--- title: "Luke Zettlemoyer — author profile and papers" description: "Luke Zettlemoyer, University of Washington: 58 papers on Elamur Research (2011–2025), h-index 91 — affiliations, topics, co-authors and who cites them in…" canonical: "https://research.elamur.ai/free/en/authors/luke-zettlemoyer/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/luke-zettlemoyer/) [home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / Luke Zettlemoyer # Luke Zettlemoyer 58 papers on this site · 2011–2025 · page 1 of 3 current affiliation [University of Washington](https://ror.org/00cvxb145), Seattle, United States; [Meta (United States)](https://ror.org/01zbnvs85), Menlo Park, United States Luke Zettlemoyer has 58 papers on this site, in 2011–2025, most of them on [Language models & pretraining](https://md.research.elamur.ai/free/en/topics/language-models/), [Question answering](https://md.research.elamur.ai/free/en/topics/question-answering/), [Coreference resolution](https://md.research.elamur.ai/free/en/topics/coreference-resolution/); often with [Mike Lewis](https://md.research.elamur.ai/free/en/authors/mike-lewis/), [Hannaneh Hajishirzi](https://md.research.elamur.ai/free/en/authors/hannaneh-hajishirzi/), [Sewon Min](https://md.research.elamur.ai/free/en/authors/sewon-min/). 10 of them are among the papers [Mova](https://md.research.elamur.ai/free/en/projects/mova/) reads. [OpenAlex](https://openalex.org/A5067919401) · [ORCID](https://orcid.org/0009-0008-8296-0764) · [**h-index 91**](https://openalex.org/authors/A5067919401) · [492 works](https://openalex.org/works?filter=author.id:A5067919401) · [78 722 citations](https://openalex.org/works?filter=author.id:A5067919401&sort=cited_by_count:desc) OpenAlex, 2026-10-14 [58 works on this site](https://md.research.elamur.ai/free/en/authors/luke-zettlemoyer/#papers) · [21 467 citations in our library](https://md.research.elamur.ai/free/en/authors/luke-zettlemoyer/cited-by/) · 41 more works in our library The profile is the library's match of the name; two people with one name are not always told apart. Elsewhere: [Google Scholar](https://scholar.google.com/citations?view_op=search_authors&mauthors=Luke+Zettlemoyer) · [Semantic Scholar](https://www.semanticscholar.org/search?q=Luke+Zettlemoyer) · [dblp](https://dblp.org/search?q=Luke+Zettlemoyer) · [ACL Anthology](https://aclanthology.org/search/?q=Luke+Zettlemoyer) ## Affiliations - [University of Washington](https://ror.org/00cvxb145) · Seattle, United States —current · 2010–2026 on 251 papers · employment (ORCID) - [Meta (United States)](https://ror.org/01zbnvs85) · Menlo Park, United States —current · 2019–2026 on 65 papers - [Allen Institute for Artificial Intelligence](https://ror.org/05w520734) · Seattle, United States —2017–2025 on 21 papers - [Massachusetts Institute of Technology](https://ror.org/042nb2s44) · Cambridge, United States —2005–2025 on 12 papers - [Meta (United Kingdom)](https://ror.org/020ye1821) · London, United Kingdom —2019–2025 on 12 papers - [University of Chicago](https://ror.org/024mw5h28) · Chicago, United States —2025 on 2 papers - [Carnegie Mellon University](https://ror.org/05x2bcf33) · Pittsburgh, United States —2018–2024 on 13 papers - [New York University](https://ror.org/0190ak572) · New York, United States —2024 on 2 papers - [University of Hong Kong](https://ror.org/02zhqgq86) · Pok Fu Lam, Hong Kong —2022–2023 on 3 papers - [Johns Hopkins University](https://ror.org/00za53h95) · Baltimore, United States —2020–2023 on 2 papers From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 25 more institutions on single bylines are not listed. ## Topics [Language models & pretraining 13](https://md.research.elamur.ai/free/en/topics/language-models/) · [Question answering 10](https://md.research.elamur.ai/free/en/topics/question-answering/) · [Coreference resolution 7](https://md.research.elamur.ai/free/en/topics/coreference-resolution/) · [Semantic role labeling 7](https://md.research.elamur.ai/free/en/topics/semantic-role-labeling/) · [Text generation 4](https://md.research.elamur.ai/free/en/topics/text-generation/) · [Information retrieval & search 4](https://md.research.elamur.ai/free/en/topics/information-retrieval/) · [Semantic parsing & meaning representation 4](https://md.research.elamur.ai/free/en/topics/semantic-parsing/) · [Reasoning 