Jason Eisner — all works
- Three New Probabilistic Models for Dependency Parsing: An ExplorationJason M. EisnerEnglish · 910 citations
- Learning How to Ask: Querying LMs with Mixtures of Soft PromptsConference of the North American Chapter of the Association for Computational Linguistics (NAACL)Guanghui Qin, Jason Eisner2021 · 573 citations
- Contrastive Estimation: Training Log-Linear Models on Unlabeled DataAnnual Meeting of the Association for Computational Linguistics (ACL)Noah A. Smith, Jason Eisner2005 · 450 citations
- Using “Annotator Rationales” to Improve Machine Learning for Text CategorizationConference of the North American Chapter of the Association for Computational Linguistics (NAACL)Omar Zaidan, Jason Eisner, Christine Piatko2007 · 361 citations
- Learning Non-Isomorphic Tree Mappings for Machine TranslationJason EisnerMachine translation · 355 citations
- Contrastive Decoding: Open-ended Text Generation as OptimizationarXiv:2210.15097Xiang Lisa Li, Ari Holtzman, Daniel Fried, et al.2022 · 253 citations
- Efficient Parsing for Bilexical Context-Free Grammars and Head Automaton GrammarsAnnual Meeting of the Association for Computational Linguistics (ACL)Jason Eisner, Giorgio Satta1999 · 248 citations
- Constrained Language Models Yield Few-Shot Semantic Parsers ↗Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing · no summary yetRichard Shin et al.2021 · 238 citations
- UniMorph 2.0: Universal MorphologyLanguage Resources and Evaluation Conference (LREC)Christo Kirov, Ryan Cotterell, John Sylak-Glassman, et al.2018 · 223 citations
- Minimum Risk Annealing for Training Log-Linear ModelsAnnual Meeting of the Association for Computational Linguistics (ACL)David A. Smith, Jason Eisner2006 · 219 citations
- Dependency Parsing by Belief PropagationConference on Empirical Methods in Natural Language Processing (EMNLP)David Smith, Jason Eisner2008 · 198 citations
- The CoNLL–SIGMORPHON 2018 Shared Task: Universal Morphological ReinflectionConference on Computational Natural Language Learning (CoNLL)Ryan Cotterell, Christo Kirov, John Sylak-Glassman, et al.2018 · 181 citations
- Are All Languages Equally Hard to Language-Model?Conference of the North American Chapter of the Association for Computational Linguistics (NAACL)Ryan Cotterell, Sabrina J. Mielke, Jason Eisner, et al.2018 · 148 citations
- Quasi-Synchronous Grammars: Alignment by Soft Projection of Syntactic DependenciesDavid Smith, Jason EisnerMachine translation · 135 citations
- What Kind of Language Is Hard to Language-Model?Annual Meeting of the Association for Computational Linguistics (ACL)Sabrina J. Mielke, Ryan Cotterell, Kyle Gorman, et al.2019 · 132 citations
- Task-Oriented Dialogue as Dataflow SynthesisTransactions of the Association for Computational Linguistics (TACL)Jacob Andreas, John Bufe, David Burkett, et al.2020 · 121 citations
- Contrastive Decoding: Open-ended Text Generation as Optimization ↗Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · no summary yetXiang Lisa Li et al.2023 · 114 citations
- Parser Adaptation and Projection with Quasi-Synchronous Grammar Features ↗Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing · no summary yetDavid A. Smith, Jason Eisner2009 · 108 citations
- Weighting Finite-State Transductions With Neural Context ↗Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies · no summary yetPushpendre Rastogi, Ryan Cotterell, Jason Eisner2016 · 102 citations
- The Galactic Dependencies Treebanks: Getting More Data by Synthesizing New LanguagesDingquan Wang, Jason EisnerEnglish · 99 citations
- Modeling Word Forms Using Latent Underlying Morphs and PhonologyTransactions of the Association for Computational Linguistics (TACL)Ryan Cotterell, Nanyun Peng, Jason Eisner2015 · 98 citations
- LLM-Rubric: A Multidimensional, Calibrated Approach to Automated Evaluation of Natural Language TextsAnnual Meeting of the Association for Computational Linguistics (ACL)Helia Hashemi, Jason Eisner, Corby Rosset, et al.2024 · 88 citations
- Specializing Word Embeddings (for Parsing) by Information Bottleneck ↗Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) · no summary yetXiang Lisa Li, Jason Eisner2019 · 88 citations
- Morphological Smoothing and Extrapolation of Word Embeddings ↗Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · no summary yetRyan Cotterell, Hinrich Schütze, Jason Eisner2016 · 87 citations
- On the Complexity and Typology of Inflectional Morphological SystemsTransactions of the Association for Computational Linguistics (TACL)Ryan Cotterell, Christo Kirov, Mans Hulden, et al.2019 · 81 citations
- Machine Translation System Combination using ITG-based Alignments ↗Proceedings of ACL-08: HLT, Short Papers · no summary yetDamianos Karakos et al.2008 · 81 citations
- Decision-Oriented Dialogue for Human-AI CollaborationTransactions of the Association for Computational Linguistics (TACL)Jessy Lin, Nicholas Tomlin, Jacob Andreas, et al.2024 · 57 citations
- Surface Statistics of an Unknown Language Indicate How to Parse ItTransactions of the Association for Computational Linguistics (TACL)Dingquan Wang, Jason Eisner2018 · 30 citations
- Fine-Grained Prediction of Syntactic Typology: Discovering Latent Structure with Supervised LearningTransactions of the Association for Computational Linguistics (TACL)Dingquan Wang, Jason Eisner2017 · 28 citations
- Easy-first Coreference ResolutionInternational Conference on Computational Linguistics (COLING)Veselin Stoyanov, Jason Eisner2012 · 26 citations
- Non-Programmers Can Label Programs Indirectly via Active Examples: A Case Study with Text-to-SQL ↗Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing · no summary yetRuiqi Zhong et al.2023 · 15 citations
- The Whole Truth and Nothing But the Truth: Faithful and Controllable Dialogue Response Generation with Dataflow Transduction and Constrained Decoding ↗Findings of the Association for Computational Linguistics: ACL 2023 · no summary yetHao Fang et al.2023 · 6 citations
- LLMs Know More About Numbers than They Can Say ↗Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 2: Short Papers) · no summary yetFengting Yuchi, Li Du, Jason Eisner2026
This page in Markdown → https://md.research.elamur.ai/free/en/authors/jason-eisner/works/