DATA AUGMENTATION METHOD

Counterfactual Data Augmentation for Neural Machine Translation (2021.naacl-main)

Challenge:	Existing benchmarks fail to reflect robustness challenges and fairly evaluate models.
Approach:	They propose to ground language models to knowledge bases to investigate distribution shifts in language and linguistic aspects of distribution shift.
Outcome:	The proposed method fails to evaluate language models in large and small datasets . the proposed model fails to cope with unseen schemas and language variations .

Copied to clipboard

Qi Liu, Matt Kusner, Phil Blunsom

Sentence Concatenation Approach to Data Augmentation for Neural Machine Translation (2021.naacl-srw)

Challenge:	Neural machine translation models often rely on large-scale parallel corpora for training, exhibiting degraded performance on low-resource languages.
Approach:	They propose a method that interprets language models and phrasal alignment causally and generates augmented parallel translation corpora by sampling new source phrases from a masked language model.
Outcome:	The proposed method improves translation, backtranslation and translation robustness on IWSLT’15 English Vietnamese, WMT’17 English - German, and WMT'18 English – Turkish.

Copied to clipboard

Seiichiro Kondo, Kengo Hotate, Tosho Hirasawa, Masahiro Kaneko, Mamoru Komachi

DialAug: Mixing up Dialogue Contexts in Contrastive Learning for Robust Conversational Modeling (2022.coling-1)

Challenge:	Neural machine translation is known to show poor performance at long sentence translations . however, when the sentence length exceeds a certain value, the quality of NMT becomes inferior to that of statistical machine translation.
Approach:	They propose a method that uses given parallel corpora as train data to generate long sentences by concatenating two sentences at random.
Outcome:	The proposed method improves translation quality more when combined with back-translation.

Copied to clipboard

Lahari Poddar, Peiyao Wang, Julia Reinspach

Code-Switching for Enhancing NMT with Pre-Specified Translation (N19-1)

Challenge:	a conversational system can learn to rank response candidates for a given dialogue context by computing similarity between their vector representations.
Approach:	They propose a framework that incorporates augmented dialogue contexts into the learning objective.
Outcome:	The proposed framework outperforms existing methods and is more robust to perturbations seen during inference.

Copied to clipboard

Kai Song, Yue Zhang, Heng Yu, Weihua Luo, Kun Wang, Min Zhang

Data Augmentation for Low-Resource Dialogue Summarization (2022.findings-naacl)

Challenge:	Existing methods to constrain NMT use placeholder tags for lexicon words and hard constraints during decoding.
Approach:	They propose to use placeholder tags to replace lexicon words with target translations . they use a data augmentation method to make code-switched training data .
Outcome:	The proposed method improves translation quality without hurting unconstrained words.

Copied to clipboard

Yongtai Liu, Joshua Maynez, Gonçalo Simões, Shashi Narayan

Entity-level Factual Adaptiveness of Fine-tuning based Abstractive Summarization Models (2024.eacl-long)

Challenge:	DADS generates synthetic examples by replacing sections of text from input dialogue and summary while preserving the augmented summary to correspond to a viable summary for the simulated dialogue.
Approach:	They propose a Data Augmentation technique for low-resource Dialogue Summarization that uses pretrained language models to generate diverse alternatives.
Outcome:	The proposed method generates synthetic examples from a low-resource dataset . it produces topically diverse examples without introducing additional hallucinations .

Copied to clipboard

Jongyoon Song, Nohil Park, Bongkyu Hwang, Jaewoong Yun, Seongho Joe, Youngjune Gwon, Sungroh Yoon

A Rationale-centric Counterfactual Data Augmentation Method for Cross-Document Event Coreference Resolution (2024.naacl-long)

Challenge:	Abstractive summarization models generate factually inconsistent content when parametric knowledge conflicts with knowledge in the input document.
Approach:	They propose a method to enhance factual adaptiveness while achieving factual consistency on original datasets.
Outcome:	The proposed method improves factual adaptiveness while achieving factual consistency on original datasets.

Copied to clipboard

Bowen Ding, Qingkai Min, Shengkun Ma, Yingjie Li, Linyi Yang, Yue Zhang

RuleR: Improving LLM Controllability by Rule-based Data Recycling (2025.naacl-short)

Challenge:	Existing state-of-the-art event coreference resolution systems rely on spurious and spurious associations in the input mention pair text.
Approach:	They propose a rationale-centric counterfactual data augmentation method that leverages the debiasing capability of counterfact data haussed by LLM-in-the-loop to mitigate spurious association while emphasizing causation.
Outcome:	The proposed method achieves state-of-the-art on three popular cross-document benchmarks and demonstrates robustness in out-of domain scenarios.

