Search Results for author: Marcel Bollmann

Found 15 papers, 4 papers with code

How far can we get with one GPU in 100 hours? CoAStaL at MultiIndicMT Shared Task

no code implementations ACL (WAT) 2021 Rahul Aralikatte, Héctor Ricardo Murrieta Bello, Miryam de Lhoneux, Daniel Hershcovich, Marcel Bollmann, Anders Søgaard

This work shows that competitive translation results can be obtained in a constrained setting by incorporating the latest advances in memory and compute optimization.

Translation

Error Analysis and the Role of Morphology

1 code implementation EACL 2021 Marcel Bollmann, Anders S{\o}gaard

We evaluate two common conjectures in error analysis of NLP models: (i) Morphology is predictive of errors; and (ii) the importance of morphology increases with the morphological complexity of a language.

On Forgetting to Cite Older Papers: An Analysis of the ACL Anthology

1 code implementation ACL 2020 Marcel Bollmann, Desmond Elliott

The field of natural language processing is experiencing a period of unprecedented growth, and with it a surge of published papers.

Historical Text Normalization with Delayed Rewards

no code implementations ACL 2019 Simon Flachs, Marcel Bollmann, Anders S{\o}gaard

Training neural sequence-to-sequence models with simple token-level log-likelihood is now a standard approach to historical text normalization, albeit often outperformed by phrase-based models.

reinforcement-learning Reinforcement Learning (RL)

Multi-task learning for historical text normalization: Size matters

no code implementations WS 2018 Marcel Bollmann, Anders S{\o}gaard, Joachim Bingel

Historical text normalization suffers from small datasets that exhibit high variance, and previous work has shown that multi-task learning can be used to leverage data from related problems in order to obtain more robust models.

Grammatical Error Correction Multi-Task Learning +1

Improving historical spelling normalization with bi-directional LSTMs and multi-task learning

no code implementations COLING 2016 Marcel Bollmann, Anders Søgaard

Natural-language processing of historical documents is complicated by the abundance of variant spellings and lack of annotated data.

Multi-Task Learning

Cannot find the paper you are looking for? You can Submit a new open access paper.