[Mova](https://md.mova.elamur.ai/free/en/) · [this page in HTML](https://mova.elamur.ai/free/en/docs/papers/authors/jonas-kuhn/) [home](https://md.mova.elamur.ai/free/en/) / [docs](https://md.mova.elamur.ai/free/en/docs/) / [papers](https://md.mova.elamur.ai/free/en/docs/papers/) / [authors](https://md.mova.elamur.ai/free/en/docs/papers/authors/) / Jonas Kuhn # Jonas Kuhn 11 paper cards in Mova's library · 2011–2021 Jonas Kuhn wrote 11 of the papers Mova reads, in 2011–2021, most of them on [Dependency parsing](https://md.mova.elamur.ai/free/en/docs/papers/topics/dependency-parsing/), [Machine translation](https://md.mova.elamur.ai/free/en/docs/papers/topics/machine-translation/), [Universal Dependencies](https://md.mova.elamur.ai/free/en/docs/papers/topics/universal-dependencies/); often with [Xiang Yu](https://md.mova.elamur.ai/free/en/docs/papers/authors/xiang-yu/), [Agnieszka Falenska](https://md.mova.elamur.ai/free/en/docs/papers/authors/agnieszka-falenska/), [Anders Björkelund](https://md.mova.elamur.ai/free/en/docs/papers/authors/anders-bjorkelund/). [OpenAlex](https://openalex.org/A5101531241) · [ORCID](https://orcid.org/0000-0003-2860-5960) · [**h-index 22**](https://openalex.org/authors/A5101531241) · [1569 citations](https://openalex.org/authors/A5101531241) · [192 works](https://openalex.org/works?filter=author.id:A5101531241) — openalex, 2026-10-18 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=Jonas+Kuhn) · [Semantic Scholar](https://www.semanticscholar.org/search?q=Jonas+Kuhn) · [dblp](https://dblp.org/search?q=Jonas+Kuhn) · [ACL Anthology](https://aclanthology.org/search/?q=Jonas+Kuhn) · [ORCID](https://orcid.org/orcid-search/search?searchQuery=Jonas+Kuhn) Topics: [Dependency parsing](https://md.mova.elamur.ai/free/en/docs/papers/topics/dependency-parsing/) 4 · [Machine translation](https://md.mova.elamur.ai/free/en/docs/papers/topics/machine-translation/) 4 · [Universal Dependencies](https://md.mova.elamur.ai/free/en/docs/papers/topics/universal-dependencies/) 3 · [Treebanks](https://md.mova.elamur.ai/free/en/docs/papers/topics/treebanks/) 3 · [Coreference resolution](https://md.mova.elamur.ai/free/en/docs/papers/topics/coreference-resolution/) 1 · [Part-of-speech tagging](https://md.mova.elamur.ai/free/en/docs/papers/topics/part-of-speech-tagging/) 1 ## Ideas Mova took (2) From the ideas ledger: an idea tried, kept or queued, or measured with no gain, and what it gave. - **measured, no gain** — en/src/parse.rs: add a dynamic oracle for arc-standard that charges each action by the number of gold arcs it makes unreachable, and train with it; measure cv LAS on the train folds against the static oracle, two runs each. *([Approximate Dynamic Oracle for Dependency Parsing with…](https://md.mova.elamur.ai/free/en/docs/papers/ud-2018-yu-approximate-dynamic-oracle-dependency-parsing/) · approximate arc-standard dynamic oracle with exploration, greedy parser, EWT dev our tags: 77.67 -> 76.40 (variants 76.04-76.49; 20 epochs 77.50 -> 76.47)…)* - **measured, no gain** — Add a bridging pass after coreference in coref/src/sieve.rs, with high-precision rules from the paper's list, only for mentions the sieves left unlinked and only for unmodified definites (the N): building part → the latest building (house, castle, hut … the… *([Bridging resolution: Task definition, corpus resources and…](https://md.mova.elamur.ai/free/en/docs/papers/roesiger-2018-bridging-resolution-task-definition-corpus/) · bridging for unmodified «the N» (building part, relative, body part → latest building/person, ≤3 sentences) scored against GUM Bridge=: 3 links on dev (1…)* ## Papers 1. **[Applying Occam's Razor to Transformer-Based Dependency Parsing: What Works, What Doesn't, and What is Really Necessary](https://md.mova.elamur.ai/free/en/docs/papers/grunewald-2021-applying-occam-s-razor-transformer/)** *(2021)* `measured` Modern graph-based dependency parsers for Universal Dependencies rely on transformer embeddings but differ in several design choices: which pretrained model to use, whether to add LSTM layers, and whether to train jointly on POS and morphology. 2. **[CCOHA: Clean Corpus of Historical American English](https://md.mova.elamur.ai/free/en/docs/papers/alatrash-2020-ccoha-clean-corpus-historical-american/)** *(2020)* The paper cleans the downloadable version of the Corpus of Historical American English (COHA), about 406 million words from 1810 to 2009. 