3](https://md.research.elamur.ai/free/en/topics/reasoning/) · [Named entity recognition 2](https://md.research.elamur.ai/free/en/topics/named-entity-recognition/) · [Machine translation 2](https://md.research.elamur.ai/free/en/topics/machine-translation/) · [Multilingual & cross-lingual NLP 2](https://md.research.elamur.ai/free/en/topics/multilingual-nlp/) · [Evaluation & benchmarks 2](https://md.research.elamur.ai/free/en/topics/evaluation-benchmarks/) · [Syntax & grammar formalisms 2](https://md.research.elamur.ai/free/en/topics/syntax-grammar/) · [Implicature 1](https://md.research.elamur.ai/free/en/topics/implicature/) · [Bias, fairness & safety 1](https://md.research.elamur.ai/free/en/topics/bias-fairness-safety/) ## Papers The most cited first (OpenAlex and our library). **1** [2](https://md.research.elamur.ai/free/en/authors/luke-zettlemoyer/page/2/) [3](https://md.research.elamur.ai/free/en/authors/luke-zettlemoyer/page/3/) [next →](https://md.research.elamur.ai/free/en/authors/luke-zettlemoyer/page/2/) 1. **[BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://md.research.elamur.ai/free/en/papers/lewis-2020-bart-denoising-sequence-sequence-pre/)** *(2020 · 12 752 citations)* Earlier self-supervised pre-training methods were usually built either for understanding tasks, like BERT-style masked models, or for generation, like GPT-style left-to-right models. 2. **[TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension](https://md.research.elamur.ai/free/en/papers/joshi-2017-triviaqa-large-scale-distantly-supervised/)** *(2017 · 3 204 citations)* Existing reading comprehension benchmarks tend to stress only one difficulty, and models quickly approach human scores on them. 3. **[SpanBERT: Improving Pre-training by Representing and Predicting Spans](https://md.research.elamur.ai/free/en/papers/joshi-2019-spanbert-improving-pre-training-representing/)** *(2019 · 2 580 citations)* Masked language models like BERT hide individual subword tokens. Yet many NLP tasks, such as extractive question answering and coreference resolution, depend on how whole multi-token spans relate to each other. SpanBERT changes BERT's pre-training in two ways to fit this better. First, it masks contiguous random… 4. **[Toolformer: Language Models Can Teach Themselves to Use Tools](https://md.research.elamur.ai/free/en/papers/schick-2023-toolformer-language-models-can-teach/)** *(2023 · 2 020 citations)* Large language models can tackle new tasks from a few examples, yet they often fail at things small specialized systems do well, such as exact arithmetic, fact lookup, or knowing the current date. 5. **[AllenNLP: A Deep Semantic Natural Language Processing Platform](https://md.research.elamur.ai/free/en/papers/gardner-2018-allennlp-deep-semantic-natural-language/)** *(2018 · 1 804 citations)* Code for neural NLP research is often hard to rerun, debug, and extend. Important hyperparameters get lost among low-level details, and baselines are frequently rebuilt from scratch. A team from the Allen Institute for AI introduces AllenNLP, an open-source PyTorch library that makes deep learning experiments in NLP… 6. **[Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?](https://md.research.elamur.ai/free/en/papers/min-2022-rethinking-role-demonstrations-what-makes/)** *(2022 · 1 423 citations)* In-context learning lets a large language model handle a new task by reading a few labeled examples in its prompt, with no weight updates. 7. **[End-to-end Neural Coreference Resolution](https://md.research.elamur.ai/free/en/papers/lee-2017-end-end-neural-coreference-resolution/)** *(2017 · 1 277 citations)* The first coreference model trained end to end without a parser or a mention detector. Every span up to 10 words is a candidate; each span gets a mention score and each pair an antecedent score, and a span chooses among all earlier spans plus a dummy antecedent fixed at score 0 (no link, or not a mention). Span… 8. **[QuAC: Question Answering in Context](https://md.research.elamur.ai/free/en/papers/choi-2018-quac-question-answering-context/)** *(2018 · 1 057 citations)* QuAC is a large crowdsourced resource for machine reading comprehension in dialogs where a learner seeks information. 