Despite recent advances, standard sequence labeling systems often fail when processing noisy user-generated text or consuming the output of an Optical Character Recognition (OCR) process. In this paper, we improve the noise-aware training method by proposing an empirical error generation approach that employs a sequence-to-sequence model trained to perform translation from error-free to erroneous text. Using an OCR engine, we generated a large parallel text corpus for training and produced several real-world noisy sequence labeling benchmarks for evaluation. Moreover, to overcome the data sparsity problem that exacerbates in the case of imperfect textual input, we learned noisy language model-based embeddings. Our approach outperformed the baseline noise generation and error correction techniques on the erroneous sequence labeling data sets. To facilitate future research on robustness, we make our code, embeddings, and data conversion scripts publicly available.READ FULL TEXT
Sequence labeling systems should perform reliably not only under ideal
In Grammatical Error Correction (GEC), sequence labeling models enjoy fa...
Neural Machine Translation models are brittle to input noise. Current
A great deal of historical corpora suffer from errors introduced by the ...
Grammatical Error Correction (GEC) has been recently modeled using the
Neural text generation (data- or text-to-text) demonstrates remarkable
Spell check is a useful application which involves processing noisy