Papers with neural machine translation models
Context-aware Neural Machine Translation with Coreference Information (D19-65)
Copied to clipboard
| Challenge: | Existing models for translating a sentence in a text do not consider coreference relations provided within the text. |
| Approach: | They propose a graph-based encoder which can consider coreference relations provided within the text explicitly. |
| Outcome: | The proposed model improves on the previous approach by 0.9 points on the BLEU score . the graph-based encoder can handle a longer text well, compared with the previous model . |
Translating Headers of Tabular Data: A Pilot Study of Schema Translation (2021.emnlp-main)
Copied to clipboard
| Challenge: | Schema translation is not well studied in the community because of morphological difference and context difference between plain text and tabular data. |
| Approach: | They propose a schema translation model augmented with schema context . they model a target header and its context as a directed graph to represent their entities . |
| Outcome: | The proposed model outperforms state-of-the-art models on schema translation . it uses a graph to represent entity types and relations, and a relational-aware transformer . |
Hie-BART: Document Summarization with Hierarchical BART (2021.naacl-srw)
Copied to clipboard
| Challenge: | Existing document summarization models do not capture hierarchical structures of documents . proposed model incorporates multi-granularity self-attention (MG-SA) |
| Approach: | They propose a new abstractive document summarization model, hierarchical BART . the proposed model captures hierarchically structured sentences in the BART model . |
| Outcome: | The proposed model outperforms baseline models and improves performance on CNN/Daily Mail dataset. |
Bag-of-Words as Target for Neural Machine Translation (P18-2)
Copied to clipboard
| Challenge: | Existing neural machine translation models only use one correct sentence as the target, and the other correct sentences are punished as the incorrect ones. |
| Approach: | They propose an approach that uses both the sentences and the bag-of-words as targets in the training stage to encourage the model to generate the potentially correct sentences that are not appeared in the train set. |
| Outcome: | The proposed model outperforms baseline models on a Chinese-English translation dataset by the BLEU score of 4.55. |
Improving Beam Search by Removing Monotonic Constraint for Neural Machine Translation (P18-2)
Copied to clipboard
| Challenge: | a beam search algorithm produces monotonic left-to-right order, meaning a hypothesis cannot be revisited . a proposed algorithm allows discarded hypotheses to be recovered in a later step. |
| Approach: | They propose to decode a beam search algorithm that considers multiple hypotheses simultaneously . they propose to maintain all found hypothese a single priority queue and a universal score function . |
| Outcome: | The proposed algorithm improves translations even for high-performance models in English-Japanese translation task. |
Focus on the Target’s Vocabulary: Masked Label Smoothing for Machine Translation (2022.acl-short)
Copied to clipboard
| Challenge: | Label smoothing and vocabulary sharing are widely used in neural machine translation models, but they can be conflicting and lead to suboptimal performance. |
| Approach: | They propose a mechanism that masks the soft label probability of source-side words to zero and integrates label smoothing with vocabulary sharing to improve translation quality. |
| Outcome: | The proposed mechanism improves translation quality and model calibration on bilingual and multilingual datasets, while retaining the original smoothing method. |
Cheating to Identify Hard Problems for Neural Machine Translation (2023.findings-eacl)
Copied to clipboard
| Challenge: | We find that the most frequent tokens are not necessarily the most accurately translated due to these often being function words and punctuation that can be used more flexibly in translation. |
| Approach: | They propose a method to provide a compressed representation of the target as an input and a second method to fine-tune a standard transformer model. |
| Outcome: | The proposed method produces models with higher scores, but with more errors . the proposed method is based on two forms of cheating: providing a compressed representation of the target as an input and fine-tuning on the test set. |
Overcoming Catastrophic Forgetting beyond Continual Learning: Balanced Training for Neural Machine Translation (2022.acl-long)
Copied to clipboard
| Challenge: | Neural networks tend to gradually forget the previously learned knowledge when learning multiple tasks sequentially from dynamic data distributions. |
| Approach: | They propose a method that iteratively provides complementary knowledge to student models by dynamically updating teacher models trained on specific data orders. |
| Outcome: | The proposed method improves on multiple machine translation tasks and improves performance over baseline systems. |
Enhancing Machine Translation with Dependency-Aware Self-Attention (2020.acl-main)
Copied to clipboard
| Challenge: | Currently, most neural machine translation models rely on pairs of parallel sentences, assuming syntactic information is automatically learned by an attention mechanism. |
| Approach: | They propose a parameter-free, dependency-aware self-attention mechanism that integrates syntactic knowledge into a Transformer model and propose 'a parameter free approach' they also propose - a novel mechanism that improves translation quality for long sentences and in low-resource scenarios. |
| Outcome: | The proposed approach improves translation quality on English-German and English-Turkish translation tasks and in low-resource scenarios. |
Unsupervised Domain Adaptation for Neural Machine Translation with Domain-Aware Feature Embeddings (D19-1)
Copied to clipboard
| Challenge: | Recent studies have focused on domain adaptation for neural machine translation systems where in-domain data is scarce or nonexistent. |
| Approach: | They propose an approach that adapts models with domain-aware feature embeddings, which are learned via an auxiliary language modeling task. |
| Outcome: | The proposed model performs better in multiple experimental settings and with back translation. |
Curated Datasets and Neural Models for Machine Translation of Informal Registers between Mayan and Spanish Vernaculars (2024.naacl-long)
Copied to clipboard
| Challenge: | a set of corpora in several Mayan languages spoken in Guatemala and Mexico is published . the languages are considered to be somewhat in decline in terms of resources and global exposure . |
| Approach: | They develop, curate, and publicly release a set of corpora in several Mayan languages spoken in Guatemala and southern Mexico, which they call MayanV. |
| Outcome: | The proposed datasets are parallel with Spanish, the dominant language of the region, and differ in register from most other available resources. |
Single Model Ensemble for Subword Regularized Models in Low-Resource Machine Translation (2022.findings-acl)
Copied to clipboard
| Challenge: | Existing subword regularizations use multiple segmentations during training but only use one segmentation in inference. |
| Approach: | They propose an inference strategy that uses multiple subword segmentations to solve this discrepancy in the training process and inference. |
| Outcome: | The proposed strategy reduces the cost of training and improves the performance of models trained with subword regularization in low-resource machine translation tasks. |
Paraphrase Generation and Evaluation on Colloquial-Style Sentences (2020.lrec-1)
Copied to clipboard
| Challenge: | a new study investigates the quality and novelty of generated paraphrases . paraphrase models can be used for information retrieval and data mining . |
| Approach: | They use state-of-the-art neural machine translation models trained on the Opusparcus corpus to generate paraphrases in six languages. |
| Outcome: | The proposed model outperforms the existing model on human evaluation in five of the six languages. |
Manifold Adversarial Augmentation for Neural Machine Translation (2021.findings-acl)
Copied to clipboard
| Challenge: | Recent studies show that NMT models can drop significantly when small perturbations are added to input sentences. |
| Approach: | They propose a data augmentation approach to sample sentences from the vicinity distributions in higher-level representations. |
| Outcome: | The proposed method improves translation accuracy on training samples from higher-level representations. |
Smart-Start Decoding for Neural Machine Translation (2021.naacl-main)
Copied to clipboard
| Challenge: | Existing neural machine translation models adopt a monotonic decoding order of either left-to-right or right-to left. |
| Approach: | They propose a method that starts decoding target words from the right side of a median word and generates words on the left. |
| Outcome: | The proposed method outperforms baseline models on three datasets. |
Learning to Jointly Translate and Predict Dropped Pronouns with a Shared Reconstruction Mechanism (D18-1)
Copied to clipboard
| Challenge: | Pronouns are often omitted in pro-drop languages, such as Chinese . this leads to various translation problems in terms of completeness, syntax and semantics . |
| Approach: | They propose a reconstruction-based approach to alleviate dropped pronoun (DP) translation problems for neural machine translation models by employing a shared reconstructor and a joint learning approach. |
| Outcome: | The proposed approach improves translation performance and accuracy of DP predictions. |
The Fine-Tuning Paradox: Boosting Translation Quality Without Sacrificing LLM Abilities (2024.acl-long)
Copied to clipboard