Copied to clipboard

Ming Li, Han Chen, Chenguang Wang, Dang Nguyen, Dianqi Li, Tianyi Zhou

Challenge:	Existing supervised fine-tuning datasets are composed of general instructions without userspecified constraints.
Approach:	They propose a data augmentation method incorporating multiple constraints into the original data samples according to predefined rules to create new training tasks.
Outcome:	The proposed method improves LLM controllability while maintaining general instruction-following capabilities.

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

Copied to clipboard

Takuma Tanigawa, Tomoyosi Akiba, Hajime Tsukada

Text Smoothing: Enhance Various Data Augmentation Methods on Text Classification Tasks (2022.acl-short)

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

Xing Wu, Chaochen Gao, Meng Lin, Liangjun Zang, Songlin Hu

SSMBA: Self-Supervised Manifold Based Data Augmentation for Improving Out-of-Domain Robustness (2020.emnlp-main)

Challenge:	Experimental results show text smoothing outperforms data augmentation methods by a substantial margin.
Approach:	They propose to use a masked language model to convert a token to a smoothed representation by converting a sentence from its one-hot representation to 'controllable smoothes' they propose to combine text smoothing with other data augmentation methods to achieve better performance.
Outcome:	The proposed method outperforms mainstream data augmentation methods by a substantial margin on different datasets in a low-resource regime.

Copied to clipboard

Nathan Ng, Kyunghyun Cho, Marzyeh Ghassemi

Counterfactual Data Augmentation via Perspective Transition for Open-Domain Dialogues (2022.emnlp-main)

Challenge:	Data augmentation is a common method used to improve out-of-domain (OOD) generalization.
Approach:	They propose a data augmentation method that uses corruption and reconstruction functions to move randomly on a manifold to generate training examples.
Outcome:	The proposed method outperforms existing methods and baseline models on both in-domain and OOD data and achieves gains of 0.8% on OOD Amazon reviews, 1.8% accuracy on OOO MNLI, and 1.4 BLEU on in- domain IWSLT14 German-English.

Copied to clipboard

Jiao Ou, Jinchao Zhang, Yang Feng, Jie Zhou

Constructing contrastive samples via summarization for text classification with limited annotations (2021.findings-emnlp)

Challenge:	Existing methods to augment dialogue datasets are labor-intensive and time-consuming . Currently, smoking is harmful for your health.
Approach:	They propose a data augmentation method to augment dialogue responses with different semantics by counterfactual inference.
Outcome:	The proposed method outperforms baselines on multiple downstream tasks.

Copied to clipboard

Yangkai Du, Tengfei Ma, Lingfei Wu, Fangli Xu, Xuhong Zhang, Bo Long, Shouling Ji

Style Transfer as Data Augmentation: A Case Study on Named Entity Recognition (2022.emnlp-main)

Challenge:	Various contrastive learning methods have been developed and lead to state-of-the-art performance in many computer vision tasks.
Approach:	They propose a method to construct efficient contrastive samples using text summarization to gain better representations of text classification tasks with limited annotations.
Outcome:	The proposed framework gains better representations on text classification tasks with limited annotations and is compared with existing methods on real-world text classification datasets.

Copied to clipboard

Shuguang Chen, Leonardo Neves, Thamar Solorio

Named Entity Recognition

Challenge:	Existing methods to increase training data in low-resource domains may not be effective due to data scarcity.
Approach:	They propose a method to transform a high-resource domain into a low-resourced domain by changing its style-related attributes to generate synthetic data for training.
Outcome:	The proposed method can significantly improve results on five domain pairs under different data regimes.

An Augmented Benchmark Dataset for Geometric Question Answering through Dual Parallel Text Encoding (2022.coling-1)

Copied to clipboard

Jie Cao, Jing Xiao

Question Answering

Challenge:	Existing methods for solving geometric problems are limited due to lack of high-quality datasets and efficient neural solvers.
Approach:	They propose to annotate 2,518 geometric problems with richer types and greater difficulty using a benchmark dataset.
Outcome:	The proposed method improves the accuracy of automatic geometric problem solving to 66.09%.

ACROSS: An Alignment-based Framework for Low-Resource Many-to-One Cross-Lingual Summarization (2023.findings-acl)

Copied to clipboard

Peiyao Li, Zhengkun Zhang, Jun Wang, Liang Li, Adam Jatowt, Zhenglu Yang

Mitigating Exposure Bias in Grammatical Error Correction with Data Augmentation and Reweighting (2023.eacl-main)

Challenge:	Existing studies ignore data imbalance in multilingual settings and do not utilize monolingual data.
Approach:	They propose a cross-lingual summarization model that aligns cross-linguistic data with high-resource monolingual data via contrastive and consistency loss.
Outcome:	The proposed model outperforms baseline models and consistently dominates on 45 language pairs.

Copied to clipboard

Hannan Cao, Wenmian Yang, Hwee Tou Ng

Neural Fuzzy Repair: Integrating Fuzzy Matches into Neural Machine Translation (P19-1)

Challenge:	Existing approaches to grammatical error correction (GEC) use sequence-to-sequence models, but there is an exposure bias problem.
Approach:	They propose a data manipulation approach to overcome the exposure bias problem in seq2seq GEC . they propose augmentation methods to mimic decoder input and reweighting methods to automatically balance the importance of each kind of augmented samples.
Outcome:	The proposed method improves on benchmark GEC datasets.

Copied to clipboard

Bram Bulte, Arda Tezcan

Measuring and Mitigating Name Biases in Neural Machine Translation (2022.acl-long)

Challenge:	Several configurations are tested on the DGT-TM data set for the language directions English into Dutch (ENNL) and English into Hungarian (ENHU).
Approach:	They propose and test two methods for augmenting NMT training data with fuzzy TM matches by concatenation.
Outcome:	The proposed method improves on the DGT-TM data set for two language pairs and is easy to implement.

Copied to clipboard

Jun Wang, Benjamin Rubinstein, Trevor Cohn

ConvTrans: Transforming Web Search Sessions for Conversational Dense Retrieval (2022.emnlp-main)

Challenge:	Neural machine translation systems exhibit problematic biases, such as stereotypical gender bias in occupation terms.
Approach:	They propose a method to reduce biases in person name translations by randomly switching entities during translation.
Outcome:	The proposed method eliminates the problem without any effect on translation quality.

Copied to clipboard

Kelong Mao, Zhicheng Dou, Hongjin Qian, Fengran Mo, Xiaohua Cheng, Zhao Cao

Natural Language Interfaces

Challenge:	Recent studies show that conversational dense retrieval is a promising technique for realizing conversational search, but its implementation is severely hindered by the lack of data.
Approach:	They propose a method that transforms easily-accessible web search sessions into conversational search sessions to alleviate the data scarcity problem.
Outcome:	The proposed method can transform easily-accessible web search sessions into conversational search sessions.

MixText: Linguistically-Informed Interpolation of Hidden Space for Semi-Supervised Text Classification (2020.acl-main)

Copied to clipboard

Jiaao Chen, Zichao Yang, Diyi Yang

Improving Grammatical Error Correction with Data Augmentation by Editing Latent Representation (2020.coling-main)

Challenge:	Xie et al., 2016) demonstrate that semi-supervised learning models suffer from over-fitting when there is only limited labeled data.
Approach:	They propose a semi-supervised learning method for text classification using a data augmentation method called TMix.
Outcome:	The proposed method outperforms pre-trained and fine-tuned models on several text classification benchmarks.

Copied to clipboard

Zhaohong Wan, Xiaojun Wan, Wenguang Wang

Improving Spoken Language Understanding by Wisdom of Crowds (2020.coling-main)

Challenge:	Existing methods for enhancing grammatical error correction use noise to generate tokens . existing methods only generate sentences with limited error types, which leads to lack of diversity of generated errors.
Approach:	They propose a data augmentation method that can apply noise to latent representations of a sentence to generate synthetic samples with various error types.
Outcome:	The proposed method improves performance and robustness of existing models on public benchmarks and on FCE benchmarks.

Copied to clipboard

Koichiro Yoshino, Kana Ikeuchi, Katsuhito Sudoh, Satoshi Nakamura

Challenge:	Existing systems that use statistical approaches to improve spoken language understanding (SLU) lack of training data is an important problem, especially for new system tasks.
Approach:	They propose to use crowdsourcing and knowledge community websites to augment the spoken language understanding system by collecting paraphrasing variations for new system tasks and augmented them using similar questions from a knowledge community website.
Outcome:	The proposed architecture augmented more than 120,000 samples to improve accuracies even with small seed data.