9. **[FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation](https://md.research.elamur.ai/free/en/papers/min-2023-factscore-fine-grained-atomic-evaluation/)** *(2023 · 970 citations)* Checking the factuality of long outputs from large language models is hard for two reasons. One response usually mixes correct and incorrect claims, so a single yes/no verdict per sentence or response discards useful information. Verifying every claim by hand is also slow and expensive. The authors propose FActScore… 10. **[Adversarial Example Generation with Syntactically Controlled Paraphrase Networks](https://md.research.elamur.ai/free/en/papers/iyyer-2018-adversarial-example-generation-syntactically-controlled/)** *(2018 · 936 citations)* NLP datasets often lack linguistic variety, so models trained on them can fail when the same meaning appears in a different sentence structure. 11. **[Mask-Predict: Parallel Decoding of Conditional Masked Language Models](https://md.research.elamur.ai/free/en/papers/ghazvininejad-2019-mask-predict-parallel-decoding-conditional/)** *(2019 · 671 citations)* Standard neural machine translation produces output one token at a time, which makes decoding slow. Earlier non-autoregressive (parallel) methods were faster but lost considerable accuracy. The authors propose conditional masked language models (CMLMs). These are transformer encoder-decoders whose decoder attends in… 12. **[Scalable Zero-shot Entity Linking with Dense Entity Retrieval](https://md.research.elamur.ai/free/en/papers/wu-2020-scalable-zero-shot-entity-linking/)** *(2020 · 618 citations)* Entity linking means mapping each mention in a text to an entry in a knowledge base that may hold millions of entities. 13. **[Higher-Order Coreference Resolution with Coarse-to-Fine Inference](https://md.research.elamur.ai/free/en/papers/lee-2018-higher-order-coreference-resolution-coarse/)** *(2018 · 612 citations)* First-order coreference systems score only pairs of mentions. Each link is decided on its own, so a cluster can be made of links that each look plausible but don't fit together. In the paper's example, an ambiguous "you" connects a singular "I" with a plural "all of you". The authors extend the end-to-end… 14. **[Weakly Supervised Learning of Semantic Parsers for Mapping Instructions to Actions](https://md.research.elamur.ai/free/en/papers/artzi-2013-weakly-supervised-learning-semantic-parsers/)** *(2013 · 592 citations)* The authors train a system to map natural-language navigation instructions to sequences of agent actions on a map. 15. **[Deep Semantic Role Labeling: What Works and What's Next](https://md.research.elamur.ai/free/en/papers/he-2017-deep-semantic-role-labeling-what/)** *(2017 · 589 citations)* A neural SRL model that treats each predicate's arguments as BIO tags over the sentence, with no syntax input. 16. **[Evaluating Gender Bias in Machine Translation](https://md.research.elamur.ai/free/en/papers/stanovsky-2019-evaluating-gender-bias-machine-translation/)** *(2019 · 588 citations)* Machine translation from English into languages with grammatical gender often forces a system to decide a person's gender. 17. **[Dissecting Contextual Word Embeddings: Architecture and Representation](https://md.research.elamur.ai/free/en/papers/peters-2018-dissecting-contextual-word-embeddings-architecture/)** *(2018 · 585 citations)* Pretrained bidirectional language models (biLMs) such as ELMo improve many NLP tasks, but it was unclear whether the usual LSTM backbone matters or what the layers actually encode. 18. **[s1: Simple test-time scaling](https://md.research.elamur.ai/free/en/papers/muennighoff-2025-s1-simple-test-time-scaling/)** *(2025 · 584 citations)* The paper looks for the least machinery needed to reproduce what OpenAI's o1 showed: a model that gets more accurate when it is allowed to think longer at inference time. 19. **[Intrinsic Dimensionality Explains the Effectiveness of Language Model Fine-Tuning](https://md.research.elamur.ai/free/en/papers/aghajanyan-2021-intrinsic-dimensionality-explains-effectiveness-language/)** *(2021 · 530 citations)* The authors explain why huge pretrained language models with hundreds of millions of parameters can be fine-tuned with ordinary gradient descent on a few hundred or a few thousand labeled examples without overfitting. 