Papers by Marcin Namysl

2 papers
Empirical Error Modeling Improves Robustness of Noisy Neural Sequence Labeling (2021.findings-acl)

Copied to clipboard

Challenge: Standard sequence labeling systems fail when processing noisy user-generated text or consuming the output of an OCR process.
Approach: They propose an empirical error generation approach that employs a sequence-to-sequence model trained to perform translation from error-free to erroneous text.
Outcome: The proposed method outperforms baseline noise generation and error correction techniques on the erroneous sequence labeling data sets.
NAT: Noise-Aware Training for Robust Neural Sequence Labeling (2020.acl-main)

Copied to clipboard

Challenge: Sequence labeling systems should perform reliably under ideal conditions and with corrupted inputs.
Approach: They propose two noise-aware training objectives that improve robustness of sequence labeling performed on perturbed inputs.
Outcome: The proposed methods improve robustness on English and German named entity recognition benchmarks.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations