TRANSLATION MODEL

Domain-specific transformer models for query translation (2023.acl-industry)

Challenge:	a recent study shows that without artificially encouraging models to hallucinate, existing methods fall short . hallucinations are cases when the model generates output that is partially or fully unrelated to the source sentence.
Approach:	They propose a method that evaluates the percentage of the source contribution to a generated translation.
Outcome:	The proposed method improves detection accuracy for the most severe hallucinations by a factor of 2.

Copied to clipboard

Mandar Kulkarni, Nikesh Garera, Anusua Trivedi

Improving Mongolian-Chinese Neural Machine Translation with Morphological Noise (P19-2)

Challenge:	In domains such as Grocery, users prefer to buy certain brands of products . a large non-English speaking population makes it difficult to translate code-mix queries .
Approach:	They propose a model to preserve/correct Grocery brand names while translating context words . they propose to use a dataset of popular Groceries brand names to train the model .
Outcome:	The proposed model preserves/corrects Grocery brand names while translating context words . it is tested with a large non-English speaking population and is deployed in production .

Copied to clipboard

Yatu Ji, Hongxu Hou, Chen Junjie, Nier Wu

Responsible & Trustworthy NLP

Challenge:	Existing models for Mongolian-Chinese translation are based on recurrent, convolutional neural networks or completely eliminate recurrence connections.
Approach:	They propose a adversarial training model to alleviate the UNK problem in Mongolian-Chinese machine translation by adding a screener to the model to emphasize the added Mongolian morphological noise.
Outcome:	The proposed model reduces training time and improves accuracy in Mongolian-Chinese translation tasks.

Restricted or Not: A General Training Framework for Neural Machine Translation (2022.acl-srw)

Copied to clipboard

Zuchao Li, Masao Utiyama, Eiichiro Sumita, Hai Zhao

Improving Retrieval Augmented Neural Machine Translation by Controlling Source and Fuzzy-Match Interactions (2023.findings-eacl)

Challenge:	Existing work imposes constraints on beam search decoding, which limits the concurrent processing ability of the model in deployment.
Approach:	They propose a general training framework that allows a model to support both restricted and unrestricted translations by adopting an additional auxiliary training process without constraining the decoding process.
Outcome:	The proposed training framework is tested on simulated and original benchmarks.

Copied to clipboard

Cuong Hoang, Devendra Sachan, Prashant Mathur, Brian Thompson, Marcello Federico

Learning Language Specific Sub-network for Multilingual Machine Translation (2021.acl-long)

Challenge:	a general-domain model has access to customer or domain specific parallel data at inference time, but not during training.
Approach:	They propose a zero-shot adaptation approach where a general-domain model has access to customer or domain specific parallel data at inference time, but not during training.
Outcome:	The proposed architecture outperforms existing architectures in two language pairs . it consistently improves BLEU across language pair, domain, and number k of fuzzy matches .

Copied to clipboard

Zehui Lin, Liwei Wu, Mingxuan Wang, Lei Li

Improving Grammatical Error Correction with Machine Translation Pairs (2020.findings-emnlp)

Challenge:	Multilingual neural machine translation models suffer from performance degradation when learning multiple languages.
Approach:	They propose to use LaSS to jointly train a single unified multilingual MT model.
Outcome:	The proposed model gains on 36 language pairs by up to 1.2 BLEU and zero-shot translation with 8.3 BLUE on 30 language pairs.

Copied to clipboard

Wangchunshu Zhou, Tao Ge, Chang Mu, Ke Xu, Furu Wei, Ming Zhou

Prosody in Cascade and Direct Speech-to-Text Translation: a case study on Korean Wh-Phrases (2024.findings-eacl)

Challenge:	Existing methods to generate error-corrected sentence pairs for improving grammatical error correction are not available.
Approach:	They propose a method to generate error-corrected sentence pairs for improving grammatical error correction based on machine translation models of different qualities .
Outcome:	The proposed method can generate multiple error-corrected sentence pairs from Chinese to English text.

