Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userChar2Subword: Extending the Subword Embedding Space Using Robust Character Compositionality
118
0
0.0
(
0
)
Added by
Gustavo Aguilar
Publication date
2020
fields
Informatics Engineering
and research's language is
English
Ask ChatGPT about the research
No Arabic abstract
Byte-pair encoding (BPE) is a ubiquitous algorithm in the subword tokenization process of language models. BPE provides multiple benefits, such as handling the out-of-vocabulary problem and reducing vocabulary sparsity. However, this process is defined from the pre-training data statistics, making the tokenization on different domains susceptible to infrequent spelling sequences (e.g., misspellings as in social media or character-level adversarial attacks). On the other hand, though robust to misspellings, pure character-level models often lead to unreasonably large sequences and make it harder for the model to learn meaningful contiguous characters. We propose a character-based subword module (char2subword) that learns the subword embedding table in pre-trained models like BERT to alleviate these challenges. 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. We show our methods effectiveness by outperforming mBERT on the linguistic code-switching evaluation (LinCE) benchmark.
rate research
Read More
Previous work has modeled the compositionality of words by creating character-level models of meaning, reducing problems of sparsity for rare words. However, in many writing systems compositionality has an effect even on the character-level: the meaning of a character is derived by the sum of its parts. In this paper, we model this effect by creating embeddings for characters based on their visual characteristics, creating an image for the character and running it through a convolutional neural network to produce a visual character embedding. Experiments on a text classification task demonstrate that such model allows for better processing of instances with rare characters in languages such as Chinese, Japanese, and Korean. Additionally, qualitative analyses demonstrate that our proposed model learns to focus on the parts of characters that carry semantic content, resulting in embeddings that are coherent in visual space.
State-of-the-art models in natural language processing rely on separate rigid subword tokenization algorithms, which limit their generalization ability and adaptation to new settings. In this paper, we propose a new model inductive bias that learns a subword tokenization end-to-end as part of the model. To this end, we introduce a soft gradient-based subword tokenization module (GBST) that automatically learns latent subword representations from characters in a data-driven fashion. Concretely, GBST enumerates candidate subword blocks and learns to score them in a position-wise fashion using a block scoring network. We additionally introduce Charformer, a deep Transformer model that integrates GBST and operates on the byte level. Via extensive experiments on English GLUE, multilingual, and noisy text datasets, we show that Charformer outperforms a series of competitive byte-level baselines while generally performing on par and sometimes outperforming subword-based models. Additionally, Charformer is fast, improving the speed of both vanilla byte-level and subword-level Transformers by 28%-100% while maintaining competitive quality. We believe this work paves the way for highly performant token-free models that are trained completely end-to-end.
Exposing diverse subword segmentations to neural machine translation (NMT) models often improves the robustness of machine translation as NMT models can experience various subword candidates. However, the diversification of subword segmentations mostly relies on the pre-trained subword language models from which erroneous segmentations of unseen words are less likely to be sampled. In this paper, we present adversarial subword regularization (ADVSR) to study whether gradient signals during training can be a substitute criterion for exposing diverse subword segmentations. We experimentally show that our model-based adversarial samples effectively encourage NMT models to be less sensitive to segmentation errors and improve the performance of NMT models in low-resource and out-domain datasets.
Embedding from Language Models (ELMo) has shown to be effective for improving many natural language processing (NLP) tasks, and ELMo takes character information to compose word representation to train language models.However, the character is an insufficient and unnatural linguistic unit for word representation.Thus we introduce Embedding from Subword-aware Language Models (ESuLMo) which learns word representation from subwords using unsupervised segmentation over words.We show that ESuLMo can enhance four benchmark NLP tasks more effectively than ELMo, including syntactic dependency parsing, semantic role labeling, implicit discourse relation recognition and textual entailment, which brings a meaningful improvement over ELMo.
A popular natural language processing task decades ago, word alignment has been dominated until recently by GIZA++, a statistical method based on the 30-year-old IBM models. Though recent years have finally seen Giza++ performance bested, the new methods primarily rely on large machine translation models, massively multilingual language models, or supervision from Giza++ alignments itself. We introduce Embedding-Enhanced Giza++, and outperform Giza++ without any of the aforementioned factors. Taking advantage of monolingual embedding space geometry of the source and target language only, we exceed Giza++s performance in every tested scenario for three languages. In the lowest-resource scenario of only 500 lines of bitext, we improve performance over Giza++ by 10.9 AER. Our method scales monotonically outperforming Giza++ for all tested scenarios between 500 and 1.9 million lines of bitext. Our code will be made publicly available.
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
