NEURAL MACHINE TRANSLATION

Pieces of Eight: 8-bit Neural Machine Translation (N18-3)

Challenge:	Neural machine translation (NMT) has a drawback in that it can generate only high-frequency words owing to the computational costs of the softmax function in the output layer.
Approach:	They propose two methods to generate low-frequency words and deal with unknown words using Japanese predicate conjugation information without discarding linguistic information.
Outcome:	The proposed methods can generate low-frequency words and deal with unknown words.

Copied to clipboard

Jerry Quinn, Miguel Ballesteros

Multi-Task Neural Model for Agglutinative Language Translation (2020.acl-srw)

Challenge:	Neural machine translation models are trained using 32-bit floating point values and have improved fluency and adequacy.
Approach:	They propose to use 8-bit quantization to train models using 32-bit floating point values and show that 8- bit translation makes a non-negligible impact in terms of speed with no degradation in accuracy and adequacy.
Outcome:	The proposed method improves accuracy and accuracy without degradation in accuracy and adequacy.

Copied to clipboard

Yirong Pan, Xiao Li, Yating Yang, Rui Dong

Learning to Generate Word- and Phrase-Embeddings for Efficient Phrase-Based Neural Machine Translation (D19-56)

Challenge:	Neural machine translation (NMT) has been gaining popularity in high-resource translation tasks, but struggles in low-ressource and morphologically-rich scenarios.
Approach:	They propose a multi-task neural model that jointly learns to perform bi-directional translation and agglutinative language stemming.
Outcome:	The proposed model can significantly improve translation performance on agglutinative languages by using a small amount of monolingual data.

Copied to clipboard

Chan Young Park, Yulia Tsvetkov

Semantic Text Processing

Challenge:	Neural machine translation (NMT) often fails in one-to-many translation, e.g., in the translation of multi-word expressions, compounds, and collocations.
Approach:	They propose a phrase-based NMT model that generates embeddings of words or phrases.
Outcome:	The proposed model performs on par with state-of-the-art phrase-based NMT.

stopes - Modular Machine Translation Pipelines (2022.emnlp-demos)

Copied to clipboard

Pierre Andrews, Guillaume Wenzek, Kevin Heffernan, Onur Çelebi, Anna Sun, Ammar Kamran, Yingzhe Guo, Alexandre Mourachko, Holger Schwenk, Angela Fan

Robust Neural Machine Translation for Abugidas by Glyph Perturbation (2024.eacl-short)

Challenge:	Neural machine translation is a natural language deep learning application that needs data to be trained.
Approach:	They describe a framework that empowers scalability and versatility for research use cases.
Outcome:	The proposed framework empowers scalability and versatility for research use cases.

Copied to clipboard

Hour Kaing, Chenchen Ding, Hideki Tanaka, Masao Utiyama

Responsible & Trustworthy NLP

Challenge:	Neural machine translation systems are vulnerable when trained on limited data.
Approach:	They propose to add noise to the training phase to increase robustness of NMT systems trained on limited data.
Outcome:	The proposed training strategy overcomes noise and improves robustness for low-resource tasks for abugida glyphs.

Adversarially Improving NMT Robustness to ASR Errors with Confusion Sets (2022.aacl-short)

Copied to clipboard

Shuaibo Wang, Yufeng Chen, Songming Zhang, Deyi Xiong, Jinan Xu

Content Word Aware Neural Machine Translation (2020.acl-main)

Challenge:	Existing methods for robustness against homophone errors are limited to homophones . substitution errors are the most common errors in NMT models .
Approach:	They propose an adversarial example generation method based on confusion sets that contain words easily confusable with a target word by ASR to conduct adversarially training for NMT models.
Outcome:	The proposed method improves on the clean test set and can be used in real-world scenarios.