Copied to clipboard

Giulio Zhou, Tsz Kin Lam, Alexandra Birch, Barry Haddow

Understanding and Improving Hidden Representations for Neural Machine Translation (N19-1)

Challenge:	Existing direct S2TT systems have been unable to disambiguate utterances where prosody plays a crucial role.
Approach:	They propose to use contrastive evaluation to quantitatively measure the ability of direct S2TT systems to disambiguate utterances where prosody plays a crucial role.
Outcome:	The proposed system improves overall accuracy 12.9% and improves intent scores 15.6%.

Copied to clipboard

Guanlin Li, Lemao Liu, Xintong Li, Conghui Zhu, Tiejun Zhao, Shuming Shi

A Hybrid Approach for Automatic Extraction of Bilingual Multiword Expressions from Parallel Corpora (L18-1)

Challenge:	Existing studies have explored some methods for understanding hidden representations, but they have not sought to improve the translation quality rationally according to their understanding.
Approach:	They propose to construct a sequence of nested relative tasks and measure the feature generalization ability of the learned hidden representation over these tasks.
Outcome:	The proposed methods achieve consistent improvements (up to +1.3 BLEU) on two widely-used datasets.

Copied to clipboard

Nasredine Semmar

As Little as Possible, as Much as Necessary: Detecting Over- and Undertranslations with Contrastive Conditioning (2022.acl-short)

Challenge:	Specific-domain bilingual lexicons are composed of MultiWord Expressions (MWEs) the manual construction of MWEs bilingual dictionaries is costly and time-consuming.
Approach:	They propose to use word alignment approaches to automatically construct bilingual lexicons of MWEs from parallel corpora by formalizing the alignment process as an integer linear programming problem.
Outcome:	The proposed approach extracts and aligns multiword expressions from parallel corpora and then filters them using linguistic patterns to build bilingual lexicons.

Copied to clipboard

Jannis Vamvas, Rico Sennrich

Focus on the Target’s Vocabulary: Masked Label Smoothing for Machine Translation (2022.acl-short)

Challenge:	Neural machine translation is susceptible to coverage errors such as the addition of superfluous target words or the omission of important source content.
Approach:	They propose a method for detecting Omission and addition errors with off-the-shelf translation models.
Outcome:	The proposed method is comparable to a supervised method that requires a custom quality estimation model.

Copied to clipboard

Liang Chen, Runxin Xu, Baobao Chang

Analysis on Unsupervised Acquisition Process of Bilingual Vocabulary through Iterative Back-Translation (2024.lrec-main)

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.

Copied to clipboard

Takuma Tanigawa, Tomoyosi Akiba, Hajime Tsukada

PsFuture: A Pseudo-Future-based Zero-Shot Adaptive Policy for Simultaneous Machine Translation (2024.emnlp-main)

Challenge:	Existing studies have demonstrated the effectiveness of iterative back-translation, but its reason has not been sufficiently elucidated.
Approach:	They propose a method for machine translation known as iterative back-translation . they use two monolingual data to create a pseudo-bilingual data and update translation models .
Outcome:	The proposed method improves translation quality and improves BLEU.

Copied to clipboard

Libo Zhao, Jing Li, Ziqian Zeng

On Measuring Context Utilization in Document-Level MT Systems (2024.findings-eacl)

Challenge:	Simultaneous machine translation (SiMT) requires target tokens to be generated in real-time as streaming source tokens are consumed.
Approach:	They propose a zero-shot adaptive read/write policy for siMT that generates target tokens concurrently as streaming source tokens are consumed.
Outcome:	The proposed policy achieves performance on par with strong baselines and the P2F method can further enhance performance.

Copied to clipboard

Wafaa Mohammed, Vlad Niculae

Context-Aware Neural Machine Translation Learns Anaphora Resolution (P18-1)

Challenge:	Current studies on document-level translation evaluation focus on sentence-level models which are inadequate for capturing improvements in discourse phenomena.
Approach:	They propose to complement accuracy-based evaluation with measures of context utilization.
Outcome:	The proposed model can be used to handle context-dependent discourse phenomena using an automatic annotation tool.

