Multi hash embeddings in spaCy

1 code implementation • 19 Dec 2022 • Lester James Miranda, Ákos Kádár, Adriane Boyd, Sofie Van Landeghem, Anders Søgaard, Matthew Honnibal

In this technical report we lay out a bit of history and introduce the embedding methods in spaCy in detail.

named-entity-recognition Named Entity Recognition +2

Using Wikipedia Edits in Low Resource Grammatical Error Correction

1 code implementation • WS 2018 • Adriane Boyd

We develop a grammatical error correction (GEC) system for German using a small gold GEC corpus augmented with edits extracted from Wikipedia revision history.

Grammatical Error Correction Machine Translation

Normalization in Context: Inter-Annotator Agreement for Meaning-Based Target Hypothesis Annotation

no code implementations • WS 2018 • Adriane Boyd

Reading Comprehension

The MERLIN corpus: Learner language and the CEFR

no code implementations • LREC 2014 • Adriane Boyd, Jirka Hana, Lionel Nicolas, Detmar Meurers, Katrin Wisniewski, Andrea Abel, Karin Sch{\"o}ne, Barbora {\v{S}}tindlov{\'a}, Chiara Vettori

The MERLIN corpus is a written learner corpus for Czech, German, and Italian that has been designed to illustrate the Common European Framework of Reference for Languages (CEFR) with authentic learner data.

Language Acquisition Native Language Identification

Informing Determiner and Preposition Error Correction with Hierarchical Word Clustering

no code implementations • WS 2012 • Adriane Boyd, Marion Zepf, Detmar Meurers

Clustering