Vicinal Risk Minimization for Few-Shot Cross-lingual Transfer in Abusive Language Detection (2023.emnlp-main)

Copied to clipboard

Gretel De la Peña Sarracén, Paolo Rosso, Robert Litschko, Goran Glavaš, Simone Ponzetto

Low-Resource Comparative Opinion Quintuple Extraction by Data Augmentation with Prompting (2023.findings-emnlp)

Challenge:	Existing methods for few-shot cross-lingual transfer learning are limited in target languages due to the scarcity of resources.
Approach:	They propose a method which interpolates pairs of instances based on the angle of their representations and propose augmentation methods to enhance few-shot cross-lingual abusive language detection.
Outcome:	The proposed method improves few-shot cross-lingual abusive language detection in seven languages typologically distinct from English and three different domains.

Copied to clipboard

Qingting Xu, Yu Hong, Fubang Zhao, Kaisong Song, Yangyang Kang, Jiaxiang Chen, Guodong Zhou

RoChBert: Towards Robust BERT Fine-tuning for Chinese (2022.findings-emnlp)

Challenge:	Comparative Opinion Quintuple Extraction (COQE) aims to predict comparative opinion quintuples from comparative sentences.
Approach:	They propose a low-resource approach to extract comparative opinion quintuples from comparative sentences . they propose augmentation using ChatGPT and a data-centric approach .
Outcome:	The proposed approach improves the existing pipeline-based method and achieves state-of-the-art results.

Copied to clipboard

Zihan Zhang, Jinfeng Li, Ning Shi, Bo Yuan, Xiangyu Liu, Rong Zhang, Hui Xue, Donghong Sun, Chao Zhang

Dually Self-Improved Counterfactual Data Augmentation Using Large Language Model (2025.acl-long)

Challenge:	Pre-trained language models (e.g., BERT) have been proved vulnerable to adversarial texts.
Approach:	They propose to fuse Chinese phonetic and glyph features into pre-trained models by using a more comprehensive adversarial graph.
Outcome:	The proposed framework outperforms existing methods in significant ways on a wide range of tasks while remaining accurate on benign texts.

Copied to clipboard

Luhao Zhang, Xinyu Zhang, Linmei Hu, Dandan Song, Liqiang Nie

Summarizing Patients’ Problems from Hospital Progress Notes Using Pre-trained Sequence-to-Sequence Models (2022.coling-1)

Challenge:	Existing approaches to generate counterfactual data augmentation are limited due to imbalance and biases in real-world training data.
Approach:	They propose a self-improved method for generating high-quality counterfacts using large language models.
Outcome:	The proposed method generates high-quality counterfacts on the natural language inference task using lightweight and task-specific LLMs.

Copied to clipboard

Yanjun Gao, Dmitriy Dligach, Timothy Miller, Dongfang Xu, Matthew M. M. Churpek, Majid Afshar

Enhancing Sequence-to-Sequence Neural Lemmatization with External Resources (2021.eacl-main)

Challenge:	Problem list summarization requires a model to understand, abstract, and generate clinical documentation.
Approach:	They propose a task that summarises patients' main problems from daily progress notes using input from the provider's progress notes during hospitalization.
Outcome:	The proposed model outperforms two state-of-the-art seq2seq transformer architectures in summarizing patients' main problems from daily progress notes in the medical information mart for Intensive Care (MIMIC)-III.

Copied to clipboard

Kirill Milintsevich, Kairit Sirts

Counter-GAP: Counterfactual Bias Evaluation through Gendered Ambiguous Pronouns (2023.eacl-main)

Challenge:	a hybrid approach to lemmatization enhances the seq2seq neural model with additional lemmas extracted from an external lexicon or a rule-based system.
Approach:	They propose a hybrid approach that enhances a seq2seq neural model with additional lemmas extracted from an external lexicon or a rule-based system.
Outcome:	The proposed model achieves statistically significant improvements on 23 UD languages, compared to baseline models not utilizing additional lemma information.

