# Finite-context Indexing of Restricted Output Space for NLP Models Facing Noisy Input

arXiv: https://arxiv.org/abs/2310.14110 · HTML: https://mlsanity.com/paper/2310.14110/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 33 of its 60 references that are in the map.
- First posted on arXiv 21 Oct 2023.

## Builds on (most cited first, 30 of 33)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [Intriguing properties of neural networks](https://mlsanity.com/paper/1312.6199/) (2013)
- [GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding](https://mlsanity.com/paper/1804.07461/) (2018)
- [Practical Black-Box Attacks against Machine Learning](https://mlsanity.com/paper/1602.02697/) (2016)
- [Adversarial Examples for Evaluating Reading Comprehension Systems](https://mlsanity.com/paper/1707.07328/) (2017)
- [Delving into Transferable Adversarial Examples and Black-box Attacks](https://mlsanity.com/paper/1611.02770/) (2016)
- [Generating Natural Language Adversarial Examples](https://mlsanity.com/paper/1804.07998/) (2018)
- [Black-box Generation of Adversarial Text Sequences to Evade Deep Learning Classifiers](https://mlsanity.com/paper/1801.04354/) (2018)
- [Synthetic and Natural Noise Both Break Neural Machine Translation](https://mlsanity.com/paper/1711.02173/) (2017)
- [SemEval-2017 Task 4: Sentiment Analysis in Twitter](https://mlsanity.com/paper/1912.00741/) (2019)
- [Generating Natural Adversarial Examples](https://mlsanity.com/paper/1710.11342/) (2017)
- [Certified Robustness to Adversarial Word Substitutions](https://mlsanity.com/paper/1909.00986/) (2019)
- [Combating Adversarial Misspellings with Robust Word Recognition](https://mlsanity.com/paper/1905.11268/) (2019)
- [Breaking NLI Systems with Sentences that Require Simple Lexical Inferences](https://mlsanity.com/paper/1805.02266/) (2018)
- [Robust Encodings: A Framework for Combating Adversarial Typos](https://mlsanity.com/paper/2005.01229/) (2020)
- [MTNT: A Testbed for Machine Translation of Noisy Text](https://mlsanity.com/paper/1809.00388/) (2018)
- [Modeling Localness for Self-Attention Networks](https://mlsanity.com/paper/1810.10182/) (2018)
- [Named Entity Disambiguation for Noisy Text](https://mlsanity.com/paper/1706.09147/) (2017)
- [GitHub Typo Corpus: A Large-Scale Multilingual Dataset of Misspellings and Grammatical Errors](https://mlsanity.com/paper/1911.12893/) (2019)
- [Robsut Wrod Reocginiton via semi-Character Recurrent Neural Network](https://mlsanity.com/paper/1608.02214/) (2016)
- [Hierarchical Character Embeddings: Learning Phonological and Semantic Representations in Languages of Logographic Origin using Recursive Neural Networks](https://mlsanity.com/paper/1912.09913/) (2019)
- [Domain-shift Conditioning using Adaptable Filtering via Hierarchical Embeddings for Robust Chinese Spell Check](https://mlsanity.com/paper/2008.12281/) (2020)
- [An Effective, Performant Named Entity Recognition System for Noisy Business Telephone Conversation Transcripts](https://mlsanity.com/paper/2209.13736/) (2022)
- [May I Ask Who's Calling? Named Entity Recognition on Call Center Transcripts for Privacy Law Compliance](https://mlsanity.com/paper/2010.15598/) (2020)

## Abstract (arXiv)

NLP models excel on tasks with clean inputs, but are less accurate with noisy inputs. In particular, character-level noise such as human-written typos and adversarially-engineered realistic-looking misspellings often appears in text and can easily trip up NLP models. Prior solutions to address character-level noise often alter the content of the inputs (low fidelity), thus inadvertently lowering model accuracy on clean inputs. We proposed FiRo, an approach to boost NLP model performance on noisy inputs without sacrificing performance on clean inputs. FiRo sanitizes the input text while preserving its fidelity by inferring the noise-free form for each token in the input. FiRo uses finite-context aggregation to obtain contextual embeddings which is then used to find the noise-free form within a restricted output space. The output space is restricted to a small cluster of probable candidates in order to predict the noise-free tokens more accurately. Although the clusters are small, FiRo's effective vocabulary (union of all clusters) can be scaled up to better preserve the input content. Experimental results show NLP models that use FiRo outperforming baselines on six classification tasks and one sequence labeling task at various degrees of noise.