[Mova](https://md.mova.elamur.ai/free/en/) · [this page in HTML](https://mova.elamur.ai/free/en/docs/papers/authors/xiang-yu/) [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/) / Xiang Yu # Xiang Yu 5 paper cards in Mova's library · 2017–2020 Xiang Yu wrote 5 of the papers Mova reads, in 2017–2020, most of them on [Dependency parsing](https://md.mova.elamur.ai/free/en/docs/papers/topics/dependency-parsing/), [Universal Dependencies](https://md.mova.elamur.ai/free/en/docs/papers/topics/universal-dependencies/), [Treebanks](https://md.mova.elamur.ai/free/en/docs/papers/topics/treebanks/); often with [Jonas Kuhn](https://md.mova.elamur.ai/free/en/docs/papers/authors/jonas-kuhn/), [Ngoc Thang Vu](https://md.mova.elamur.ai/free/en/docs/papers/authors/ngoc-thang-vu/), [Agnieszka Falenska](https://md.mova.elamur.ai/free/en/docs/papers/authors/agnieszka-falenska/). [ORCID](https://orcid.org/0000-0001-9431-5131) 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=Xiang+Yu) · [Semantic Scholar](https://www.semanticscholar.org/search?q=Xiang+Yu) · [dblp](https://dblp.org/search?q=Xiang+Yu) · [ACL Anthology](https://aclanthology.org/search/?q=Xiang+Yu) · [ORCID](https://orcid.org/orcid-search/search?searchQuery=Xiang+Yu) Topics: [Dependency parsing](https://md.mova.elamur.ai/free/en/docs/papers/topics/dependency-parsing/) 2 · [Universal Dependencies](https://md.mova.elamur.ai/free/en/docs/papers/topics/universal-dependencies/) 2 · [Treebanks](https://md.mova.elamur.ai/free/en/docs/papers/topics/treebanks/) 2 · [Machine translation](https://md.mova.elamur.ai/free/en/docs/papers/topics/machine-translation/) 2 · [Part-of-speech tagging](https://md.mova.elamur.ai/free/en/docs/papers/topics/part-of-speech-tagging/) 1 ## Ideas Mova took (1) 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)…)* ## Papers 1. **[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… 2. **[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. 3. **[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… 4. **[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. 5. **['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. ## Co-authors (6) - [Jonas Kuhn](https://md.mova.elamur.ai/free/en/docs/papers/authors/jonas-kuhn/) ×5 - [Ngoc Thang Vu](https://md.mova.elamur.ai/free/en/docs/papers/authors/ngoc-thang-vu/) ×3 - [Agnieszka Falenska](https://md.mova.elamur.ai/free/en/docs/papers/authors/agnieszka-falenska/) ×2 - [Anders Björkelund](https://md.mova.elamur.ai/free/en/docs/papers/authors/anders-bjorkelund/) - Simon Tannert - [Tillmann Dönicke](https://md.mova.elamur.ai/free/en/docs/papers/authors/tillmann-donicke/) - [← previous Xavier Carreras](https://md.mova.elamur.ai/free/en/docs/papers/authors/xavier-carreras/) - [next → Xiaoqiang Luo](https://md.mova.elamur.ai/free/en/docs/papers/authors/xiaoqiang-luo/) - [↑ back to Authors](https://md.mova.elamur.ai/free/en/docs/papers/authors/)