paper-with-me

홈 › Papers

Char2Subword: Extending the Subword Embedding Space Using Robust Character Compositionality

2020-10-24 · Findings (EMNLP) 2021 11 · Gustavo Aguilar, Bryan McCann, Tong Niu, Nazneen Rajani, Nitish Keskar, Thamar Solorio

Byte-pair encoding (BPE) is a ubiquitous algorithm in the subword tokenization process of language models as it provides multiple benefits. However, this process is solely based on pre-training data statistics, making it hard for the tokenizer to handle infrequent spellings. On the other hand, though robust to misspellings, pure character-level models often lead to unreasonably long sequences and make it harder for the model to learn meaningful words. To alleviate these challenges, we propose a character-based subword module (char2subword) that learns the subword embedding table in pre-trained models like BERT. Our char2subword module builds representations from characters out of the subword vocabulary, and it can be used as a drop-in replacement of the subword embedding table. The module is robust to character-level alterations such as misspellings, word inflection, casing, and punctuation. We integrate it further with BERT through pre-training while keeping BERT transformer parameters fixed--and thus, providing a practical method. Finally, we show that incorporating our module to mBERT significantly improves the performance on the social media linguistic code-switching evaluation (LinCE) benchmark.

📄 PDF Abstract BibTeX arXiv:2010.12730

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
mBERT mBERT
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Adam 설명 없음
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Linear Warmup With Linear Decay Linear Warmup With Linear Decay is a learning rate schedule in which we increase the learning rate linearly for $n$ updates and then linearly decay afterwards.

Similar Papers 제목 키워드 기반

Effective Subword Segmentation for Text Comprehension

2018-11-06 · Zhuosheng Zhang, Hai Zhao, Kangwei Ling, Jiangtong Li 외

Representation learning is the foundation of machine reading comprehension and inference. In state-of-the-art models, character-level representations have been broadly adopted to alleviate the problem of effectively repr…

Machine Reading ComprehensionReading ComprehensionRepresentation LearningSegmentation

Subword-based Compact Reconstruction of Word Embeddings

2019-06-01 · NAACL 2019 6 · Shota Sasaki, Jun Suzuki, Kentaro Inui

The idea of subword-based word embeddings has been proposed in the literature, mainly for solving the out-of-vocabulary (OOV) word problem observed in standard word-based word embeddings. In this paper, we propose a meth…

Word Embeddings

Fast and Accurate Transformer-based Translation with Character-Level Encoding and Subword-Level Decoding

2021-11-16 · ACL ARR November 2021 11 · Anonymous

The Transformer translation model is fast to train and achieves state-of-the-art results for various translation tasks. However, unknown input words at test time remain a challenge for the Transformer, especially when …

DecoderTranslation

Subword-augmented Embedding for Cloze Reading Comprehension

2018-06-24 · COLING 2018 8 · Zhuosheng Zhang, Yafang Huang, Hai Zhao

Representation learning is the foundation of machine reading comprehension. In state-of-the-art models, deep learning methods broadly use word and character level representations. However, character is not naturally the …

Machine Reading ComprehensionReading ComprehensionRepresentation Learning

Treat the Word As a Whole or Look Inside? Subword Embeddings Model Language Change and Typology

2019-08-01 · WS 2019 8 · Yang Xu, Jiasheng Zhang, David Reitter

We use a variant of word embedding model that incorporates subword information to characterize the degree of compositionality in lexical semantics. Our models reveal some interesting yet contrastive patterns of long-term…