Copied to clipboard

Elena Voita, Pavel Serdyukov, Rico Sennrich, Ivan Titov

Information Extraction & Text Mining

Challenge:	Standard machine translation systems process sentences in isolation and ignore extra-sentential information.
Approach:	They propose a context-aware neural machine translation model that controls flow of information from extended context to the translation model.
Outcome:	The proposed model improves on an English-Russian subtitles dataset over its context-agnostic version (+0.7) and over simple concatenation of context and source sentences (+0.6).

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

Copied to clipboard

Poorya Zaremoodi, Gholamreza Haffari

Cross-Attention is All You Need: Adapting Pretrained Transformers for Machine Translation (2021.emnlp-main)

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

Mozhdeh Gheini, Xiang Ren, Jonathan May

A Reinforcement Learning Approach to Improve Low-Resource Machine Translation Leveraging Domain Monolingual Data (2024.lrec-main)

Challenge:	a series of experiments show that fine-tuning only the cross-attention parameters is nearly as effective as fine-timing all parameters.
Approach:	They conduct experiments to fine-tune a translation model on data where either the source or target language has changed.
Outcome:	The proposed model can be trained to several new languages with reduced parameter storage overhead.

Copied to clipboard

Hongxiao Zhang, Mingtong Liu, Chunyou Li, Yufeng Chen, Jinan Xu, Ming Zhou

Few-Shot Learning Translation from New Languages (2025.emnlp-main)

Challenge:	Existing methods for fine-tuning domain adaptation have overfitting problem in low-resource domains . lack of parallel data makes it difficult for model to learn domain-specific knowledge .
Approach:	They propose a Reinforcement Learning Domain Adaptation method for Neural Machine Translation that uses in-domain source monolingual data to make up for the lack of parallel data.
Outcome:	The proposed method can alleviate overfitting and reinforce the model to learn domain-specific knowledge.

Copied to clipboard

Carlos Mullov, Alexander Waibel

Semantic Text Processing

Challenge:	Recent work shows strong transfer learning capability to unseen languages in sequence-to-sequence neural networks . current transfer learning methods require much less downstream task data than would otherwise be required.
Approach:	They first train word embeddings models on varying amounts of data and plug them into a machine translation model.
Outcome:	The proposed model can learn Flores with only 500 parallel sentences and 31,250 sentences of monolingual data, and it can exceed 15 BLEU on unseen languages.

Learning Adaptive Segmentation Policy for Simultaneous Translation (2020.emnlp-main)

Copied to clipboard

Ruiqing Zhang, Chuanqiang Zhang, Zhongjun He, Hua Wu, Haifeng Wang

A Novel Two-step Fine-tuning Framework for Transfer Learning in Low-Resource Neural Machine Translation (2024.findings-naacl)

Challenge:	Experimental results show that adaptive segmentation policies for simultaneous translation are more accurate than current methods . if translation starts before adequate source content is delivered, the quality of translation degrades . waiting for too much source text increases latency, which would hurt accuracy .
Approach:	They propose a new adaptive segmentation policy for simultaneous translation based on human interpreters . it learns to segment the source text by considering possible translations produced by the translation model .
Outcome:	Experimental results show that the proposed method achieves better accuracy-latency trade-off over state-of-the-art methods.

Copied to clipboard

Yuan Gao, Feng Hou, Ruili Wang

Enriching Biomedical Knowledge for Low-resource Language Through Large-scale Translation (2023.eacl-main)

Challenge:	Existing transfer learning methods for neural machine translation use a well-trained translation model to initialize a child model with corresponding datasets.
Approach:	They propose a two-step fine-tuning framework for transfer learning in low-resource neural machine translation that adjusts the parent model to fit the child language by using the child source data.
Outcome:	The proposed framework improves on five low-resource translations on high-resolution languages.

