--- title: "Anders Søgaard — papers and cards" description: "Anders Søgaard: 8 paper cards in the Research library (2013–2021), with what each paper is about, the ideas Mova took from it, and the co-authors." canonical: "https://research.elamur.ai/free/en/authors/anders-sogaard/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/anders-sogaard/) [home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / Anders Søgaard # Anders Søgaard 8 paper cards in the Research library · 2013–2021 Anders Søgaard wrote 8 of the papers Mova reads, in 2013–2021, most of them on [Coreference resolution](https://md.research.elamur.ai/free/en/topics/coreference-resolution/), [Treebanks](https://md.research.elamur.ai/free/en/topics/treebanks/), [Part-of-speech tagging](https://md.research.elamur.ai/free/en/topics/part-of-speech-tagging/); often with [Marcel Bollmann](https://md.research.elamur.ai/free/en/authors/marcel-bollmann/), [Joachim Bingel](https://md.research.elamur.ai/free/en/authors/joachim-bingel/), Anna Jørgensen. [OpenAlex](https://openalex.org/A5018138946) · [ORCID](https://orcid.org/0000-0001-5250-4276) · [**h-index 42**](https://openalex.org/authors/A5018138946) · [8345 citations](https://openalex.org/authors/A5018138946) · [438 works](https://openalex.org/works?filter=author.id:A5018138946) — 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=Anders+S%C3%B8gaard) · [Semantic Scholar](https://www.semanticscholar.org/search?q=Anders+S%C3%B8gaard) · [dblp](https://dblp.org/search?q=Anders+S%C3%B8gaard) · [ACL Anthology](https://aclanthology.org/search/?q=Anders+S%C3%B8gaard) · [ORCID](https://orcid.org/orcid-search/search?searchQuery=Anders+S%C3%B8gaard) Topics: [Coreference resolution](https://md.research.elamur.ai/free/en/topics/coreference-resolution/) 1 · [Treebanks](https://md.research.elamur.ai/free/en/topics/treebanks/) 1 · [Part-of-speech tagging](https://md.research.elamur.ai/free/en/topics/part-of-speech-tagging/) 1 ## Papers 1. **[Ellipsis Resolution as Question Answering: An Evaluation](https://md.research.elamur.ai/free/en/papers/eacl-2021-aralikatte-ellipsis-resolution-as-question-answering/)** *(2021)* The paper treats ellipsis resolution as a reading-comprehension problem. The elided clause becomes a question, and the antecedent becomes the answer span in the preceding text. The authors train BERT-based models on sluice ellipsis and VP ellipsis, first alone and then jointly with question-answering and coreference… 2. **[Historical Text Normalization with Delayed Rewards](https://md.research.elamur.ai/free/en/papers/acl-2019-flachs-historical-text-normalization-delayed-rewards/)** *(2019)* Sequence-to-sequence normalisers are usually trained with token-level maximum likelihood. The paper fine-tunes such a model with policy gradient, so that the training signal is the exact match of the whole normalisation, a delayed reward. Six historical datasets are used. Fine-tuning reduces the error by 20% for… 3. **[Few-Shot and Zero-Shot Learning for Historical Text Normalization](https://md.research.elamur.ai/free/en/papers/aclbulk-2019-bollmann-few-shot-zero-shot-learning/)** *(2019)* The paper evaluates 63 multi-task configurations of an encoder-decoder normaliser on ten datasets in eight languages. 4. **[Multi-task learning for historical text normalization: Size matters](https://md.research.elamur.ai/free/en/papers/aclbulk-2018-bollmann-multi-task-learning-historical-text/)** *(2018)* The paper asks when multi-task learning helps historical normalisation. It tests an encoder-decoder model with and without auxiliary tasks on 10 datasets from 8 languages, from German and English to Hungarian, Icelandic, Slovene, Spanish, Portuguese and Swedish. Most datasets either always gain or always lose from… 5. **[Learning attention for historical text normalization by learning to pronounce](https://md.research.elamur.ai/free/en/papers/aclbulk-2017-bollmann-learning-attention-historical-text-normalization/)** *(2017)* The paper treats historical normalisation as a character-level transduction with an encoder-decoder RNN, so no explicit character alignment is needed. 