Copied to clipboard

Kehai Chen, Rui Wang, Masao Utiyama, Eiichiro Sumita

Synthesizing Parallel Data of User-Generated Texts with Zero-Shot Neural Machine Translation (2020.tacl-1)

Challenge:	Empirical results show that NMT does not consider word importance when predicting translations.
Approach:	They propose a content word-aware NMT model that exploits the results of translation using a sequence of content words learned by a simple content word recognition method.
Outcome:	Empirical results show that the proposed model improves translation performance . it uses word frequency information to distinguish between content and function words .

Copied to clipboard

Benjamin Marie, Atsushi Fujita

Modeling Task-Aware MIMO Cardinality for Efficient Multilingual Neural Machine Translation (2021.acl-short)

Challenge:	Neural machine translation systems are usually trained on clean parallel data, but the quality of translations is poor when translating noisy texts.
Approach:	They synthesize parallel data of UGT and exploit monolingual data to generate translations . they propose to use monolingual parallel data to train or adapt NMT systems .
Outcome:	The proposed approach improves the translation quality of noisy texts while making them more robust.

Copied to clipboard

Hongfei Xu, Qiuhui Liu, Josef van Genabith, Deyi Xiong

Dynamic Sentence Sampling for Efficient Training of Neural Machine Translation (P18-2)

Challenge:	Existing work has increased the modeling capacity of multilingual NMT by deepening or widening the Transformer.
Approach:	They propose to increase the model capacity by deepening the Transformer . they propose to use a multi-input-multi-output architecture to combine multiple inputs .
Outcome:	The proposed model surpasses previous work and is 1.31 times faster than existing models.

Copied to clipboard

Rui Wang, Masao Utiyama, Eiichiro Sumita

Compositional Representation of Morphologically-Rich Input for Neural Machine Translation (P18-2)

Challenge:	Existing methods to train neural machine translation (NMT) use a fixed training procedure where each sentence is sampled once during each epoch.
Approach:	They propose to dynamically sample sentences to accelerate NMT training . a weight is assigned to each sentence based on the measured difference between training costs of two iterations.
Outcome:	Empirical results show that the proposed method can significantly accelerate training and improve NMT performance.

Copied to clipboard

Duygu Ataman, Marcello Federico

Fusing Recency into Neural Machine Translation with an Inter-Sentence Gate Model (C18-1)

Challenge:	Neural machine translation models are typically trained with fixed-size input and output vocabularies, which creates a bottleneck on their accuracy and generalization capability.
Approach:	They propose to replace the source-language embedding layer of NMT with a bi-directional recurrent neural network that generates compositional representations of the input at any desired level of granularity.
Outcome:	The proposed approach outperforms existing methods in a low-resource setting with five languages . the proposed approach consistently outperformed existing methods with a single word representation .

Copied to clipboard

Shaohui Kuang, Deyi Xiong

A Survey of Domain Adaptation for Neural Machine Translation (C18-1)

Challenge:	Neural machine translation systems translate one sentence at a time, ignoring inter-sentence information.
Approach:	They propose an inter-sentence gate model that uses the same encoder to encode two adjacent sentences . it captures the connection between sentences and fuses recency from neighboring sentences a model proposes .
Outcome:	The proposed model improves on NIST Chinese-English translation tasks . it captures the connection between sentences and fuses recency from neighboring sentences .

Copied to clipboard

Chenhui Chu, Rui Wang

Did Translation Models Get More Robust Without Anyone Even Noticing? (2025.acl-long)

Challenge:	Neural machine translation (NMT) is a deep learning based approach for machine translation.
Approach:	They propose to use a deep learning approach to train machine translation in scenarios where large-scale parallel corpora are available.
Outcome:	The proposed approach yields the state-of-the-art translation performance in resource rich scenarios.

Copied to clipboard

Ben Peters, Andre Martins

Robustness in NLP

Challenge:	Neural machine translation models are highly sensitive to “noisy” inputs, such as spelling errors, abbreviations, and formatting issues.
Approach:	They revisit this insight in light of recent multilingual MT models and large language models applied to machine translation.
Outcome:	The proposed models perform better on clean data than previous models, but none of the open models use robustness techniques.

Neural Machine Translation for Bilingually Scarce Scenarios: a Deep Multi-Task Learning Approach (N18-1)

Copied to clipboard

Poorya Zaremoodi, Gholamreza Haffari

Neural Machine Translation with Decoding History Enhanced Attention (C18-1)

Challenge:	Neural machine translation requires large amount of parallel training text to learn a reasonable quality translation model.
Approach:	They propose a multi-task learning approach that leverages monolingual linguistic resources in the source side of a machine translation task.
Outcome:	The proposed approach is effective on three translation tasks: English-to-French, English- to-Farsi, and English-à-Vietnamese.

Copied to clipboard

Mingxuan Wang, Jun Xie, Zhixing Tan, Jinsong Su, Deyi Xiong, Chao Bian

CODET: A Benchmark for Contrastive Dialectal Evaluation of Machine Translation (2024.findings-eacl)

Challenge:	Neural machine translation with source-side attention has been criticized for its poor memory performance.
Approach:	They propose to use a Decoding History Enhanced Attention mechanism to render NMT models better at selecting both source-side and target-side information.
Outcome:	The proposed model improves by 0:9 BLEU on Chinese-English translation and the state-of-the-art on a larger task.

Copied to clipboard

Md Mahfuz Ibn Alam, Sina Ahmadi, Antonios Anastasopoulos

One Sentence One Model for Neural Machine Translation (L18-1)

Challenge:	Neural machine translation systems exhibit limited robustness in handling source-side linguistic variations.
Approach:	They propose a dialectal benchmark to quantify the robustness of MT systems to handle source-side linguistic variations.
Outcome:	The proposed benchmark demonstrates that large MT models face challenges translating dialectal variants.

Copied to clipboard

Xiaoqing Li, Jiajun Zhang, Chengqing Zong

Encoders Help You Disambiguate Word Senses in Neural Machine Translation (D19-1)

Challenge:	Neural machine translation (NMT) is a new state of the art that can produce better results than traditional statistical machine translation.
Approach:	They propose a dynamic neural network which learns a general network as usual and fine-tunes it for each test sentence.
Outcome:	The proposed method improves translation performance when similar sentences are available.

Copied to clipboard

Gongbo Tang, Rico Sennrich, Joakim Nivre

Language Models

Challenge:	Neural machine translation models can perform word sense disambiguation (WSD) however, it is unclear which component dominates the process of disambiguating words.
Approach:	They evaluate hidden states and investigate distributions of self-attention in NMT encoders and decoders to disambiguate word senses.
Outcome:	The proposed model outperforms encoder hidden states on large datasets . the model outpersforms decoders on large data sets .

Prompt-Driven Neural Machine Translation (2022.findings-acl)

Copied to clipboard

Yafu Li, Yongjing Yin, Jing Li, Yue Zhang

Towards Enhancing Faithfulness for Neural Machine Translation (2020.emnlp-main)

Challenge:	Neural machine translation models still face various challenges including fragility and lack of style flexibility.
Approach:	They propose to incorporate prompts into neural machine translation to improve translation control and style flexibility.
Outcome:	Empirical results show that the proposed method improves translation control and quality and improves human-in-the-loop translation.

Copied to clipboard

Rongxiang Weng, Heng Yu, Xiangpeng Wei, Weihua Luo

BiVert: Bidirectional Vocabulary Evaluation Using Relations for Machine Translation (2024.lrec-main)

Challenge:	Neural machine translation (NMT) has achieved great success due to the ability to generate high-quality sentences.
Approach:	They propose a training strategy with a multi-task learning paradigm to build a faithfulness enhanced NMT model.
Outcome:	The proposed model can generate high-quality sentences that are very close to natural language.

Copied to clipboard

Carinne Cherf, Yuval Pinter

Two Parents, One Child: Dual Transfer for Low-Resource Neural Machine Translation (2021.findings-acl)

Challenge:	Neural machine translation (NMT) evaluation is crucial to determine the quality of translations.
Approach:	They propose a bidirectional semantic-based evaluation method to assess the sense distance of the translation from the source text.
Outcome:	The proposed method uses the multilingual encyclopedic dictionary BabelNet . it shows a strong correlation between the evaluation scores and human assessments .