20. **[BERT for Coreference Resolution: Baselines and Analysis](https://md.research.elamur.ai/free/en/papers/joshi-2019-bert-coreference-resolution-baselines-analysis/)** *(2019 · 488 citations)* This paper tests how much a pretrained BERT encoder helps coreference resolution. It also looks at where the resulting system still fails. The authors start from c2f-coref (Lee et al., 2018), a span-ranking model, and swap its LSTM encoder, which used ELMo and GloVe inputs, for a fine-tuned BERT. Long documents have… 21. **[REPLUG: Retrieval-Augmented Black-Box Language Models](https://md.research.elamur.ai/free/en/papers/shi-2023-replug-retrieval-augmented-black-box/)** *(2023 · 482 citations)* The most capable large language models are often reachable only through APIs, so their weights and hidden states cannot be changed or inspected. 22. **[Paraphrase-Driven Learning for Open Question Answering](https://md.research.elamur.ai/free/en/papers/fader-2013-paraphrase-driven-learning-open-question/)** *(2013 · 438 citations)* The paper tackles open-domain question answering over a noisy knowledge base built automatically by information extraction from web text. 23. **[Neural AMR: Sequence-to-Sequence Models for Parsing and Generation](https://md.research.elamur.ai/free/en/papers/konstas-2017-neural-amr-sequence-sequence-models/)** *(2017 · 425 citations)* The paper applies sequence-to-sequence neural models to both AMR parsing and AMR generation. The main obstacle is data sparsity, so the authors pretrain on millions of unlabelled Gigaword sentences: a parser labels them, a generator is pretrained on those pairs, and then both are fine-tuned on the 16,833 gold pairs.… 24. **[Emerging Cross-lingual Structure in Pretrained Language Models](https://md.research.elamur.ai/free/en/papers/conneau-2020-emerging-cross-lingual-structure-pretrained/)** *(2020 · 378 citations)* Multilingual masked language models such as mBERT and XLM transfer well across languages. Earlier work proposed explanations, such as a shared subword vocabulary, but tested them only on a single mBERT and never measured them systematically. The authors train bilingual MLMs on Wikipedia, pairing English with French… 25. **[Question-Answer Driven Semantic Role Labeling: Using Natural Language to Annotate Natural Language](https://md.research.elamur.ai/free/en/papers/he-2015-question-answer-driven-semantic-role/)** *(2015 · 322 citations)* The paper introduces question-answer driven semantic role labeling (QA-SRL): each verbal predicate is labeled with wh-questions, such as "Who finished something?", and each question is answered by phrases of the sentence. **1** [2](https://md.research.elamur.ai/free/en/authors/luke-zettlemoyer/page/2/) [3](https://md.research.elamur.ai/free/en/authors/luke-zettlemoyer/page/3/) [next →](https://md.research.elamur.ai/free/en/authors/luke-zettlemoyer/page/2/) ## Also in our library 41 more works of theirs are in our library without a page here yet; they will appear as we publish them. ## Co-authors here 12 of 128 co-authors with a page, the most papers together first. - [Mike Lewis](https://md.research.elamur.ai/free/en/authors/mike-lewis/) ×17 - [Hannaneh Hajishirzi](https://md.research.elamur.ai/free/en/authors/hannaneh-hajishirzi/) ×9 - [Sewon Min](https://md.research.elamur.ai/free/en/authors/sewon-min/) ×9 - [Luheng He](https://md.research.elamur.ai/free/en/authors/luheng-he/) ×7 - [Wen-tau Yih](https://md.research.elamur.ai/free/en/authors/wen-tau-yih/) ×7 - [Omer Levy](https://md.research.elamur.ai/free/en/authors/omer-levy/) ×6 - [Armen Aghajanyan](https://md.research.elamur.ai/free/en/authors/armen-aghajanyan/) ×5 - [Kenton Lee](https://md.research.elamur.ai/free/en/authors/kenton-lee/) ×5 - [Marjan Ghazvininejad](https://md.research.elamur.ai/free/en/authors/marjan-ghazvininejad/) ×5 - [Weijia Shi](https://md.research.elamur.ai/free/en/authors/weijia-shi/) ×5 - [Daniel S. Weld](https://md.research.elamur.ai/free/en/authors/daniel-s-weld/) ×4 - [Gabriel Stanovsky](https://md.research.elamur.ai/free/en/authors/gabriel-stanovsky/) ×4 ## Cited by Papers of our library cite their works 21 467 times (of the 140 884 papers whose bibliographies we read); [1 203 citing papers with a page here →](https://md.research.elamur.ai/free/en/authors/luke-zettlemoyer/cited-by/).