# CharacterBERT and Self-Teaching for Improving the Robustness of Dense Retrievers on Queries with Typos

arXiv: https://arxiv.org/abs/2204.00716 · HTML: https://mlsanity.com/paper/2204.00716/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- Builds on 35 of its 50 references that are in the map.
- First posted on arXiv 1 Apr 2022.

## Builds on (most cited first, 30 of 35)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [XLNet: Generalized Autoregressive Pretraining for Language Understanding](https://mlsanity.com/paper/1906.08237/) (2019)
- [Deep contextualized word representations](https://mlsanity.com/paper/1802.05365/) (2018)
- [MS MARCO: A Human Generated MAchine Reading COmprehension Dataset](https://mlsanity.com/paper/1611.09268/) (2016)
- [Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation](https://mlsanity.com/paper/1609.08144/) (2016)
- [ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT](https://mlsanity.com/paper/2004.12832/) (2020)
- [Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval](https://mlsanity.com/paper/2007.00808/) (2020)
- [RocketQA: An Optimized Training Approach to Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2010.08191/) (2020)
- [Overview of the TREC 2019 deep learning track](https://mlsanity.com/paper/2003.07820/) (2020)
- [Pretrained Transformers for Text Ranking: BERT and Beyond](https://mlsanity.com/paper/2010.06467/) (2020)
- [Distilling Knowledge from Reader to Retriever for Question Answering](https://mlsanity.com/paper/2012.04584/) (2020)
- [Unsupervised Corpus Aware Language Model Pre-training for Dense Passage Retrieval](https://mlsanity.com/paper/2108.05540/) (2021)
- [RocketQAv2: A Joint Training Method for Dense Passage Retrieval and Passage Re-ranking](https://mlsanity.com/paper/2110.07367/) (2021)
- [Exploring the Limits of Language Modeling](https://mlsanity.com/paper/1602.02410/) (2016)
- [Condenser: a Pre-training Architecture for Dense Retrieval](https://mlsanity.com/paper/2104.08253/) (2021)
- [Optimizing Dense Retrieval Model Training with Hard Negatives](https://mlsanity.com/paper/2104.08051/) (2021)
- [Improving Efficient Neural Ranking Models with Cross-Architecture Knowledge Distillation](https://mlsanity.com/paper/2010.02666/) (2020)
- [Simple Entity-Centric Questions Challenge Dense Retrievers](https://mlsanity.com/paper/2109.08535/) (2021)
- [Scaling Deep Contrastive Learning Batch Size under Memory Limited Setup](https://mlsanity.com/paper/2101.06983/) (2021)
- [CharacterBERT: Reconciling ELMo and BERT for Word-Level Open-Vocabulary Representations From Characters](https://mlsanity.com/paper/2010.10392/) (2020)
- [Adv-BERT: BERT is not robust on misspellings! Generating nature adversarial samples on BERT](https://mlsanity.com/paper/2003.04985/) (2020)
- [Salient Phrase Aware Dense Retrieval: Can a Dense Retriever Imitate a Sparse One?](https://mlsanity.com/paper/2110.06918/) (2021)
- [Distilling Dense Representations for Ranking using Tightly-Coupled Teachers](https://mlsanity.com/paper/2010.11386/) (2020)
- [PAIR: Leveraging Passage-Centric Similarity Relation for Improving Dense Passage Retrieval](https://mlsanity.com/paper/2108.06027/) (2021)
- [Tevatron: An Efficient and Flexible Toolkit for Dense Retrieval](https://mlsanity.com/paper/2203.05765/) (2022)
- [RepBERT: Contextualized Text Embeddings for First-Stage Retrieval](https://mlsanity.com/paper/2006.15498/) (2020)
- [Evaluating the Robustness of Retrieval Pipelines with Query Variation Generators](https://mlsanity.com/paper/2111.13057/) (2021)

