normalizes genetic variants in text. Bioinformatics. 2016 [bib] [pdf] [code] [link] journal
- Rocktäschel and Riedel. Learning Knowledge Base Inference with Neural Theorem Provers. in: AKBC. 2016 [bib] [pdf] workshop
- Bhoopchand, Rocktäschel, Barr and Riedel. Learning Python Code Suggestion with a Sparse Pointer Network. Technical Report arXiv:1611.08307. 2016 [bib] [pdf] [code] techreport
- Kolesnyk, Rocktäschel and Riedel. Generating Natural Language Inference Chains. Technical Report arXiv:1606.01404. 2016 [bib] [pdf] techreport
- Demeester, Rocktäschel and Riedel. Regularizing Relation Representations by First-order Implications. in: AKBC. 2016 [bib] [pdf] workshop
Also presented at BeneLearn 2016. - Rocktäschel, Grefenstette, Hermann, Kočiský and Blunsom. Reasoning about Entailment with Neural Attention. in: ICLR. 2016 [bib] [pdf] conference
2015
- Riedel, Singh, Bouchard, Rocktäschel and Sanchez. Towards Two-Way Interaction with Reading Machines. in: SLSP. 2015 [bib] [pdf] conference
- Singh, Rocktäschel and Riedel. Towards Combined Matrix and Tensor Factorization for Universal Schema Relation Extraction. in: VSM. 2015 [bib] [pdf] workshop
- Rocktäschel, Singh and Riedel. Injecting Logical Background Knowledge into Embeddings for Relation Extraction. in: NAACL-HLT. 2015. [bib] [pdf] [code] [slides] conference
- Singh, Rocktäschel, Hewitt, Naradowsky and Riedel. WOLFE: An NLP-friendly Declarative Machine Learning Stack. in: NAACL-HLT Demo. 2015 [bib] [pdf] demo
- Sanchez, Rocktäschel, Riedel and Singh. Towards Extracting Faithful and Descriptive Representations of Latent Variable Models. in: KRR. 2015 [bib] [pdf] workshop
- Krallinger, Rabal, Leitner, Vazquez, Salgado, Lu, Leaman, Lu, Ji, Lowe and others. The CHEMDNER corpus of chemicals and drugs and its annotation principles. Journal of Cheminformatics. 2015 [bib] [pdf] journal
- Bouchard, Naradowsky, Riedel, Rocktäschel and Vlachos. Matrix and Tensor Factorization Methods for Natural Language Processing. in: ACL Tutorial. 2015 [bib] [pdf] [link] tutorial
2014
- Singh, Riedel, Hewitt and Rocktäschel. Designing an IDE for Probabilistic Programming: Challenges and a Prototype. in: ProbProg. 2014 [bib] [pdf] [code] workshop
- Rocktäschel, Bosnjak, Singh and Riedel. Low-Dimensional Embeddings of Logic. in: SP14. 2014 [bib] [pdf] workshop
Google Exceptional Submission Award.
Also presented at StarAI 2014 with minor changes. - Riedel, Singh, Srikumar, Rocktäschel, Visengeriyeva and Noessner. WOLFE: Strength Reduction and Approximate Programming for Probabilistic Programming. in: StarAI. 2014 [bib] [pdf] [code] [link] workshop
Also presented at NeurIPS 2014 Probabilistic Programming Workshop. - Singh, Hewitt, Rocktäschel and Riedel. A Visual and Interactive IDE for Probabilistic Programming. in: NeurIPS Demo. 2014 [bib] demo
2013
- Huber, Rocktäschel, Weidlich, Thomas and Leser. Extended Feature Set for Chemical Named Entity Recognition and Indexing. in: BioCreative. 2013 [bib] [pdf] workshop
- Rocktäschel, Huber, Weidlich and Leser. WBI-NER: The impact of domain-specific features on the performance of identifying and classifying mentions of drugs. in: SemEval. 2013 [bib] [pdf] workshop
Placed 1st in the DDIExtraction 2013 Task 9.1. - Thomas, Neves, Rocktäschel and Leser. WBI-DDI: Drug-Drug Interaction Extraction using Majority Voting. in: SemEval. 2013 [bib] [pdf] workshop
Placed 2nd in the DDIExtraction 2013 Task 9.2.
2012
- Rocktäschel, Weidlich and Leser. ChemSpot: a hybrid system for chemical named entity recognition. Bioinformatics. 2012 [bib] [pdf] [code] [link] journal
- Rocktäschel. Joint Extraction of Proteins and Bio-Molecular Events using Imperatively Defined Factor Graphs. Diploma Thesis. Humboldt-Universität zu Berlin. 2012 [bib] thesis
Faculty Award for Exceptional Diploma Thesis.