Copied to clipboard

Meng Zhang, Liangyou Li, Qun Liu

Robust Neural Machine Translation with Joint Textual and Phonetic Embedding (P19-1)

Challenge:	Neural machine translation suffers when parallel data is scarce for training . a new framework to transfer multiple sources of auxiliary data is proposed .
Approach:	They propose a framework to transfer multiple sources of auxiliary data from high-resource parallel data to low-resourced translation models using pretrained language models.
Outcome:	The proposed approach yields consistent improvements over strong competitors for multiple translation directions.

Copied to clipboard

Hairong Liu, Mingbo Ma, Liang Huang, Hao Xiong, Zhongjun He

Syntactic Text Processing

Challenge:	Neural machine translation models are sensitive to noises in input sentences . one special kind of noise is the homophone noise, where words are replaced by other words with similar pronunciations.
Approach:	They propose to embed phonetic and textual information into neural machine translation datasets to improve robustness to homophone noises.
Outcome:	The proposed method improves the robustness of neural machine translation to homophone noises on clean test sets.

Lattice-Based Transformer Encoder for Neural Machine Translation (P19-1)

Copied to clipboard

Fengshun Xiao, Jiangtong Li, Hai Zhao, Rui Wang, Kehai Chen

Semantic Text Processing

Challenge:	Neural machine translation (NMT) takes deterministic sequences for source representations. However, word-level or subword-level segmentation has multiple choices to split a source sequence with different word segmentors or different subword vocabulary sizes.
Approach:	They propose lattice-based encoders to explore effective word or subword representations in an automatic way during training.
Outcome:	The proposed encoders can explore effective word or subword representation in an automatic way during training.

Continual Learning for Neural Machine Translation (2021.naacl-main)

Copied to clipboard

Yue Cao, Hao-Ran Wei, Boxing Chen, Xiaojun Wan

Competency-Aware Neural Machine Translation: Can Machine Translation Know its Own Translation Quality? (2022.emnlp-main)

Challenge:	Neural machine translation models are data-driven and require large-scale training corpus . continual learning remains a big challenge for artificial intelligence systems and models .
Approach:	They propose a continual learning framework for NMT models that incorporates multiple stages of training to alleviate catastrophic forgetting problem.
Outcome:	The proposed framework achieves superior performance compared to baseline models in all settings.

Copied to clipboard

Pei Zhang, Baosong Yang, Hao-Ran Wei, Dayiheng Liu, Kai Fan, Luo Si, Jun Xie

Distilling Multiple Domains for Neural Machine Translation (2020.emnlp-main)

Challenge:	Neural machine translation models are often criticized for failures that happen without competency awareness.
Approach:	They propose a method that extends conventional NMT with a self-estimator to translate a source sentence and estimate its competency.
Outcome:	The proposed method performs on translation tasks intact and on quality estimation tasks better than existing methods.

Copied to clipboard

Anna Currey, Prashant Mathur, Georgiana Dinu

Responsible & Trustworthy NLP

Challenge:	Neural machine translation is a powerful tool for high-resource domains, but performance suffers when the input domain is low-resourced.
Approach:	They propose a framework for training a single multi-domain neural machine translation model that can translate multiple domains without increasing inference time or memory usage.
Outcome:	The proposed model improves translation on both high- and low-resource domains over strong multi-domain baselines and is robust under noisy data conditions.

Token Drop mechanism for Neural Machine Translation (2020.coling-main)

Copied to clipboard

Huaao Zhang, Shigui Qiu, Xiangyu Duan, Min Zhang

Investigating Catastrophic Forgetting During Continual Training for Neural Machine Translation (2020.coling-main)

Challenge:	Neural machine translation models are vulnerable to unfamiliar inputs.
Approach:	They propose to drop tokens of the input sentences to improve generalization and avoid overfitting for the NMT model.
Outcome:	The proposed approach improves on Chinese-English and English-Romanian benchmarks and achieves significant performance improvements over baselines.

