--- title: "Karl Moritz Hermann — papers and cards" description: "Karl Moritz Hermann: 2 paper cards in the Research library (2012–2018), with what each paper is about, the ideas Mova took from it, and the co-authors." canonical: "https://research.elamur.ai/free/en/authors/karl-moritz-hermann/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/karl-moritz-hermann/) [home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / Karl Moritz Hermann # Karl Moritz Hermann 2 paper cards in the Research library · 2012–2018 Karl Moritz Hermann wrote 2 of the papers Mova reads, in 2012–2018, most of them on [Machine translation](https://md.research.elamur.ai/free/en/topics/machine-translation/); often with Bevan Jones, [Chris Dyer](https://md.research.elamur.ai/free/en/authors/chris-dyer/), Daniel Bauer. [OpenAlex](https://openalex.org/A5001284503) · [**h-index 25**](https://openalex.org/authors/A5001284503) · [7477 citations](https://openalex.org/authors/A5001284503) · [43 works](https://openalex.org/works?filter=author.id:A5001284503) — 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=Karl+Moritz+Hermann) · [Semantic Scholar](https://www.semanticscholar.org/search?q=Karl+Moritz+Hermann) · [dblp](https://dblp.org/search?q=Karl+Moritz+Hermann) · [ACL Anthology](https://aclanthology.org/search/?q=Karl+Moritz+Hermann) · [ORCID](https://orcid.org/orcid-search/search?searchQuery=Karl+Moritz+Hermann) Topics: [Machine translation](https://md.research.elamur.ai/free/en/topics/machine-translation/) 1 ## Papers 1. **[The NarrativeQA Reading Comprehension Challenge](https://md.research.elamur.ai/free/en/papers/kocisky-2018-narrativeqa-reading-comprehension-challenge/)** *(2018)* NarrativeQA pairs 1,567 long stories (half Gutenberg books, half movie scripts) with plot summaries from Wikipedia; annotators who saw only the summary wrote about 30 question–answer pairs per story in their own words (46,765 in all, answers 4.7 tokens on average, a second reference answer per question). 2. **[Semantics-Based Machine Translation with Hyperedge Replacement Grammars](https://md.research.elamur.ai/free/en/papers/jones-2012-semantics-based-machine-translation-hyperedge/)** *(2012)* The paper translates through a graph-shaped meaning representation. A source sentence is analysed into a graph, the graph is the pivot, and the target sentence is generated from it. The grammar is a weighted synchronous hyperedge replacement grammar. Its rules are learned from aligned string and graph pairs by an… ## Co-authors (10) - Bevan Jones - [Chris Dyer](https://md.research.elamur.ai/free/en/authors/chris-dyer/) - Daniel Bauer - Edward Grefenstette - Gábor Melis - [Jacob Andreas](https://md.research.elamur.ai/free/en/authors/jacob-andreas/) - Jonathan Schwarz - [Kevin Knight](https://md.research.elamur.ai/free/en/authors/kevin-knight/) - Phil Blunsom - Tomáš Kočiský ## More papers in the library (2) Pages of the Research library: our summary, the ideas, references and who cites each. - [Reasoning about Entailment with Neural Attention](https://md.research.elamur.ai/free/en/papers/rocktaschel-2015-reasoning-about-entailment-neural-attention/) — Tim Rocktaschel, Edward Grefenstette, Karl Moritz Hermann, et al. · 2015 - [Teaching Machines to Read and Comprehend](https://md.research.elamur.ai/free/en/papers/hermann-2015-teaching-machines-read-comprehend/) — Karl Moritz Hermann, Tomáš Kočiský, Edward Grefenstette, et al. · 2015