most citedOptimal Hyperparameters for Deep LSTM-Networks for Sequence Labeling Tasks

266 citations · 282 across the 6 of their papers we have counts for

collaborators

7 papers

cs.CL20191 cited

Classification and Clustering of Arguments with Contextualized Word Embeddings

Nils Reimers, Benjamin Schiller, Tilman Beck +3

We experiment with two recent contextualized word embedding methods (ELMo and BERT) in the context of open-domain argument search. For the first time, we show how to leverage the p…

cs.CL20196 cited

Preference-based Interactive Multi-Document Summarisation

Yang Gao, Christian M. Meyer, Iryna Gurevych

Interactive NLP is a promising paradigm to close the gap between automatic NLP systems and the human upper bound. Preference-based interactive learning has been successfully applie…

cs.CL2019

Analysis of Automatic Annotation Suggestions for Hard Discourse-Level Tasks in Expert Domains

Claudia Schulz, Christian M. Meyer, Jan Kiesewetter +5

Many complex discourse-level tasks can aid domain experts in their work but require costly expert annotations for data creation. To speed up and ease annotations, we investigate th…

cs.CL2019

Pitfalls in the Evaluation of Sentence Embeddings

Steffen Eger, Andreas Rücklé, Iryna Gurevych

Deep learning models continuously break new records across different NLP tasks. At the same time, their success exposes weaknesses of model evaluation. Here, we compile several key…

cs.CL20176 cited

Lexical-semantic resources: yet powerful resources for automatic personality classification

Xuan-Son Vu, Lucie Flekova, Lili Jiang +1

In this paper, we aim to reveal the impact of lexical-semantic resources, used in particular for word sense disambiguation and sense-level semantic categorization, on automatic per…

cs.CL2017266 cited

Optimal Hyperparameters for Deep LSTM-Networks for Sequence Labeling Tasks

Nils Reimers, Iryna Gurevych

Selecting optimal parameters for a neural network architecture can often make the difference between mediocre and state-of-the-art performance. However, little is published which p…