CANINE: Pre-training an Efficient Tokenization-Free Encoder for Language Representation

• URL: http://arxiv.org/abs/2103.06874v2
• Date: Mon, 15 Mar 2021 17:58:09 GMT
• Title: CANINE: Pre-training an Efficient Tokenization-Free Encoder for Language Representation
• Authors: Jonathan H. Clark, Dan Garrette, Iulia Turc, John Wieting
• Abstract summary: CANINE is a neural encoder that operates directly on character sequences without explicit tokenization or vocabulary. CanINE outperforms a comparable mBERT model by >= 1 F1 on TyDi QA, a challenging multilingual benchmark.
• Score: 12.005340904206697
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Pipelined NLP systems have largely been superseded by end-to-end neural modeling, yet nearly all commonly-used models still require an explicit tokenization step. While recent tokenization approaches based on data-derived subword lexicons are less brittle than manually engineered tokenizers, these techniques are not equally suited to all languages, and the use of any fixed vocabulary may limit a model's ability to adapt. In this paper, we present CANINE, a neural encoder that operates directly on character sequences, without explicit tokenization or vocabulary, and a pre-training strategy with soft inductive biases in place of hard token boundaries. To use its finer-grained input effectively and efficiently, CANINE combines downsampling, which reduces the input sequence length, with a deep transformer stack, which encodes context. CANINE outperforms a comparable mBERT model by >= 1 F1 on TyDi QA, a challenging multilingual benchmark, despite having 28% fewer model parameters.

Related papers

• Tokenization as Finite-State Transduction [24.19959327497118]
  We introduce a finite-state framework which can efficiently encode all possible tokenizations of a regular language. We show that Byte-Pair. Match (BPE) and MaxPiece (WordPiece) fit within this framework. An application of this is to guided generation, where the outputs of a language model are constrained to match some pattern.
  arXiv  Detail & Related papers  (2024-10-21T07:10:07Z)
• Understanding and Mitigating Tokenization Bias in Language Models [6.418593476658017]
  State-of-the-art language models are autoregressive and operate on subword units known as tokens. We show that popular encoding schemes induce a sampling bias that cannot be mitigated with more training or data. We propose a novel algorithm to obtain unbiased estimates from any language model trained on tokenized data.
  arXiv  Detail & Related papers  (2024-06-24T17:38:02Z)
• Towards Faster k-Nearest-Neighbor Machine Translation [56.66038663128903]
  k-nearest-neighbor machine translation approaches suffer from heavy retrieve overhead on the entire datastore when decoding each token. We propose a simple yet effective multi-layer perceptron (MLP) network to predict whether a token should be translated jointly by the neural machine translation model and probabilities produced by the kNN.
  arXiv  Detail & Related papers  (2023-12-12T16:41:29Z)
• Unleashing the Multilingual Encoder Potential: Boosting Zero-Shot Performance via Probability Calibration [12.424785560515094]
  Pretrained multilingual encoder models can directly perform zero-shot multilingual tasks or linguistic probing by reformulating the input examples into cloze-style prompts. This method is limited by the model's bias toward predicting label words which frequently occurred during the pretraining. We combine the models with calibration techniques which modify the probabilities of label words predicted by the models.
  arXiv  Detail & Related papers  (2023-10-08T08:31:05Z)
• GanLM: Encoder-Decoder Pre-training with an Auxiliary Discriminator [114.8954615026781]
  We propose a GAN-style model for encoder-decoder pre-training by introducing an auxiliary discriminator. GanLM is trained with two pre-training objectives: replaced token detection and replaced token denoising. Experiments in language generation benchmarks show that GanLM with the powerful language understanding capability outperforms various strong pre-trained language models.
  arXiv  Detail & Related papers  (2022-12-20T12:51:11Z)
• A Vocabulary-Free Multilingual Neural Tokenizer for End-to-End Task Learning [8.052271364177988]
  Subword tokenization is a commonly used input pre-processing step in most recent NLP models. We propose a vocabulary-free neural tokenizer by distilling segmentation information from subword tokenization. Our tokenizer consistently improves performance on multilingual (NLI) and code-switching (sentiment analysis) tasks.
  arXiv  Detail & Related papers  (2022-04-22T16:50:49Z)
• Lexically Aware Semi-Supervised Learning for OCR Post-Correction [90.54336622024299]
  Much of the existing linguistic data in many languages of the world is locked away in non-digitized books and documents. Previous work has demonstrated the utility of neural post-correction methods on recognition of less-well-resourced languages. We present a semi-supervised learning method that makes it possible to utilize raw images to improve performance.
  arXiv  Detail & Related papers  (2021-11-04T04:39:02Z)
• Sentence Bottleneck Autoencoders from Transformer Language Models [53.350633961266375]
  We build a sentence-level autoencoder from a pretrained, frozen transformer language model. We adapt the masked language modeling objective as a generative, denoising one, while only training a sentence bottleneck and a single-layer modified transformer decoder. We demonstrate that the sentence representations discovered by our model achieve better quality than previous methods that extract representations from pretrained transformers on text similarity tasks, style transfer, and single-sentence classification tasks in the GLUE benchmark, while using fewer parameters than large pretrained models.
  arXiv  Detail & Related papers  (2021-08-31T19:39:55Z)
• Exploring Unsupervised Pretraining Objectives for Machine Translation [99.5441395624651]
  Unsupervised cross-lingual pretraining has achieved strong results in neural machine translation (NMT) Most approaches adapt masked-language modeling (MLM) to sequence-to-sequence architectures, by masking parts of the input and reconstructing them in the decoder. We compare masking with alternative objectives that produce inputs resembling real (full) sentences, by reordering and replacing words based on their context.
  arXiv  Detail & Related papers  (2021-06-10T10:18:23Z)
• ByT5: Towards a token-free future with pre-trained byte-to-byte models [23.532359202069063]
  Most widely-used pre-trained language models operate on sequences of tokens corresponding to word or subword units. We show that a standard Transformer architecture can be used with minimal modifications to process byte sequences. We also demonstrate that byte-level models are significantly more robust to noise and perform better on tasks that are sensitive to spelling and pronunciation.
  arXiv  Detail & Related papers  (2021-05-28T07:03:22Z)
• Fast End-to-End Speech Recognition via a Non-Autoregressive Model and Cross-Modal Knowledge Transferring from BERT [72.93855288283059]
  We propose a non-autoregressive speech recognition model called LASO (Listen Attentively, and Spell Once) The model consists of an encoder, a decoder, and a position dependent summarizer (PDS)
  arXiv  Detail & Related papers  (2021-02-15T15:18:59Z)

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.