## Built on by (most cited first, 22 of 22)

- [Bridging the Gap Between Indexing and Retrieval for Differentiable Search Index with Query Generation](https://mlsanity.com/paper/2206.10128/) (2022)
- [Open-source Large Language Models are Strong Zero-shot Query Likelihood Models for Document Ranking](https://mlsanity.com/paper/2310.13243/) (2023)
- [Agent4Ranking: Semantic Robust Ranking via Personalized Query Rewriting Using Multi-agent LLM](https://mlsanity.com/paper/2312.15450/) (2023)
- [Robust Neural Information Retrieval: An Adversarial and Out-of-distribution Perspective](https://mlsanity.com/paper/2407.06992/) (2024)
- [Low-Resource Dense Retrieval for Open-Domain Question Answering: A Comprehensive Survey](https://mlsanity.com/paper/2208.03197/) (2022)
- [Investigating the Robustness of Retrieval-Augmented Generation at the Query Level](https://mlsanity.com/paper/2507.06956/) (2025)
- [A Study on FGSM Adversarial Training for Neural Retrieval](https://mlsanity.com/paper/2301.10576/) (2023)
- [A Study on the Efficiency and Generalization of Light Hybrid Retrievers](https://mlsanity.com/paper/2210.01371/) (2022)
- [Selecting which Dense Retriever to use for Zero-Shot Search](https://mlsanity.com/paper/2309.09403/) (2023)
- [On the Impact of Speech Recognition Errors in Passage Retrieval for Spoken Question Answering](https://mlsanity.com/paper/2209.12944/) (2022)
- [Typo-Robust Representation Learning for Dense Retrieval](https://mlsanity.com/paper/2306.10348/) (2023)
- [Can Pretrained Language Models Derive Correct Semantics from Corrupt Subwords under Noise?](https://mlsanity.com/paper/2306.15268/) (2023)
- [Noise-Robust Dense Retrieval via Contrastive Alignment Post Training](https://mlsanity.com/paper/2304.03401/) (2023)
- [Benchmark Granularity and Model Robustness for Image-Text Retrieval](https://mlsanity.com/paper/2407.15239/) (2024)
- [Defense of Adversarial Ranking Attack in Text Retrieval: Benchmark and Baseline via Detection](https://mlsanity.com/paper/2307.16816/) (2023)
- [How You Ask Matters! Adaptive RAG Robustness to Query Variations](https://mlsanity.com/paper/2604.10745/) (2026)
- [LEA: Improving Sentence Similarity Robustness to Typos Using Lexical Attention Bias](https://mlsanity.com/paper/2307.02912/) (2023)
- [A Multimodal Dense Retrieval Approach for Speech-Based Open-Domain Question Answering](https://mlsanity.com/paper/2409.13483/) (2024)
- [PiMRef: Deducing Ever-evolving Spear-phishing Emails with Knowledge Base Invariants](https://mlsanity.com/paper/2507.15393/) (2025)
- [Make Text Unlearnable: Exploiting Effective Patterns to Protect Personal Data](https://mlsanity.com/paper/2307.00456/) (2023)
- [On the Robustness of LLM-Based Dense Retrievers: A Systematic Analysis of Generalizability and Stability](https://mlsanity.com/paper/2604.16576/) (2026)
- [Hypencoder Revisited: Reproducibility and Analysis of Non-Linear Scoring for First-Stage Retrieval](https://mlsanity.com/paper/2604.27037/) (2026)

## Abstract (arXiv)

Current dense retrievers are not robust to out-of-domain and outlier queries, i.e. their effectiveness on these queries is much poorer than what one would expect. In this paper, we consider a specific instance of such queries: queries that contain typos. We show that a small character level perturbation in queries (as caused by typos) highly impacts the effectiveness of dense retrievers. We then demonstrate that the root cause of this resides in the input tokenization strategy employed by BERT. In BERT, tokenization is performed using the BERT's WordPiece tokenizer and we show that a token with a typo will significantly change the token distributions obtained after tokenization. This distribution change translates to changes in the input embeddings passed to the BERT-based query encoder of dense retrievers. We then turn our attention to devising dense retriever methods that are robust to such queries with typos, while still being as performant as previous methods on queries without typos. For this, we use CharacterBERT as the backbone encoder and an efficient yet effective training method, called Self-Teaching (ST), that distills knowledge from queries without typos into the queries with typos. Experimental results show that CharacterBERT in combination with ST achieves significantly higher effectiveness on queries with typos compared to previous methods. Along with these results and the open-sourced implementation of the methods, we also provide a new passage retrieval dataset consisting of real-world queries with typos and associated relevance assessments on the MS MARCO corpus, thus supporting the research community in the investigation of effective and robust dense retrievers. Code, experimental results and dataset are made available at https://github.com/ielab/CharacterBERT-DR.