Copied to clipboard

Zhongbin Xie, Vid Kocijan, Thomas Lukasiewicz, Oana-Maria Camburu

Dialogue Distillation: Open-Domain Dialogue Augmentation Using Unpaired Data (2020.emnlp-main)

Challenge:	a number of studies have focused on gender bias in language models, but these methods fail to detect it.
Approach:	They propose to use gender bias in coreference resolution to evaluate gender bias . they propose to construct an annotated quadruple-level dataset with 4008 instances .
Outcome:	The proposed method is able to detect gender bias in a quadruple dataset . previous methods failed to detect bias or cancel it, the authors argue .

Copied to clipboard

Rongsheng Zhang, Yinhe Zheng, Jianzhi Shao, Xiaoxi Mao, Yadong Xi, Minlie Huang

Controllable Text Simplification with Explicit Paraphrasing (2021.naacl-main)

Challenge:	Existing research has focused on training open-domain dialogue models using unpaired data.
Approach:	They propose a data-level distillation method for training open-domain dialogue models by utilizing unpaired data.
Outcome:	The proposed method produces high-quality dialogue pairs with diverse contents, and can improve competitive baselines.

Copied to clipboard

Mounica Maddela, Fernando Alva-Manchego, Wei Xu

CLFFRD: Curriculum Learning and Fine-grained Fusion for Multimodal Rumor Detection (2024.lrec-main)

Challenge:	Existing text simplification systems rely on deletion and do not paraphrase well.
Approach:	They propose a hybrid approach that leverages linguistically-motivated rules for splitting and deletion and couples them with a neural paraphrasing model to produce varied rewriting styles.
Outcome:	The proposed model improves paraphrasing capability and paraphrases more often than existing models.

Copied to clipboard

Fan Xu, Lei Zeng, Bowei Zou, Ai Ti Aw, Huan Rong

Multimodality

Challenge:	Existing multimodal rumor detection models overlook sample difficulty and order when training . Existing models overlook text-level difficulty, image-level and multimodal difficulty when training samples .
Approach:	They propose a curriculum learning framework that uses fine-grained fusion to detect rumors . they propose fusion-based methods that combine text and images to enhance semantic cohesion .
Outcome:	The proposed framework outperforms state-of-the-art models on English and Chinese benchmark datasets.

Controllable Dialogue Simulation with In-context Learning (2022.findings-emnlp)

Copied to clipboard

Zekun Li, Wenhu Chen, Shiyang Li, Hong Wang, Jing Qian, Xifeng Yan

Data Augmentation via Subtree Swapping for Dependency Parsing of Low-Resource Languages (2020.coling-main)

Challenge:	Existing methods to generate annotated dialogues require crowdsourcing, which is expensive and time-consuming.
Approach:	They propose a dialogue simulation method based on large language model in-context learning that generates new dialogues and annotations in a controllable way.
Outcome:	The proposed method can expand a small set of dialogue data with minimum or zero human involvement and parameter update.

Copied to clipboard

Mathieu Dehouck, Carlos Gómez-Rodríguez

ESimCSE: Enhanced Sample Building Method for Contrastive Learning of Unsupervised Sentence Embedding (2022.coling-1)

Challenge:	Lack of annotated training data is a big issue for building reliable NLP systems for most of the world’s languages.
Approach:	They propose a method to swap subtrees between annotated sentences while enforcing strong constraints on those trees to ensure maximum grammaticality of the new sentences.
Outcome:	The proposed method outperforms previous methods using the same inputs and using low-resource languages.

Copied to clipboard

Xing Wu, Chaochen Gao, Liangjun Zang, Jizhong Han, Zhongyuan Wang, Songlin Hu

Data Augmentation with Atomic Templates for Spoken Language Understanding (D19-1)

Challenge:	a new method for learning unsupervised sentence embeddings is proposed . unsup-SimCSE is biased because of the length information encoded into the sentence embeds .
Approach:	They propose a new unsupervised sentence embedding method that uses dropout to obtain positive pairs from a pre-trained Transformer encoder.
Outcome:	The proposed method outperforms the state-of-the-art unsup-SimCSE on a STS task.

Copied to clipboard

Zijian Zhao, Su Zhu, Kai Yu

Self-training Improves Pre-training for Natural Language Understanding (2021.naacl-main)

Challenge:	Existing methods to enlarge SLU data require large amounts of labelled data.
Approach:	They propose a data augmentation method with atomic templates for Spoken Language Understanding which generates atomic exemplars from atomic template.
Outcome:	The proposed method improves on a DSTC 2&3 dataset which is a domain adaptation setting of SLU.