Copied to clipboard

Long Phan, Tai Dang, Hieu Tran, Trieu H. Trinh, Vy Phan, Lam D. Chau, Minh-Thang Luong

Gaussian Multi-head Attention for Simultaneous Machine Translation (2022.findings-acl)

Challenge:	Biomedical data and benchmarks are highly valuable but limited in low-resource languages such as English.
Approach:	They propose a translation model in Vietnamese that trains a pretrained Encoder-Decoder Transformer model on 20 million translated abstracts.
Outcome:	The proposed model can translate and produce both pretrained and supervised biomedical data in two biomedically important domains.

Copied to clipboard

Shaolei Zhang, Yang Feng

STACL: Simultaneous Translation with Implicit Anticipation and Controllable Latency using Prefix-to-Prefix Framework (P19-1)

Challenge:	Existing methods for siMT do not explicitly model the alignment to perform the control.
Approach:	They propose to model alignment and translation in a unified manner by Gaussian Multi-head Attention (GMA) they propose to integrate alignment-related priors into the translation model to determine final attention.
Outcome:	The proposed method outperforms strong baselines on trade-off between translation and latency.

Copied to clipboard

Mingbo Ma, Liang Huang, Hao Xiong, Renjie Zheng, Kaibo Liu, Baigong Zheng, Chuanqiang Zhang, Zhongjun He, Hairong Liu, Xing Li, Hua Wu, Haifeng Wang

Adaptive Policy with Wait-k Model for Simultaneous Translation (2023.emnlp-main)

Challenge:	Simultaneous translation is notoriously dif- ficult due to word-order differences.
Approach:	They propose a prefix-to-prefix framework that implicitly learns to anticipate in a single translation model.
Outcome:	The proposed framework achieves low latency and reasonable qual- ity on 4 directions.

Copied to clipboard

Libo Zhao, Kai Fan, Wei Luo, Wu Jing, Shushu Wang, Ziqian Zeng, Zhongqiang Huang

Pruning-then-Expanding Model for Domain Adaptation of Neural Machine Translation (2021.naacl-main)

Challenge:	Existing approaches to simultaneous machine translation require a robust read/write policy . a standalone multi-path wait-k model performs competitively with adaptive policies .
Approach:	They propose a more flexible approach by decoupling the adaptive policy model from the translation model.
Outcome:	The proposed approach outperforms baseline approaches in translation tasks.

Copied to clipboard

Shuhao Gu, Yang Feng, Wanying Xie

Alleviating Distribution Shift in Synthetic Data for Machine Translation Quality Estimation (2025.acl-long)

Challenge:	Existing methods for domain adaptation suffer from catastrophic forgetting, large domain divergence, and model explosion.
Approach:	They propose a method which prunes the model and keeps the important neurons or parameters responsible for both general-domain and in-domain translation.
Outcome:	The proposed method improves on different language pairs and domains compared with strong baselines.

Copied to clipboard

Xiang Geng, Zhejian Lai, Jiajun Chen, Hao Yang, Shujian Huang

Penalizing Divergence: Multi-Parallel Translation for Low-Resource Languages of North America (2022.coling-1)

Challenge:	Quality Estimation (QE) models evaluate the quality of machine translations without reference translations, serving as the reward models for the translation task.
Approach:	They propose a framework for alleviating distribution shift in synthetic QE data . they employ a constrained beam search algorithm and distinct generation models to enhance translation diversity.
Outcome:	The proposed framework outperforms SOTA baselines like CometKiwi in supervised and unsupervised settings.

Copied to clipboard

Garrett Nicolai, Changbing Yang, Miikka Silfverberg

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

Challenge:	Existing studies show that multi-parallel translation models can overfit when training data are limited.
Approach:	They introduce a regularizer which penalizes translation models when they represent source sentences with identical target translations in divergent ways.
Outcome:	The proposed model improves when the target data for all language pairs are identical.

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.

Improving Language Model Integration for Neural Machine Translation (2023.findings-acl)

Copied to clipboard

Christian Herold, Yingbo Gao, Mohammad Zeineldeen, Hermann Ney

PAEG: Phrase-level Adversarial Example Generation for Neural Machine Translation (2022.coling-1)

Challenge:	Existing methods to integrate external language models into machine translation systems have been based on the assumption that the external model learns an implicit target-side language model at decoding time.
Approach:	They transfer this concept to the task of machine translation and compare it with the most prominent way of including additional monolingual data - namely back-translation.
Outcome:	The proposed approach outperforms the most prominent way of including additional monolingual data, namely back-translation.

