Challenge: Subword segmentation algorithms can produce sub-optimal segmentation when the target language is rich in morphological changes or there is not enough data for learning compact composition rules.
Approach: They compare character-based and subword-based neural machine translation systems . they find character-driven models are better at handling morphological phenomena .
Outcome: The character-based models are better at handling morphological phenomena, generating rare and unknown words, and more suitable for transferring to unseen domains.

Similar Papers

On the Importance of Word Boundaries in Character-level Neural Machine Translation (D19-56)

Copied to clipboard

Challenge: Neural Machine Translation models typically use a fixed-size lexical vocabulary . subword segmentation methods rely on statistical heuristics that lack any linguistic notion .
Approach: They propose a hierarchical decoding architecture for character-level NMT using subwords . they propose fewer parameters and a more efficient approach to perform translation at the level of words .
Outcome: The proposed model can reach higher translation accuracy than the subword-level model with fewer parameters while maintaining longer-distance contextual and grammatical dependencies.
One Size Does Not Fit All: Comparing NMT Representations of Different Granularities (N19-1)

Copied to clipboard

Challenge: Recent work has shown that contextualized word representations are a viable alternative to simple word prediction tasks.
Approach: They propose to use subword units and characters to model morphology, syntax, and semantics instead of word embeddings.
Outcome: The proposed representations are better for modeling syntax and more robust to noisy input.
Subword Regularization: Improving Neural Network Translation Models with Multiple Subword Candidates (P18-1)

Copied to clipboard

Challenge: Subword units are an effective way to alleviate the open vocabulary problems in neural machine translation.
Approach: They propose a method to regularize subword segmentations probabilistically by sampling subwords . they also propose 'unigram' language model to be used for better subword sampling .
Outcome: The proposed method improves on low resource and out-of-domain settings with multiple corpora.
Improving Neural Machine Translation by Incorporating Hierarchical Subword Features (C18-1)

Copied to clipboard

Challenge: Using subwords, we find that the appropriate subword units for the three layers differ depending on the model . incorporating hierarchical subword features improves BLEU scores on the IWSLT evaluation datasets.
Approach: They propose a method that expresses a word by combining "subwords" they propose to incorporate hierarchical subword features into a single embedding layer .
Outcome: The proposed method improves BLEU scores on the IWSLT evaluation datasets.
Subword-Delimited Downsampling for Better Character-Level Translation (2022.findings-emnlp)

Copied to clipboard

Challenge: Subword-level models are expensive in terms of time and computation, but character-level model with downsampling component can be used for machine translation.
Approach: They propose a character-level downsampling method which is informed by subwords to improve model performance.
Outcome: The proposed method outperforms existing methods and shows that it can be done without sacrificing quality.
How Suitable Are Subword Segmentation Strategies for Translating Non-Concatenative Morphology? (2021.findings-emnlp)

Copied to clipboard

Challenge: Data-driven subword segmentation is the default strategy for open-vocabulary machine translation but may not be sufficiently generic for learning non-concatenative morphology.
Approach: They propose to test data-driven subword segmentation on non-concatenative morphological phenomena in a controlled, semi-synthetic setting.
Outcome: The proposed model can translate non-concatenative morphological phenomena in a controlled, semi-synthetic setting.
Understanding Pure Character-Based Neural Machine Translation: The Case of Translating Finnish into English (2020.coling-main)

Copied to clipboard

Challenge: Recent work shows that deeper character-based neural machine translation models outperform subword-based models.
Approach: They propose to investigate the ability of character-based models to learn word senses and morphological inflections and the attention mechanism in Finnish into English translation.
Outcome: The character-based models outperform subword-based model in Finnish to English translation.
The Effectiveness of Morphology-aware Segmentation in Low-Resource Neural Machine Translation (2021.eacl-srw)

Copied to clipboard

Challenge: Current NMT systems typically operate at the level of subwords, causing problems of vocabulary sparsity.
Approach: They compare subword segmentation methods with morphologically-based methods in a low-resource setting . they find that no consistent and reliable differences emerge between the methods .
Outcome: The proposed methods outperform BPE in a low-resource translation setting.
Towards Reasonably-Sized Character-Level Transformer NMT by Finetuning Subword Systems (2020.emnlp-main)

Copied to clipboard

Challenge: Existing approaches to train character-level models require very deep architectures that are difficult and slow to train.
Approach: They propose to fine tune a Transformer token-based model to get a model without token segmentation.
Outcome: The proposed model improves translation quality and robustness to noise while requiring less token segmentation.
Adversarial Subword Regularization for Robust Neural Machine Translation (2020.findings-emnlp)

Copied to clipboard

Challenge: Existing methods for segmenting words into subword units are not robust enough to handle multiple subword candidates.
Approach: They propose to regularize subword segmentations that maximize the translation loss by using gradient signals during training to prevent erroneous segmentations of unseen words.
Outcome: The proposed method improves the performance of NMT models on low-resource and out-domain datasets.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations