Doug Downey

Generating Literature-Driven Scientific Theories at Scale ACL 2026 Ai2 Scholar QA: Organized Literature Synthesis with Attribution ACL 2025 Intent-aware Schema Generation and Refinement for Literature Review Tables EMNLP 2025 SciRIFF: A Resource to Enhance Language Model Instruction-Following over Scientific Literature EMNLP 2025 ARIES: A Corpus of Scientific Paper Edits Made in Response to Peer Reviews ACL 2024 SciMON: Scientific Inspiration Machines Optimized for Novelty ACL 2024 CARE: Extracting Experimental Findings From Clinical Literature NAACL 2024 TOPICAL: TOPIC Pages AutomagicaLly NAACL 2024 Penguins Don’t Fly: Reasoning about Generics through Instantiations and Exceptions EACL 2023 PaperMage: A Unified Toolkit for Processing, Representing, and Manipulating Visually-Rich Scientific Documents EMNLP 2023 CHAMP: Efficient Annotation and Consolidation of Cluster Hierarchies EMNLP 2023 SciRepEval: A Multi-Format Benchmark for Scientific Document Representations EMNLP 2023 S2abEL: A Dataset for Entity Linking from Scientific Tables EMNLP 2023 I2D2: Inductive Knowledge Distillation with NeuroLogic and Self-Imitation ACL 2023 Are Layout-Infused Language Models Robust to Layout Distribution Shifts? A Case Study with Scientific Documents ACL 2023 Embedding Recycling for Language Models EACL 2023 Multi-LexSum: Real-world Summaries of Civil Rights Lawsuits at Multiple Granularities NIPS 2022 Don’t Say What You Don’t Know: Improving the Consistency of Abstractive Summarization by Constraining Beam Search EMNLP 2022 Learning to Perform Complex Tasks through Compositional Fine-Tuning of Language Models EMNLP 2022 ACCoRD: A Multi-Document Approach to Generating Diverse Descriptions of Scientific Concepts EMNLP 2022 Few-Shot Self-Rationalization with Natural Language Prompts NAACL 2022 Who’s on First?: Probing the Learning and Representation Capabilities of Language Models on Deterministic Closed Domains CONLL 2021 “It doesn’t look good for a date”: Transforming Critiques into Preferences for Conversational Recommendation Systems EMNLP 2021 Who’s on First?: Probing the Learning and Representation Capabilities of Language Models on Deterministic Closed Domains EMNLP 2021 SPECTER: Document-level Representation Learning using Citation-informed Transformers ACL 2020 Don’t Stop Pretraining: Adapt Language Models to Domains and Tasks ACL 2020 Stolen Probability: A Structural Weakness of Neural Language Models ACL 2020 Abductive Commonsense Reasoning ICLR 2020 Generative Data Augmentation for Commonsense Reasoning EMNLP 2020 Just Add Functions: A Neural-Symbolic Language Model AAAI 2020 A new evaluation framework for topic modeling algorithms based on synthetic corpora AISTATS 2019 Using Large Corpus N-gram Statistics to Improve Recurrent Neural Language Models NAACL 2019 CODAH: An Adversarially-Authored Question Answering Dataset for Common Sense NAACL 2019 Construction of the Literature Graph in Semantic Scholar NAACL 2018 Estimating Marginal Probabilities of n-grams for Recurrent Neural Language Models EMNLP 2018 Sampling Informative Training Data for RNN Language Models ACL 2018 Extracting Commonsense Properties from Embeddings with Limited Human Guidance ACL 2018 VecShare: A Framework for Sharing Word Representation Vectors EMNLP 2017 Efficient Methods for Inferring Large Sparse Topic Hierarchies ACL 2015 Efficient Methods for Incorporating Knowledge into Topic Models EMNLP 2015 Efficient Methods for Inferring Large Sparse Topic Hierarchies IJCNLP 2015 Adding High-Precision Links to Wikipedia EMNLP 2014 Scaling Semi-supervised Naive Bayes with Feature Marginals ACL 2013 Overcoming the Memory Bottleneck in Distributed Training of Latent Variable Models of Text NAACL 2013 Local and Global Algorithms for Disambiguation to Wikipedia ACL 2011 Language Models as Representations for Weakly Supervised NLP Tasks CONLL 2011 Improved Extraction Assessment through Better Language Models NAACL 2010 It’s a Contradiction – no, it’s not: A Case Study using Functional Relations EMNLP 2008 Look Ma, No Hands: Analyzing the Monotonic Feature Abstraction for Text Classification NIPS 2008 Sparse Information Extraction: Unsupervised Language Models to the Rescue ACL 2007 KnowItNow: Fast, Scalable Information Extraction from the Web EMNLP 2005