Copied to clipboard

Juncheng Wan, Jian Yang, Shuming Ma, Dongdong Zhang, Weinan Zhang, Yong Yu, Zhoujun Li

Training Data Augmentation for Code-Mixed Translation (2021.naacl-main)

Challenge:	Existing methods for adversarial example generation are word-level or character-level, which ignore the ubiquitous phrase structure.
Approach:	They propose a phrase-level adversarial example generation framework to enhance the robustness of the translation model by adopting a sentence-level substitution strategy.
Outcome:	The proposed method improves translation performance and robustness to noise on three benchmarks.

Copied to clipboard

Abhirut Gupta, Aditya Vavre, Sunita Sarawagi

Accurate Online Posterior Alignments for Principled Lexically-Constrained Decoding (2022.acl-long)

Challenge:	We show a 5.8 point increase in BLEU on heavily code-mixed sentences . code-mixing is becoming more commonplace in several bilingual communities .
Approach:	They propose a method to convert existing parallel data sources into code-mixed parallel data.
Outcome:	The proposed method shows a 5.8 point increase in BLEU on heavily code-mixed sentences on a Hindi-English code-mixed translation task.

Copied to clipboard

Soumya Chatterjee, Sunita Sarawagi, Preethi Jyothi

End-to-End Simultaneous Speech Translation with Differentiable Segmentation (2023.findings-acl)

Challenge:	Existing methods of offline alignment use only the entire target sentence.
Approach:	They propose a posterior alignment technique that is truly online in its execution and superior in terms of alignment error rates compared to existing methods.
Outcome:	The proposed technique is online in execution and superior in alignment error rates compared to existing methods.

Copied to clipboard

Shaolei Zhang, Yang Feng

Speech & Audio in NLP

Challenge:	Existing methods to perform simultaneous speech translation always separate segmentation from the underlying model.
Approach:	They propose to use Differentiable Segmentation (DiSeg) to learn segmentation from the translation model.
Outcome:	Experimental results show that the proposed model can learn segmentation from the translation model.

STEMM: Self-learning with Speech-text Manifold Mixup for Speech Translation (2022.acl-long)

Copied to clipboard

Qingkai Fang, Rong Ye, Lei Li, Yang Feng, Mingxuan Wang

Multimodality

Challenge:	Existing methods to learn speech representations for end-to-end speech-totext translation (ST) neglect the representation discrepancy across modalities.
Approach:	They propose a method to calibrate the representation discrepancy between modalities by mixing up the representation sequences of different modality inputs.
Outcome:	The proposed method alleviates the cross-modal representation discrepancy and improves on a strong baseline on eight translation directions.

Dub-S2ST: Textless Speech-to-Speech Translation for Seamless Dubbing (2025.findings-emnlp)

Copied to clipboard

Jeongsoo Choi, Jaehun Kim, Joon Son Chung

A Locally Linear Procedure for Word Translation (2020.coling-main)

Challenge:	Existing speech translation approaches often overlook the transfer of speech patterns, leading to mismatches with source speech and limiting their suitability for dubbing applications.
Approach:	They propose a diffusion-based speech-to-unit translation model with explicit duration control that enables time-aligned translation.
Outcome:	The proposed system preserves key characteristics such as duration, speaker identity, and speaking speed while maintaining key characteristics.

Copied to clipboard

Soham Dan, Hagai Taitelbaum, Jacob Goldberger

Rethinking the Value of Transformer Components (2020.coling-main)

Challenge:	Existing methods to learn word embeddings of two languages are limited by the expressiveness of the translation model.
Approach:	They propose an algorithm that uses multiple orthogonal translation matrices to model the mapping and derive an algorithm to learn these multiple matric.
Outcome:	The proposed algorithm achieves better performance in bilingual and cross-lingual word translation tasks compared to the single matrix baseline.