Copied to clipboard

Shuhao Gu, Yang Feng

Beyond Error Propagation in Neural Machine Translation: Characteristics of Language Also Matter (D18-1)

Challenge:	Neural machine translation models suffer from catastrophic forgetting during continual training . models tend to overfit to frequent observations in the in-domain data but forget previously learned knowledge.
Approach:	They investigated the causes of catastrophic forgetting in NMT models by examining their parameters and modules.
Outcome:	The proposed model forgets previously learned knowledge and swings to fit new data . the results show that some parameters are important for both the general-domain and in-domain translation and the great change of them during continual training brings about the performance decline in general- domain.

Copied to clipboard

Lijun Wu, Xu Tan, Di He, Fei Tian, Tao Qin, Jianhuang Lai, Tie-Yan Liu

Effective Use of Target-side Context for Neural Machine Translation (2020.coling-main)

Challenge:	Neural machine translation suffers from exposure bias and error propagation problem.
Approach:	They conduct a series of analyses to deeply understand the accuracy drop problem . they find that the left part of the translated sentence is often better than its right part .
Outcome:	The results show that the left part of the translated sentence is often better than its right part in left-to-right decoding models.

Copied to clipboard

Hideya Mino, Hitoshi Ito, Isao Goto, Ichiro Yamada, Takenobu Tokunaga

Robust Neural Machine Translation with Doubly Adversarial Inputs (P19-1)

Challenge:	Existing methods to train NMT systems with noisy data are not sufficient . et al., 2018) found that NMT models can learn with multiple types of corpora .
Approach:	They propose a Japanese-English news corpus that is content-equivalent . they extend a domain-adaptation method to train NMT models with clean corpus .
Outcome:	The proposed corpus improves translation quality and is more efficient than existing methods.

Copied to clipboard

Yong Cheng, Lu Jiang, Wolfgang Macherey

Robustness in NLP

Challenge:	Neural machine translation (NMT) models suffer from noisy perturbations in the input . a gradient-based method to craft adversarial examples informed by the translation loss is proposed .
Approach:	They propose an approach to improve the robustness of NMT models by attacking the translation model with adversarial source examples and defending the model with a target input.
Outcome:	The proposed approach improves translation performance and robustness on clean inputs and higher on noisy data.

Foiling Training-Time Attacks on Neural Machine Translation Systems (2022.findings-emnlp)

Copied to clipboard

Jun Wang, Xuanli He, Benjamin Rubinstein, Trevor Cohn

Robustness in NLP

Challenge:	Neural machine translation systems are vulnerable to backdoor attacks . successful backdoors can cause slander, hate speech, phishing, etc. attacks can target very short trigger phrases, which can be challenging to detect even when included verbatim in poisoned instances.
Approach:	They propose a method that exploits asymmetry between source and target sentences to detect outlier tokens.
Outcome:	The proposed method reduces the success of attacks by up to 89.0% while not affecting predictive accuracy.

Neural Machine Translation for Low-Resourced Indian Languages (2020.lrec-1)

Copied to clipboard

Himanshu Choudhary, Shivansh Rao, Rajesh Rohilla

Content-Equivalent Translated Parallel News Corpus and Extension of Domain Adaptation for NMT (2020.lrec-1)

Challenge:	Neural machine translation (NMT) is an effective way to convert text to a different language without human involvement.
Approach:	They propose to use multihead self-attention along with pre-trained Byte-Pair-Encoded (BPE) and MultiBPE embeddings to develop an efficient machine translation system.
Outcome:	The proposed system outperforms Google translator and the existing translators on two of the most morphological rich Indian languages.

Copied to clipboard

Hideya Mino, Hideki Tanaka, Hitoshi Ito, Isao Goto, Ichiro Yamada, Takenobu Tokunaga

Machine Translation With Weakly Paired Documents (D19-1)

Challenge:	Existing methods to train NMT systems with noisy data are not sufficient . a recent increase in foreigners visiting Japan has created a significant information gap .
Approach:	They propose a Japanese-English parallel news corpus that is content-equivalent . they extend a domain-adaptation method to train NMT models with clean corpus .
Outcome:	The proposed corpus improves translation quality and is more effective than existing methods.

Copied to clipboard

Lijun Wu, Jinhua Zhu, Di He, Fei Gao, Tao Qin, Jianhuang Lai, Tie-Yan Liu

JASS: Japanese-specific Sequence to Sequence Pre-training for Neural Machine Translation (2020.lrec-1)

Challenge:	Recent studies explore the possibility of unsupervised machine translation with monolingual data only.
Approach:	They propose a method to mine bilingual sentences from weakly paired documents . they use word distribution-level alignments to constrain word distributions of two weakly-paired documents.
Outcome:	The proposed method outperforms previous results on six translation tasks using weakly paired bilingual documents and a large number of bilingual sentences.

Copied to clipboard

Zhuoyuan Mao, Fabien Cromieres, Raj Dabre, Haiyue Song, Sadao Kurohashi

Enhancing Neural Machine Translation Through Target Language Data: A kNN-LM Approach for Domain Adaptation (2025.acl-long)

Challenge:	Neural machine translation (NMT) requires large parallel corpora for training robust and high quality models.
Approach:	They propose a Japanese-specific sequence to sequence pre-training alternative to MASS for NMT . they use Japanese as the source or target language to train their models .
Outcome:	The proposed approach can give competitive results over MASS and BRSS, and significantly surpass the individual methods.

Copied to clipboard

Abudurexiti Reheman, Hongyu Liu, Junhao Ruan, Abudukeyumu Abudula, Yingfeng Luo, Tong Xiao, JingBo Zhu

Greedy Search with Probabilistic N-gram Matching for Neural Machine Translation (D18-1)

Challenge:	Neural machine translation (NMT) has made significant progress in recent years, yet often suffers from translating in new domains, which is called domain adaptation.
Approach:	They propose a method that leverages semantically similar target language sentences in the kNN framework and generates a probability distribution over these sentences during decoding.
Outcome:	The proposed method generates a probability distribution over similar target language sentences and then interpolates with the model’s distribution.

Copied to clipboard

Chenze Shao, Xilin Chen, Yang Feng

CHIA: CHoosing Instances to Annotate for Machine Translation (2022.findings-emnlp)

Challenge:	Neural machine translation models are usually trained with word-level loss under teacher forcing algorithm . however, this method suffers from exposure bias due to high variance of gradient estimation .
Approach:	They propose a method with a differentiable sequence-level training objective . they use greedy search to alleviate the problem of exposure bias .
Outcome:	Experiments on Chinese-to-English translation tasks show that the proposed method outperforms the reinforcement-based methods.

Copied to clipboard

Rajat Bhatnagar, Ananya Ganesh, Katharina Kann

Esposito: An English-Persian Scientific Parallel Corpus for Machine Translation (2024.lrec-main)

Challenge:	Neural machine translation systems perform poorly on low-resource language pairs, for which large-scale parallel data is unavailable.
Approach:	They propose a method for selecting instances to annotate for machine translation using existing multi-way parallel datasets.
Outcome:	The proposed method outperforms unsupervised methods on 20 languages and a multi-way parallel dataset on high-resource languages.

Copied to clipboard

Mersad Esalati, Mohammad Javad Dousti, Heshaam Faili

Simul-LLM: A Framework for Exploring High-Quality Simultaneous Translation with Large Language Models (2024.acl-long)

Challenge:	Existing scientific corpus for English-Persian language pairs is lacking . supervised neural machine translation requires millions of parallel sentences .
Approach:	They propose a parallel corpus called Esposito which contains 3.5 million parallel sentences . they also propose 'test sets' that might serve as a baseline for future studies .
Outcome:	The proposed system improves the baseline on average by 7.6 and 8.4 BLEU scores for English-Persian language pairs.

Copied to clipboard

Victor Agostinelli, Max Wild, Matthew Raffel, Kazi Fuad, Lizhong Chen

Language Models

Challenge:	Modern large language models (LLMs) contain billions of parameters and can perform a variety of downstream tasks.
Approach:	They propose an open-source framework for fine-tuning large language models (LLMs) they address key challenges facing LLMs fine- tuned for simultaneous translation .
Outcome:	The proposed framework validates classical SimulMT concepts and practices in the context of LLMs and explores adapting LLM fine-tuned for NMT to the task of Simul-LLM.

Uncertainty-Aware Curriculum Learning for Neural Machine Translation (2020.acl-main)

Copied to clipboard

Yikai Zhou, Baosong Yang, Derek F. Wong, Yu Wan, Lidia S. Chao

Language Models

Challenge:	Neural machine translation (NMT) has proven to be facilitated by curriculum learning which presents examples in an easy-to-hard order at different training stages.
Approach:	They propose to use an uncertainty-aware curriculum learning approach to assess data difficulty and model competence to provide examples in an easy-to-hard order at different training stages.
Outcome:	The proposed approach outperforms baseline and related methods on translation quality and convergence speed.

Addressing Entity Translation Problem via Translation Difficulty and Context Diversity (2024.findings-acl)

Copied to clipboard

Tian Liang, Xing Wang, Mingming Yang, Yujiu Yang, Shuming Shi, Zhaopeng Tu

Optimal Transport for Unsupervised Hallucination Detection in Neural Machine Translation (2023.acl-long)

Challenge:	Neural machine translation systems often produce inadequate translations for named entities.
Approach:	They propose a data augmentation strategy to enhance the accuracy of named entity translation by retraining the target named entity pair.
Outcome:	The proposed method improves translation accuracy across test sets and terminology tests.

Copied to clipboard

Nuno M. Guerreiro, Pierre Colombo, Pablo Piantanida, André Martins

Exploring Discourse Structure in Document-level Machine Translation (2023.emnlp-main)

Challenge:	Neural machine translation models can unpredictably produce severely pathological translations, known as hallucinations, that seriously undermine user trust.
Approach:	They propose a fully unsupervised, plug-in detector that can be used with any attention-based NMT model.
Outcome:	The proposed detector outperforms existing models and is competitive with detectors that employ external models trained on millions of samples.

Copied to clipboard

Xinyu Hu, Xiaojun Wan

INK: Injecting kNN Knowledge in Nearest Neighbor Machine Translation (2023.acl-long)

Challenge:	Existing methods for document-level machine translation (DocMT) are under-utilizing the context.
Approach:	They propose a paragraph-to-paragraph translation mode that utilizes discourse information . they propose 'speech-based' translation mode which utilizes contextual information based on the context .
Outcome:	The proposed method utilizes discourse information and performs better than previous methods.

Copied to clipboard

Wenhao Zhu, Jingjing Xu, Shujian Huang, Lingpeng Kong, Jiajun Chen

Kumatigi: Quality-Driven Data Augmentation for Low-Resource Machine Translation (2026.findings-acl)

Challenge:	Neural machine translation models induce a non-smooth representation space, which harms its generalization results.
Approach:	They propose a framework to smooth the representation space by adjusting neighbor representations with a small number of new parameters.
Outcome:	The proposed framework outperforms the state-of-the-art kNN-MT system with average gains of 1.99 COMET and 1.0 BLEU on four benchmark datasets.

Copied to clipboard

Cheick Tidiani Cissé

Multi-perspective Alignment for Increasing Naturalness in Neural Machine Translation (2025.acl-long)

Challenge:	Neural machine translation for extremely low-resource languages faces compounding challenges: limited parallel data, orthographic inconsistency, and inconsistent metadata for principled training.
Approach:	They propose a quality-annotated French-Bambara corpus combining systematic curation with data augmentation strategies tailored to Bambaran.
Outcome:	The proposed framework achieves up to +3–4 BLEU over strong baselines.

Copied to clipboard

Huiyuan Lai, Esther Ploeger, Rik Van Noord, Antonio Toral