6. **[Learning a POS tagger for AAVE-like language](https://md.research.elamur.ai/free/en/papers/jorgensen-2016-learning-pos-tagger-aave-like/)** *(2016)* Newswire POS taggers do poorly on subtitles, hip-hop lyrics and tweets in African-American Vernacular English. 7. **[Improving historical spelling normalization with bi-directional LSTMs and multi-task learning](https://md.research.elamur.ai/free/en/papers/aclbulk-2016-bollmann-improving-historical-spelling-normalization-bi/)** *(2016)* The paper frames historical spelling normalisation as character-level sequence labelling and uses a bi-directional LSTM for it. 8. **[An Empirical Study of Differences between Conversion Schemes and Annotation Guidelines](https://md.research.elamur.ai/free/en/papers/bank-2013-sogaard-empirical-study-differences-between-conversion/)** *(2013)* Many dependency treebanks are converted from constituency treebanks, and different conversion schemes make different choices about heads and relation labels. ## Co-authors (9) - [Marcel Bollmann](https://md.research.elamur.ai/free/en/authors/marcel-bollmann/) ×5 - [Joachim Bingel](https://md.research.elamur.ai/free/en/authors/joachim-bingel/) ×2 - Anna Jørgensen - [Daniel Hardt](https://md.research.elamur.ai/free/en/authors/daniel-hardt/) - Dirk Hovy - [Matthew Lamm](https://md.research.elamur.ai/free/en/authors/matthew-lamm/) - Natalia Korchagina - Rahul Aralikatte - Simon Flachs ## More papers in the library (9) Pages of the Research library: our summary, the ideas, references and who cites each. - [Model-based Annotation of Coreference](https://md.research.elamur.ai/free/en/papers/aralikatte-2020-model-based-annotation-coreference/) — Rahul Aralikatte, Anders Søgaard · 2020 - [Rewarding Coreference Resolvers for Being Consistent with World Knowledge](https://md.research.elamur.ai/free/en/papers/aralikatte-2019-rewarding-coreference-resolvers-being-consistent/) — Rahul Aralikatte, Heather Lent, Ana Valeria Gonzalez, et al. · 2019 - [On the Limitations of Unsupervised Bilingual Dictionary Induction](https://md.research.elamur.ai/free/en/papers/sogaard-2018-limitations-unsupervised-bilingual-dictionary-induction/) — Anders Søgaard, Sebastian Ruder, Ivan Vulić · 2018 - [Cross-lingual RST Discourse Parsing](https://md.research.elamur.ai/free/en/papers/braud-2017-cross-lingual-rst-discourse-parsing/) — Chloé Braud, Maximin Coavoux, Anders Søgaard · 2017 - [Using millions of emoji occurrences to learn any-domain representations for detecting sentiment, emotion and sarcasm](https://md.research.elamur.ai/free/en/papers/felbo-2017-millions-emoji-occurrences-learn-any/) — Bjarke Felbo, Alan Mislove, Anders Søgaard, et al. · 2017 - [Deep multi-task learning with low level tasks supervised at lower layers](https://md.research.elamur.ai/free/en/papers/sogaard-2016-deep-multi-task-learning-low/) — Anders Søgaard, Yoav Goldberg · 2016 - [Multi-view and multi-task training of RST discourse parsers](https://md.research.elamur.ai/free/en/papers/braud-2016-multi-view-multi-task-training/) — Chloé Braud, Barbara Plank, Anders Søgaard · 2016 - [Multilingual Part-of-Speech Tagging with Bidirectional Long Short-Term Memory Models and Auxiliary Loss](https://md.research.elamur.ai/free/en/papers/plank-2016-multilingual-part-speech-tagging-bidirectional/) — Barbara Plank, Anders Søgaard, Yoav Goldberg · 2016 - [Disambiguating Explicit Discourse Connectives without Oracles](https://md.research.elamur.ai/free/en/papers/johannsen-2013-disambiguating-explicit-discourse-connectives-without/) — Anders Johannsen, Anders Søgaard · 2013