Methods › Natural Language Processing › Language Models › CharacterBERT
CharacterBERT
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
CharacterBERT is a variant of BERT that drops the wordpiece system and replaces it with a CharacterCNN module just like the one ELMo uses to produce its first layer representation. This allows CharacterBERT to represent any input token without splitting it into wordpieces. Moreover, this frees BERT from the burden of a domain-specific wordpiece vocabulary which may not be suited to your domain of interest (e.g. medical domain). Finally, it allows the model to be more robust to noisy inputs.
Papers archive 2025-07-28
8 shown of 8, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.
-
Continuous Prompt Tuning Based Textual Entailment Model for E-commerce Entity Typing 4 Nov 2022 · 1 repository · arXiv:2211.02483
-
CharacterBERT and Self-Teaching for Improving the Robustness of Dense Retrievers on Queries with Typos 1 Apr 2022 · 1 repository · arXiv:2204.00716
-
Signal in Noise: Exploring Meaning Encoded in Random Character Sequences with Character-Aware Language Models 15 Mar 2022 · 1 repository · arXiv:2203.07911
-
Exploring Meaning Encoded in Random Character Sequences with Character-Aware Language Models 16 Nov 2021 · 0 repositories
-
Imposing Relation Structure in Language-Model Embeddings Using Contrastive Learning 2 Sep 2021 · 1 repository · arXiv:2109.00840
-
UniParma at SemEval-2021 Task 5: Toxic Spans Detection Using CharacterBERT and Bag-of-Words Model 17 Mar 2021 · 1 repository · arXiv:2103.09645
-
CharacterBERT: Reconciling ELMo and BERT for Word-Level Open-Vocabulary Representations From Characters 20 Oct 2020 · 2 repositories · arXiv:2010.10392Syntology ran 5 of 8 samples · 3 unverified
-
Aggressive Language Identification Using Word Embeddings and Sentiment Features 1 Aug 2018 · 1 repository
Tasks archive 2025-07-28
20 shown of 22 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
Usage over time archive 2025-07-28
Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).
Categories archive 2025-07-28
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections