--- title: "Sharon Goldwater — papers and cards" description: "Sharon Goldwater: 4 paper cards in the Research library (2018–2022), with what each paper is about, the ideas Mova took from it, and the co-authors." canonical: "https://research.elamur.ai/free/en/authors/sharon-goldwater/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/sharon-goldwater/) [home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / Sharon Goldwater # Sharon Goldwater 4 paper cards in the Research library · 2018–2022 Sharon Goldwater wrote 4 of the papers Mova reads, in 2018–2022, most of them on [Universal Dependencies](https://md.research.elamur.ai/free/en/topics/universal-dependencies/), [Machine translation](https://md.research.elamur.ai/free/en/topics/machine-translation/); often with [Ida Szubert](https://md.research.elamur.ai/free/en/authors/ida-szubert/), [Mark Steedman](https://md.research.elamur.ai/free/en/authors/mark-steedman/), [Nathan Schneider](https://md.research.elamur.ai/free/en/authors/nathan-schneider/). [OpenAlex](https://openalex.org/A5075564798) · [ORCID](https://orcid.org/0000-0002-7298-0947) · [**h-index 41**](https://openalex.org/authors/A5075564798) · [6473 citations](https://openalex.org/authors/A5075564798) · [170 works](https://openalex.org/works?filter=author.id:A5075564798) — openalex-snapshot, 2026-10-14 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=Sharon+Goldwater) · [Semantic Scholar](https://www.semanticscholar.org/search?q=Sharon+Goldwater) · [dblp](https://dblp.org/search?q=Sharon+Goldwater) · [ACL Anthology](https://aclanthology.org/search/?q=Sharon+Goldwater) · [ORCID](https://orcid.org/orcid-search/search?searchQuery=Sharon+Goldwater) Topics: [Universal Dependencies](https://md.research.elamur.ai/free/en/topics/universal-dependencies/) 1 · [Machine translation](https://md.research.elamur.ai/free/en/topics/machine-translation/) 1 ## Papers 1. **[Universal Dependencies and Semantics for English and Hebrew Child-directed Speech](https://md.research.elamur.ai/free/en/papers/ud-2022-szubert-universal-dependencies-semantics-english-hebrew/)** *(2022)* The authors annotate child-directed speech in English (the Adam corpus of CHILDES, 18,113 utterances) and Hebrew (the Hagar corpus, 24,172 utterances) with UD, and then convert the UD trees into logical forms, a meaning representation for acquisition models. 2. **[Cross-linguistically Consistent Semantic and Syntactic Annotation of Child-directed Speech](https://md.research.elamur.ai/free/en/papers/langstream-2021-szubert-cross-linguistically-consistent-semantic-syntactic/)** *(2021)* The paper proposes a two-step method for annotating child-directed speech (CDS) in CHILDES. First, the utterances get Universal Dependencies (UD) trees, starting from the existing dependency annotation and then hand-corrected. Second, sentential logical forms (LFs) are produced from the UD trees by unlexicalised… 3. **[Are we there yet? Encoder-decoder neural networks as cognitive models of English past tense inflection](https://md.research.elamur.ai/free/en/papers/corkery-2019-are-we-there-yet-encoder/)** *(2019)* Kirov and Cotterell (2018) reported that an encoder-decoder network with attention fits human nonce-word past tenses better than an older rule model. 4. **[Evaluating Historical Text Normalization Systems: How Well Do They Generalize?](https://md.research.elamur.ai/free/en/papers/robertson-2018-evaluating-historical-text-normalization-systems/)** *(2018)* The paper argues that normalization systems are judged badly. Most reports give one accuracy over all tokens, but in historical text most test tokens were seen in training, and for those a memorization baseline (map each form to its most frequent modern form in training) is very hard to beat. The authors compare two… ## Co-authors (9) - [Ida Szubert](https://md.research.elamur.ai/free/en/authors/ida-szubert/) ×2 - [Mark Steedman](https://md.research.elamur.ai/free/en/authors/mark-steedman/) ×2 - [Nathan Schneider](https://md.research.elamur.ai/free/en/authors/nathan-schneider/) ×2 - [Omri Abend](https://md.research.elamur.ai/free/en/authors/omri-abend/) ×2 - [Samuel Gibbon](https://md.research.elamur.ai/free/en/authors/samuel-gibbon/) ×2 - Alexander Robertson - [Louis Mahon](https://md.research.elamur.ai/free/en/authors/louis-mahon/) - Maria Corkery - [Yevgen Matusevych](https://md.research.elamur.ai/free/en/authors/yevgen-matusevych/) ## More papers in the library (5) Pages of the Research library: our summary, the ideas, references and who cites each. - [A framework for analyzing concept representations in neural models](https://md.research.elamur.ai/free/en/papers/naowarat-2026-framework-analyzing-concept-representations-neural/) — Burin Naowarat, Hao Tang, Sharon Goldwater · 2026 - [Estimating the Level of Dialectness Predicts Interannotator Agreement in Multi-dialect Arabic Datasets](https://md.research.elamur.ai/free/en/papers/keleg-2024-estimating-level-dialectness-predicts-interannotator/) — Amr Keleg, Walid Magdy, Sharon Goldwater · 2024 - [Lexical Generalization in CCG Grammar Induction for Semantic Parsing](https://md.research.elamur.ai/free/en/papers/kwiatkowski-2011-lexical-generalization-ccg-grammar-induction/) — Tom Kwiatkowski, Luke Zettlemoyer, Sharon Goldwater, et al. · 2011 - [A fully Bayesian approach to unsupervised part-of-speech tagging](https://md.research.elamur.ai/free/en/papers/goldwater-2007-fully-bayesian-approach-unsupervised-part/) — Sharon Goldwater, Tom Griffiths · 2007 - [Bayesian Inference for PCFGs via Markov Chain Monte Carlo](https://md.research.elamur.ai/free/en/papers/johnson-2007-bayesian-inference-pcfgs-markov-chain/) — Mark Johnson, Thomas Griffiths, Sharon Goldwater · 2007