Copied to clipboard

Wenxuan Wang, Zhaopeng Tu

Enhancing Taiwanese Hokkien Dual Translation by Exploring and Standardizing of Four Writing Systems (2024.lrec-main)

Challenge:	Empirical results show that certain components are more important than others . we propose a new training strategy that can improve Transformer models by distinguishing unimportant components .
Approach:	They propose a training strategy that distinguishes the unimportant components in training . they compare the impact of individual component (sub-layer) on model performance .
Outcome:	The proposed training strategy can improve translation performance by distinguishing unimportant components in training.

Copied to clipboard

Bo-Han Lu, Yi-Hsuan Lin, Annie Lee, Richard Tzong-Han Tsai

MAPO: Advancing Multilingual Reasoning through Multilingual-Alignment-as-Preference Optimization (2024.acl-long)

Challenge:	Currently, machine translation systems cater to high-resource languages (HRLs), while low-resourced languages (LRLs) like Taiwanese Hokkien are relatively under-explored.
Approach:	They propose to use a pre-trained LLaMA 2-7B model specialized in Traditional Mandarin Chinese to leverage orthographic similarities between Taiwanese Hokkien Han and Traditional Mandarin China.
Outcome:	The proposed model bridges the gap between Taiwanese Hokkien and other low-resource languages by using a pre-trained LLaMA 2-7B model and a monolingual corpus.

Copied to clipboard

Shuaijie She, Wei Zou, Shujian Huang, Wenhao Zhu, Xiang Liu, Xiang Geng, Jiajun Chen

Reasoning

Challenge:	Existing models exhibit inconsistent reasoning abilities across different languages . existing models lack consistency across languages due to imbalance of training data .
Approach:	They propose a multilingual alignment-as-preference optimization framework to align reasoning processes in other languages with the dominant language.
Outcome:	The proposed framework improves multilingual reasoning across languages on three benchmarks.

Normalizing Mutual Information for Robust Adaptive Training for Translation (2022.emnlp-main)

Copied to clipboard

Youngwon Lee, Changmin Lee, Hojin Lee, Seung-won Hwang

Robustness in NLP

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 .

Continual Learning with Semi-supervised Contrastive Distillation for Incremental Neural Machine Translation (2024.acl-long)

Copied to clipboard

Yunlong Liang, Fandong Meng, Jiaan Wang, Jinan Xu, Yufeng Chen, Jie Zhou

Responsible & Trustworthy NLP

Challenge:	Multi-domain learning is a good solution for solving domain tasks but it requires retraining when adding a new domain.
Approach:	They propose to exploit unlabeled data from the same distributions of the older domains to avoid catastrophic forgetting.
Outcome:	The proposed framework exploits unlabeled data from the same distributions of the older domains to avoid catastrophic forgetting.

On the Off-Target Problem of Zero-Shot Multilingual Neural Machine Translation (2023.findings-acl)

Copied to clipboard

Liang Chen, Shuming Ma, Dongdong Zhang, Furu Wei, Baobao Chang

LLaMAX: Scaling Linguistic Horizons of LLM by Enhancing Translation Capabilities Beyond 100 Languages (2024.findings-emnlp)

Challenge:	Despite its success, multilingual neural machine translation suffers from the off-target issue, where the translation is in the wrong language.
Approach:	They propose a language-aware vocabulary sharing algorithm that can be used to increase the lexical distance between languages by isolating the vocab of different languages in the decoder.
Outcome:	The proposed algorithm reduces off-target rate for 90 translation tasks from 29% to 8%, while improving overall BLEU score by an average of 1.9 points without extra training cost or sacrificing the supervised directions’ performance.

Copied to clipboard

Yinquan Lu, Wenhao Zhu, Lei Li, Yu Qiao, Fei Yuan

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

Challenge:	Large Language Models (LLMs) exhibit exceptional translation capabilities in high-resource language tasks, yet their effectiveness in low-resourced languages is suboptimal.
Approach:	They conduct extensive multilingual continual pre-training on the LLaMA series models and develop LLiMAX for translation support across more than 100 languages.
Outcome:	The proposed model achieves higher translation performance than existing open-source models and performs on-par with specialized translation model on the Flores-101 benchmark.

