Papers with noisy user-generated text

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.
Robustness to Capitalization Errors in Named Entity Recognition (D19-55)

Copied to clipboard

Challenge: Existing methods to improve robustness to noise discard given orthographic information, which significantly degrades models' performance on well-formed text.
Approach: They propose a method which allows models to learn to utilize or ignore orthographic information depending on its usefulness in the context.
Outcome: The proposed approach achieves competitive robustness to capitalization errors while making negligible compromises on well-formed text and significantly improving generalization power on noisy user-generated text.

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