| Challenge: | Recent studies have shown that fine-tuning large language models improves their translations, but it is unclear what is the impact on desirable LLM behaviors that are not present in neural machine translation models. |
| Approach: | They perform an extensive translation evaluation on LLaMA and Falcon models with model size ranging from 7 billion up to 65 billion parameters. |
| Outcome: | The proposed model produces less literal translations after fine-tuning on parallel data. |
CodeTransOcean: A Comprehensive Multilingual Benchmark for Code Translation (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing code translation datasets focus on a single pair of programming languages . early software systems are developed using programming languages such as Fortran and COBOL . |
| Approach: | They propose a large-scale comprehensive benchmark that supports the largest variety of programming languages for code translation. |
| Outcome: | The proposed framework supports translations between multiple programming languages and a cross-framework dataset for deep learning code across different frameworks. |
Mask-Align: Self-Supervised Neural Word Alignment (2021.acl-long)
Copied to clipboard
| Challenge: | Word alignment is an important task in many natural language processing tasks. |
| Approach: | They propose a self-supervised word alignment model that takes advantage of the full context on the target side. |
| Outcome: | The proposed model outperforms previous unsupervised models and obtains state-of-the-art results on four language pairs. |
Normalizing Mutual Information for Robust Adaptive Training for Translation (2022.emnlp-main)
Copied to clipboard
| Challenge: | Neural machine translation models have been reported to generate hallucinations . despite the success of the models, there are still challenges to improve fluency . |
| Approach: | They propose a scoring metric for the importance of target sentences and tokens to encourage fluent translations. |
| Outcome: | The proposed metric improves translation fluency and source-faithfulness . the proposed nmi model is not properly normalized, the authors argue . |
Discriminative Reranking for Neural Machine Translation (2021.acl-long)
Copied to clipboard
| Challenge: | reranking models allow the integration of rich features to select a better output hypothesis within an n-best list or lattice. |
| Approach: | They use discriminative reranking to train a large transformer architecture to train an ranked list of hypotheses. |
| Outcome: | Experiments on four WMT directions show that discriminative reranking improves translation quality. |
Extended Parallel Corpus for Amharic-English Machine Translation (2022.lrec-1)
Copied to clipboard
| Challenge: | Existing approaches to automate the complex task of translation are tedious and expensive. |
| Approach: | They describe acquisition, preprocessing, segmentation, and alignment of an Amharic-English parallel corpus. |
| Outcome: | The proposed corpus outperforms statistical machine translation models by six to seven BLEU points . the results show that the subword models outperformed word-based models by three to four BLUE points compared with the word-base models . |
Enhancing Accessible Communication: from European Portuguese to Portuguese Sign Language (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing systems for translating European Portuguese into LGP glosses rely on hand-crafted rules . current systems rely only on toy examples, disregarding non-manual movements . |
| Approach: | They propose a corpora-driven rule-based machine translation system between European Portuguese and LGP glosses and two neural machine translation models. |
| Outcome: | The proposed system improves on existing translation systems and annotates a gold collection of the results. |
Evaluating Structural Generalization in Neural Machine Translation (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing studies have focused on compositional generalization with semantic parsing, but it remains unclear to what extent models can translate sentences that require structural generalization. |
| Approach: | They construct a machine translation dataset that measures compositional generalization with control of words and sentence structures. |
| Outcome: | The proposed model struggle more in structural generalization than in compositional generalization. |
Applying Intrinsic Debiasing on Downstream Tasks: Challenges and Considerations for Machine Translation (2024.emnlp-main)
Copied to clipboard
| Challenge: | In this study, we examine three considerations for intrinsic debiasing in neural machine translation models. |
| Approach: | They propose to measure the extrinsic bias of neural machine translation models by embedding them in a neural embeddable space and using different tokens to debias them. |
| Outcome: | The proposed methods over-rely on gender stereotypes and over-represent them in their models. |