Models In a Spelling Bee: Language Models Implicitly Learn the Character Composition of Tokens

• URL: http://arxiv.org/abs/2108.11193v1
• Date: Wed, 25 Aug 2021 11:48:05 GMT
• Title: Models In a Spelling Bee: Language Models Implicitly Learn the Character Composition of Tokens
• Authors: Itay Itzhak and Omer Levy
• Abstract summary: We probe the embedding layer of pretrained language models. We show that models learn the internal character composition of whole word and subword tokens.
• Score: 22.55706811131828
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Standard pretrained language models operate on sequences of subword tokens without direct access to the characters that compose each token's string representation. We probe the embedding layer of pretrained language models and show that models learn the internal character composition of whole word and subword tokens to a surprising extent, without ever seeing the characters coupled with the tokens. Our results show that the embedding layer of RoBERTa holds enough information to accurately spell up to a third of the vocabulary and reach high average character ngram overlap on all token types. We further test whether enriching subword models with additional character information can improve language modeling, and observe that this method has a near-identical learning curve as training without spelling-based enrichment. Overall, our results suggest that language modeling objectives incentivize the model to implicitly learn some notion of spelling, and that explicitly teaching the model how to spell does not enhance its performance on such tasks.

Related papers

• Pre-trained Language Models Do Not Help Auto-regressive Text-to-Image Generation [82.5217996570387]
  We adapt a pre-trained language model for auto-regressive text-to-image generation. We find that pre-trained language models offer limited help.
  arXiv  Detail & Related papers  (2023-11-27T07:19:26Z)
• Toucan: Token-Aware Character Level Language Modeling [44.85590844938571]
  Toucan is an augmentation to character-level models to make them "token-aware" We show significant speed-ups in character generation without a loss in language modeling performance. Our approach leads to a greater amount of longer sequences tokenized as single items.
  arXiv  Detail & Related papers  (2023-11-15T00:57:51Z)
• Learning Mutually Informed Representations for Characters and Subwords [26.189422354038978]
  We introduce the entanglement model, aiming to combine character and subword language models. Inspired by vision-language models, our model treats characters and subwords as separate modalities. We evaluate our model on text classification, named entity recognition, POS-tagging, and character-level sequence labeling.
  arXiv  Detail & Related papers  (2023-11-14T02:09:10Z)
• Language Model Pre-Training with Sparse Latent Typing [66.75786739499604]
  We propose a new pre-training objective, Sparse Latent Typing, which enables the model to sparsely extract sentence-level keywords with diverse latent types. Experimental results show that our model is able to learn interpretable latent type categories in a self-supervised manner without using any external knowledge.
  arXiv  Detail & Related papers  (2022-10-23T00:37:08Z)
• Exploiting Word Semantics to Enrich Character Representations of Chinese Pre-trained Models [12.0190584907439]
  We propose a new method to exploit word structure and integrate lexical semantics into character representations of pre-trained models. We show that our approach achieves superior performance over the basic pre-trained models BERT, BERT-wwm and ERNIE on different Chinese NLP tasks.
  arXiv  Detail & Related papers  (2022-07-13T02:28:08Z)
• What do tokens know about their characters and how do they know it? [3.8254443661593633]
  We show that pre-trained language models that use subword tokenization schemes can succeed at a variety of language tasks that require character-level information. We show that these models robustly encode character-level information and, in general, larger models perform better at the task.
  arXiv  Detail & Related papers  (2022-06-06T13:27:26Z)
• Charformer: Fast Character Transformers via Gradient-based Subword Tokenization [50.16128796194463]
  We propose a new model inductive bias that learns a subword tokenization end-to-end as part of the model. We introduce a soft gradient-based subword tokenization module (GBST) that automatically learns latent subword representations from characters. We additionally introduce Charformer, a deep Transformer model that integrates GBST and operates on the byte level.
  arXiv  Detail & Related papers  (2021-06-23T22:24:14Z)
• Lattice-BERT: Leveraging Multi-Granularity Representations in Chinese Pre-trained Language Models [62.41139712595334]
  We propose a novel pre-training paradigm for Chinese -- Lattice-BERT. We construct a lattice graph from the characters and words in a sentence and feed all these text units into transformers. We show that our model can bring an average increase of 1.5% under the 12-layer setting.
  arXiv  Detail & Related papers  (2021-04-15T02:36:49Z)
• CharBERT: Character-aware Pre-trained Language Model [36.9333890698306]
  We propose a character-aware pre-trained language model named CharBERT. We first construct the contextual word embedding for each token from the sequential character representations. We then fuse the representations of characters and the subword representations by a novel heterogeneous interaction module.
  arXiv  Detail & Related papers  (2020-11-03T07:13:06Z)
• SLM: Learning a Discourse Language Representation with Sentence Unshuffling [53.42814722621715]
  We introduce Sentence-level Language Modeling, a new pre-training objective for learning a discourse language representation. We show that this feature of our model improves the performance of the original BERT by large margins.
  arXiv  Detail & Related papers  (2020-10-30T13:33:41Z)
• Grounded Compositional Outputs for Adaptive Language Modeling [59.02706635250856]
  A language model's vocabulary$-$typically selected before training and permanently fixed later$-$affects its size. We propose a fully compositional output embedding layer for language models. To our knowledge, the result is the first word-level language model with a size that does not depend on the training vocabulary.
  arXiv  Detail & Related papers  (2020-09-24T07:21:14Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.