| Challenge: | Past vocabulary learning techniques identify relevant vocabulary before training, relying on corpus statistics or frequency counts without considering contextual information or the model's ability to represent it. |
| Approach: | They propose a method that self-vocabularizes a smaller, more optimal vocabulary by pairing source sentences with the model's predictions to define a new vocabulary. |
| Outcome: | The proposed method produces a 1.49 BLEU improvement in the simulated model and an increase in unique token usage and a 6–8% reduction in vocabulary size. |
Similar Papers
Entropy-Based Vocabulary Substitution for Incremental Learning in Multilingual Neural Machine Translation (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods to update a multilingual model with new language pairs are expensive and time-consuming. |
| Approach: | They propose an entropy-based vocabulary substitution method that walks through new language pairs for incremental learning while remaining the size of the original vocabulary. |
| Outcome: | The proposed method achieves better performance and saves excess overhead in a multilingual machine translation task. |
Vocabulary Learning via Optimal Transport for Neural Machine Translation (2021.acl-long)
Copied to clipboard
| Challenge: | Empirical results show that VOLT beats widely-used vocabularies in diverse scenarios, including WMT-14 English-German translation, TED bilingual translation, and TED multilingual translation. |
| Approach: | They propose a token dictionary solution that can be used without trial training to find the best dictionary with a proper size. |
| Outcome: | The proposed solution beats widely-used vocabularies in English-German translation, TED bilingual translation, and TED multilingual translation. |
Improving Lexical Choice in Neural Machine Translation (N18-1)
Copied to clipboard
| Challenge: | False positives: the output layer rewards frequent words disproportionately, we argue . Falsibles: a model that learns word representations in continuous space tends to translate rare words . |
| Approach: | They propose to fix the norms of both vectors to a constant value and integrate a lexical module which is jointly trained with the rest of the model. |
| Outcome: | The proposed approach achieves improvements of up to +4.3 BLEU surpassing phrase-based translation in nearly all settings. |
Finding the Optimal Vocabulary Size for Neural Machine Translation (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Class imbalance is said to exist when one or more classes are not of approximately equal frequency in data. |
| Approach: | They cast neural machine translation (NMT) as a classification task in an autoregressive setting and examine its limitations. |
| Outcome: | The proposed model performs better on multiple languages with large data sizes with different vocabulary sizes. |
Improving the Lexical Ability of Pretrained Language Models for Unsupervised Neural Machine Translation (2021.naacl-main)
Copied to clipboard
| Challenge: | Existing methods for unsupervised neural machine translation (UNMT) use cross-lingual pretraining to align the lexical- and high-level representations of two languages. |
| Approach: | They propose to use type-level cross-lingual subword embeddings to enhance the bilingual masked language model pretraining with lexical-level information to align the two languages. |
| Outcome: | Empirical results show that the method improves on UNMT (up to 4.5 BLEU) and bilingual lexicon induction compared to baseline models. |
The Devil is in the Details: On the Pitfalls of Vocabulary Selection in Neural Machine Translation (2022.naacl-main)
Copied to clipboard
| Challenge: | Neural Machine Translation models can be optimized to improve latency by constraining the set of output words . lexical shortlisting fails to select the right set of input words for semantically non-compositional phenomena such as idiomatic expressions. |
| Approach: | They propose a model of vocabulary selection that constrains the set of allowed output words . they propose to increase the size of the allowed set to restore translation quality . |
| Outcome: | The proposed model restores translation quality of an unconstrained system, as measured by human evaluations on WMT newstest2020 and idiomatic expressions, at an inference latency competitive with alignment-based selection using aggressive thresholds. |
Language Modeling, Lexical Translation, Reordering: The Training Process of NMT through the Lens of Classical SMT (2021.emnlp-main)
Copied to clipboard
| Challenge: | Statistical MT decomposes the translation task into distinct components that are learned separately. |
| Approach: | They show that neural machine translation models acquire different competences over the course of training . previous work shows how to improve some of the competences in NMT by using lexical translation probabilities, phrase memories, alignment information. |
| Outcome: | The proposed model improves translation quality and word-by-word translation, while learning complex reordering patterns. |
Encouraging Neural Machine Translation to Satisfy Terminology Constraints (2021.findings-acl)
Copied to clipboard
| Challenge: | a new approach to encourage neural machine translation to satisfy lexical constraints is proposed . a BLEU score and percentage of generated constraint terms are improved by the proposed method . |
| Approach: | They propose a method that encourages neural machine translation to satisfy lexical constraints at training step . they use a simplified augmentation strategy without source factors and constraint token masking to make it easier to learn the copy behavior . |
| Outcome: | The proposed method improves on baselines in terms of BLEU score and percentage of generated constraint terms. |
Effective Cross-lingual Transfer of Neural Machine Translation Models without Shared Vocabularies (P19-1)
Copied to clipboard
| Challenge: | Existing approaches to transfer a pretrained NMT model to a new, unrelated language without shared vocabularies are limited to cognate languages. |
| Approach: | They propose to transfer a pretrained NMT model to a new, unrelated language without shared vocabularies by using cross-lingual word embedding and injecting artificial noises. |
| Outcome: | The proposed methods outperform multilingual joint training by a large margin in five low-resource translation tasks. |
How Lexical is Bilingual Lexicon Induction? (2024.findings-naacl)
Copied to clipboard
| Challenge: | lexical variation and low-resource settings make it difficult to learn in low-level settings. |
| Approach: | They propose to incorporate additional lexical information into the retrieve-and-rank approach to improve lexicon induction. |
| Outcome: | The proposed approach improves on XLING by an average of 2% across all language pairs. |