T
Tanja Bergmann
Researcher at Hasso Plattner Institute
Publications - 5
Citations - 877
Tanja Bergmann is an academic researcher from Hasso Plattner Institute. The author has contributed to research in topics: Language model & Domain (software engineering). The author has an hindex of 3, co-authored 5 publications receiving 533 citations.
Papers
More filters
Proceedings ArticleDOI
FLAIR: An Easy-to-Use Framework for State-of-the-Art NLP
TL;DR: The core idea of the FLAIR framework is to present a simple, unified interface for conceptually very different types of word and document embeddings, which effectively hides all embedding-specific engineering complexity and allows researchers to “mix and match” variousembeddings with little effort.
Proceedings ArticleDOI
Pooled Contextualized Embeddings for Named Entity Recognition.
TL;DR: This work proposes a method in which it dynamically aggregate contextualized embeddings of each unique string that the authors encounter and uses a pooling operation to distill a ”global” word representation from all contextualized instances.
Journal ArticleDOI
Data profiling with metanome
TL;DR: The goal of Metanome is to provide novel profiling algorithms from research, perform comparative evaluations, and to support developers in building and testing new algorithms that incorporate many state-of-the-art profiling algorithms.
Proceedings ArticleDOI
Generating a linked soccer dataset
Tanja Bergmann,Stefan Bunk,Johannes Eschrig,Christian Hentschel,Magnus Knuth,Harald Sack,Ricarda Schüler +6 more
TL;DR: This paper presents a dataset containing information about soccer entities crawled from heterogeneous sources and linked to related entities from the LOD cloud, providing a structured overview and extensive statistics.
Linked Soccer Data.
Tanja Bergmann,Stefan Bunk,Johannes Eschrig,Christian Hentschel,Magnus Knuth,Harald Sack,Ricarda Schüler +6 more
TL;DR: A dataset containing information about soccer matches, teams, players and so forth crawled from from heterogeneous sources and linked to related entities from the LOD cloud is presented providing a structured overview and extensive statistics.