3. **[Fast and Accurate Non-Projective Dependency Tree Linearization](https://md.mova.elamur.ai/free/en/docs/papers/yu-2020-fast-accurate-non-projective-dependency/)** *(2020)* The paper treats linearization as a travelling-salesman problem. A biaffine model gives the cost of putting one token before another, and the costs are solved per subtree with a greedy TSP solver. The subtree orders are then combined into a projective tree. A transition system, borrowed from non-projective parsing… 4. **[Integrating Graph-Based and Transition-Based Dependency Parsers in the Deep Contextualized Era](https://md.mova.elamur.ai/free/en/docs/papers/ud-2020-falenska-integrating-graph-based-transition-based/)** *(2020)* The paper asks whether combining a graph-based and a transition-based parser still helps once the parsers use BiLSTM encoders and ELMo embeddings. 5. **[Identifying and Handling Cross-Treebank Inconsistencies in UD: A Pilot Study](https://md.mova.elamur.ai/free/en/docs/papers/donicke-2020-identifying-handling-cross-treebank-inconsistencies/)** *(2020)* Treebanks of the same language in Universal Dependencies share one label set, but individual relations are often annotated differently from treebank to treebank, which hurts merging corpora and transferring parsers. 6. **[Head-First Linearization with Tree-Structured Representation](https://md.mova.elamur.ai/free/en/docs/papers/yu-2019-head-first-linearization-tree-structured/)** *(2019)* The paper linearises a dependency tree, that is, it finds the word order of an unordered tree. It has two parts. The encoder is a bidirectional Tree-LSTM that passes information first up the tree and then down, so that each token sees the whole tree. The decoder is head-first: it starts at the head and attaches… 7. **[Approximate Dynamic Oracle for Dependency Parsing with Reinforcement Learning](https://md.mova.elamur.ai/free/en/docs/papers/ud-2018-yu-approximate-dynamic-oracle-dependency-parsing/)** *(2018)* A dynamic oracle tells a transition parser which action is best from a state the parser itself got into by mistake, so that training covers its own errors. 8. **[Bridging resolution: Task definition, corpus resources and rule-based experiments](https://md.mova.elamur.ai/free/en/docs/papers/roesiger-2018-bridging-resolution-task-definition-corpus/)** *(2018)* Bridging anaphors are new referents that are interpreted through an earlier, non-identical one («The city is planning a new town hall and the construction will start next week» — the construction of the town hall). 9. **['IMS at the CoNLL 2017 UD Shared Task: CRFs and Perceptrons Meet Neural Networks'](https://md.mova.elamur.ai/free/en/docs/papers/ud-2017-bjorkelund-ims-conll-2017-ud-shared/)** *(2017)* This is the IMS system for the CoNLL 2017 raw-text-to-UD task, which finished third overall and second on the surprise languages. 10. **[Generating Non-Projective Word Order in Statistical Linearization](https://md.mova.elamur.ai/free/en/docs/papers/bohnet-2012-generating-non-projective-word-order/)** *(2012)* A projective linearizer can only produce word orders in which no two edges cross, and many languages need crossings. 11. **[Underspecifying and Predicting Voice for Surface Realisation Ranking](https://md.mova.elamur.ai/free/en/docs/papers/zarrie-2011-underspecifying-predicting-voice-surface-realisation/)** *(2011)* The authors regenerate German corpus sentences with a reversible LFG grammar and a ranker that chooses among the candidate realisations. ## Co-authors (18) - [Xiang Yu](https://md.mova.elamur.ai/free/en/docs/papers/authors/xiang-yu/) ×5 - [Agnieszka Falenska](https://md.mova.elamur.ai/free/en/docs/papers/authors/agnieszka-falenska/) ×3 - [Anders Björkelund](https://md.mova.elamur.ai/free/en/docs/papers/authors/anders-bjorkelund/) ×3 - [Ngoc Thang Vu](https://md.mova.elamur.ai/free/en/docs/papers/authors/ngoc-thang-vu/) ×3 - [Annemarie Friedrich](https://md.mova.elamur.ai/free/en/docs/papers/authors/annemarie-friedrich/) - [Aoife Cahill](https://md.mova.elamur.ai/free/en/docs/papers/authors/aoife-cahill/) - [Arndt Riester](https://md.mova.elamur.ai/free/en/docs/papers/authors/arndt-riester/) - [Bernd Bohnet](https://md.mova.elamur.ai/free/en/docs/papers/authors/bernd-bohnet/) - Dominik Schlechtweg - [Ina Roesiger](https://md.mova.elamur.ai/free/en/docs/papers/authors/ina-roesiger/) - Reem Alatrash - [Sabine Schulte im Walde](https://md.mova.elamur.ai/free/en/docs/papers/authors/sabine-schulte-im-walde/) - Simon Tannert - [Sina Zarrieß](https://md.mova.elamur.ai/free/en/docs/papers/authors/sina-zarries/) - Sina Zarriess - [Stefan Grünewald](https://md.mova.elamur.ai/free/en/docs/papers/authors/stefan-grunewald/) - [Tillmann Dönicke](https://md.mova.elamur.ai/free/en/docs/papers/authors/tillmann-donicke/) - [Wolfgang Seeker](https://md.mova.elamur.ai/free/en/docs/papers/authors/wolfgang-seeker/) - [← previous Jon Oberlander](https://md.mova.elamur.ai/free/en/docs/papers/authors/jon-oberlander/) - [next → Jonathan Dunn](https://md.mova.elamur.ai/free/en/docs/papers/authors/jonathan-dunn/) - [↑ back to Authors](https://md.mova.elamur.ai/free/en/docs/papers/authors/)