--- title: "Hinrich Schütze — papers and cards" description: "Hinrich Schütze: 2 paper cards in the Research library (2007–2019), with what each paper is about, the ideas Mova took from it, and the co-authors." canonical: "https://research.elamur.ai/free/en/authors/hinrich-schutze/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/hinrich-schutze/) [home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / Hinrich Schütze # Hinrich Schütze 2 paper cards in the Research library · 2007–2019 Hinrich Schütze wrote 2 of the papers Mova reads, in 2007–2019; often with Martin Schmitt, Michaela Atterer. [OpenAlex](https://openalex.org/A5071144367) · [ORCID](https://orcid.org/0000-0001-9514-7934) · [**h-index 63**](https://openalex.org/authors/A5071144367) · [51036 citations](https://openalex.org/authors/A5071144367) · [501 works](https://openalex.org/works?filter=author.id:A5071144367) — 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=Hinrich+Sch%C3%BCtze) · [Semantic Scholar](https://www.semanticscholar.org/search?q=Hinrich+Sch%C3%BCtze) · [dblp](https://dblp.org/search?q=Hinrich+Sch%C3%BCtze) · [ACL Anthology](https://aclanthology.org/search/?q=Hinrich+Sch%C3%BCtze) · [ORCID](https://orcid.org/orcid-search/search?searchQuery=Hinrich+Sch%C3%BCtze) ## Ideas Mova took (2) From the ideas ledger: an idea tried, kept or queued, or measured with no gain, and what it gave. - **kept** — en parse-eval: report PP attachment accuracy taken from the predicted tree, not from gold (v, n1, p, n2) tuples, next to LAS on UD EWT test. Count the PP cases the parser misses as a separate number. *([Prepositional Phrase Attachment without Oracles](https://md.research.elamur.ai/free/en/papers/cl-2007-atterer-squibs-prepositional-phrase-attachment-without/) · PP attachment from the predicted tree in en parse-diag: 1615 dev PPs, 190 missed; commit 35e51ff1b)* - **kept** — Report three figures for every PP score, as the paper does: missed cases counted as errors, missed cases given the noun attachment, and missed cases discarded. A score that rises only when cases are discarded must not pass the gate. *([Prepositional Phrase Attachment without Oracles](https://md.research.elamur.ai/free/en/papers/cl-2007-atterer-squibs-prepositional-phrase-attachment-without/) · three figures, EWT dev: missed = error 72.20, missed -> noun 77.65, discarded 81.82; commit 35e51ff1b)* ## Papers 1. **[SherLIiC: A Typed Event-Focused Lexical Inference Benchmark for Evaluating Natural Language Inference](https://md.research.elamur.ai/free/en/papers/schmitt-2019-sherliic-typed-event-focused-lexical/)** *(2019)* SherLIiC is a benchmark for lexical inference in context. Each item is a candidate rule, "A is granting to B" implies "A is giving to B", where A and B are typed argument slots such as ORGANIZATION FOUNDER and EMPLOYER. The relations come from verbal paths between Freebase entities in the ClueWeb09 web corpus… 2. **[Prepositional Phrase Attachment without Oracles](https://md.research.elamur.ai/free/en/papers/cl-2007-atterer-squibs-prepositional-phrase-attachment-without/)** *(2007)* `2 ideas kept` Most PP attachment work gives the classifier the two candidate heads from gold parse trees, which the authors call an oracle. ## Co-authors (2) - Martin Schmitt - Michaela Atterer ## More papers in the library (11) Pages of the Research library: our summary, the ideas, references and who cites each. - [Exploiting Cloze-Questions for Few-Shot Text Classification and Natural Language Inference](https://md.research.elamur.ai/free/en/papers/schick-2021-exploiting-cloze-questions-few-shot/) — Timo Schick, Hinrich Schütze · 2021 - [Generating Datasets with Pretrained Language Models](https://md.research.elamur.ai/free/en/papers/schick-2021-generating-datasets-pretrained-language-models/) — Timo Schick, Hinrich Schutze · 2021 - [Investigating Pretrained Language Models for Graph-to-Text Generation](https://md.research.elamur.ai/free/en/papers/ribeiro-2021-investigating-pretrained-language-models-graph/) — Leonardo F. R. Ribeiro, Martin Schmitt, Hinrich Schütze, et al. · 2021 - [It's Not Just Size That Matters: Small Language Models Are Also Few-Shot Learners](https://md.research.elamur.ai/free/en/papers/schick-2021-it-s-not-just-size/) — Timo Schick, Hinrich Schütze · 2021 - [Self-Diagnosis and Self-Debiasing: A Proposal for Reducing Corpus-Based Bias in NLP](https://md.research.elamur.ai/free/en/papers/schick-2021-self-diagnosis-self-debiasing-proposal/) — Timo Schick, Sahana Udupa, Hinrich Schutze · 2021 - [Are Pretrained Language Models Symbolic Reasoners over Knowledge?](https://md.research.elamur.ai/free/en/papers/kassner-2020-are-pretrained-language-models-symbolic/) — Nora Kassner, Benno Krojer, Hinrich Schütze · 2020 - [Negated and Misprimed Probes for Pretrained Language Models: Birds Can Talk, But Cannot Fly](https://md.research.elamur.ai/free/en/papers/kassner-2020-negated-misprimed-probes-pretrained-language/) — Nora Kassner, Hinrich Schütze · 2020 - [ABCNN: Attention-Based Convolutional Neural Network for Modeling Sentence Pairs](https://md.research.elamur.ai/free/en/papers/yin-2016-abcnn-attention-based-convolutional-neural/) — Wenpeng Yin, Hinrich Schütze, Bing Xiang, et al. · 2016 - [Active Learning for Coreference Resolution](https://md.research.elamur.ai/free/en/papers/laws-2012-active-learning-coreference-resolution/) — Florian Laws, Florian Heimerl, Hinrich Schütze · 2012 - [SUCRE: A Modular System for Coreference Resolution](https://md.research.elamur.ai/free/en/papers/kobdani-2010-sucre-modular-system-coreference-resolution/) — Hamidreza Kobdani, Hinrich Schütze · 2010 - [Automatic Word Sense Discrimination](https://md.research.elamur.ai/free/en/papers/schutze-1998-automatic-word-sense-discrimination/) — Hinrich Schütze · 1998