Copied to clipboard

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

Extrinsic Evaluation of Machine Translation Metrics (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

Nikita Moghe, Tom Sherborne, Mark Steedman, Alexandra Birch

Quality Scoring of Source Words in Neural Translation Models (2022.emnlp-main)

Challenge:	MT metrics are widely used to distinguish the quality of machine translation systems across relatively large test sets.
Approach:	They evaluate the segment-level performance of the most widely used MT metrics by correlating them with how useful they are for downstream tasks.
Outcome:	The MT metrics are widely used to distinguish the quality of machine translation systems across relatively large test sets.

Copied to clipboard

Priyesh Jain, Sunita Sarawagi, Tushar Tomar

Cross-Lingual Optimization for Language Transfer in Large Language Models (2025.acl-long)

Challenge:	Recent approaches to improving word-level quality scores on input source sentences require training special word-scoring models or require repeated invocation of the translation model.
Approach:	They propose to reason how well each word is explained by the target sentence as against the source language model and use it to translate into an unfamiliar target language.
Outcome:	The proposed method provides up to five points higher F1 scores and is significantly faster than the state of the art methods on three language pairs.

Copied to clipboard

Jungseob Lee, Seongtae Hong, Hyeonseok Moon, Heuiseok Lim

Responsible & Trustworthy NLP

Challenge:	Adapting large language models to other languages often suffers from an overemphasis on English performance.
Approach:	They propose a cross-lingual optimization technique that efficiently transfers an English-centric LLM to a target language while preserving its English capabilities.
Outcome:	The proposed model outperforms SFT in acquiring target language proficiency and maintaining English performance in low-resource languages.

JaParaPat: A Large-Scale Japanese-English Parallel Patent Application Corpus (2024.lrec-main)

Copied to clipboard

Masaaki Nagata, Makoto Morishita, Katsuki Chousa, Norihito Yasuda

Iterative Nearest Neighbour Machine Translation for Unsupervised Domain Adaptation (2023.findings-acl)

Challenge:	a recent study has demonstrated that patent translation accuracy improves as the amount of training data or the number of model parameters increases.
Approach:	They construct a bilingual corpus of Japanese-English patent application data from 2000 to 2021 . they extracted 1.4M Japanese- English document pairs and extracted 350M sentence pairs .
Outcome:	The proposed method improves translation accuracy by 20 bleu points . it is the first publicly available large-scale Japanese-English patent corpus .

Copied to clipboard

Hui Huang, Shuangzhi Wu, Xinnian Liang, Zefan Zhou, Muyun Yang, Tiejun Zhao

Low-Resource NLP

Challenge:	Existing methods for supervised domain adaptation of machine translation focus on fine-tuning, which is non-extensible.
Approach:	They propose to perform unsupervised domain adaptation in a non-parametric manner by using in-domain monolingual data and performing nearest neighbour inference on both forward and backward directions.
Outcome:	The proposed method significantly improves the in-domain translation performance and achieves state-of-the-art results among non-parametric methods.

Samayik: A Benchmark and Dataset for English-Sanskrit Translation (2024.lrec-main)

Copied to clipboard

Ayush Maheshwari, Ashim Gupta, Amrith Krishna, Atul Kumar Singh, Ganesh Ramakrishnan, Anil Kumar Gourishetty, Jitin Singla

UQA: Corpus for Urdu Question Answering (2024.lrec-main)

Challenge:	Existing Sanskrit corpora focus on poetry and offer limited coverage of contemporary written materials.
Approach:	They release a dataset of 53,000 parallel English-Sanskrit sentences . they use spoken content that covers contemporary world affairs and interpretations .
Outcome:	a new dataset of 53,000 parallel English-Sanskrit sentences is released . the dataset outperforms existing models trained on older classical-era poetry datasets .

Copied to clipboard

Samee Arif, Sualeha Farid, Awais Athar, Agha Ali Raza