Copied to clipboard

Jingfei Du, Edouard Grave, Beliz Gunel, Vishrav Chaudhary, Onur Celebi, Michael Auli, Veselin Stoyanov, Alexis Conneau

Do It Once: An Embarrassingly Simple Joint Matching Approach to Response Selection (2021.findings-acl)

Challenge:	Unsupervised pretraining has led to improvements in natural language understanding . a data augmentation method can be used to generate labels for unlabeled examples .
Approach:	They propose a semi-supervised method which uses unlabeled data to retrieve sentences from a database of billions of unlabed sentences crawled from the web.
Outcome:	The proposed method improves on standard text classification benchmarks by 2.6% and knowledge distillation by few shots.

Copied to clipboard

Linhao Zhang, Dehong Ma, Sujian Li, Houfeng Wang

Challenge:	Existing matching models for response selection perform the independent matching (IM) approach. Existing models for matching only perform one match regardless of the number of options.
Approach:	They propose a joint matching approach which performs matching only once regardless of the number of options.
Outcome:	The proposed approach outperforms existing models and reduces training time by over half.

An Empirical Study of Contextual Data Augmentation for Japanese Zero Anaphora Resolution (2020.coling-main)

Copied to clipboard

Ryuto Konno, Yuichiroh Matsubayashi, Shun Kiyono, Hiroki Ouchi, Ryo Takahashi, Kentaro Inui

Semantically Consistent Data Augmentation for Neural Machine Translation via Conditional Masked Language Model (2022.coling-1)

Challenge:	Existing methods to augment labeled data are limited by the scarcity of labeles . a method called contextual data augmentation (CDA) can be used to augment labels .
Approach:	They propose a data augmentation method that generates labeled training instances using a pretrained language model.
Outcome:	The proposed method can improve the quality of augmented training data compared to the conventional method.

Copied to clipboard

Qiao Cheng, Jin Huang, Yitao Duan

Mustango: Toward Controllable Text-to-Music Generation (2024.naacl-long)

Challenge:	Neural network models have a large number of parameters to train, but data augmentation is relatively under-explored in natural language processing.
Approach:	They propose a bi-directional conditional Masked Language Model (CMLM) that can be conditional on both left and right contexts and the label.
Outcome:	The proposed method achieves the best performance on four translation datasets and yields up to 1.90 BLEU points over the baseline.

Copied to clipboard

Jan Melechovsky, Zixun Guo, Deepanway Ghosal, Navonil Majumder, Dorien Herremans, Soujanya Poria

Multimodality

Challenge:	Mustango is a text-to-music system that allows music-domain-knowledge-informed text-based music generation.
Approach:	They propose a music-domain-knowledge-inspired text-to-music system based on diffusion that generates music with captions that include specific instructions related to chords, beats, key and tempo.
Outcome:	The proposed system outperforms existing models in music generation tasks.

Storytelling with Dialogue: A Critical Role Dungeons and Dragons Dataset (2020.acl-main)

Copied to clipboard

Revanth Rameshkumar, Peter Bailey

Tell Me How to Ask Again: Question Data Augmentation with Controllable Rewriting in Continuous Space (2020.emnlp-main)

Challenge:	The Critical Role dataset is linguistically unique in that the narratives are generated entirely through player collaboration and spoken interaction.
Approach:	They describe the Critical Role Dungeons and Dragons Dataset and related analyses . they use a data augmentation method that produces 34,243 summary-dialogue chunk pairs .
Outcome:	The Critical Role dataset is linguistically unique in that the narratives are generated entirely through player collaboration and spoken interaction.

Copied to clipboard

Dayiheng Liu, Yeyun Gong, Jie Fu, Yu Yan, Jiusheng Chen, Jiancheng Lv, Nan Duan, Ming Zhou

Training Question Answering Models From Synthetic Data (2020.emnlp-main)

Challenge:	Existing data augmentation techniques for natural language processing tasks are difficult to design.
Approach:	They propose a controllable rewriting based question data augmentation method for machine reading comprehension, question generation and question-answering natural language inference tasks.
Outcome:	The proposed method generates high-quality, high-quality question data samples on machine reading comprehension, question generation, and question-answering natural language inference tasks.

Copied to clipboard

Raul Puri, Ryan Spring, Mohammad Shoeybi, Mostofa Patwary, Bryan Catanzaro

Natural Language Interfaces

Challenge:	Existing work on question and answer generation aims to improve question answering models given limited amount of labeled data.
Approach:	They synthesize questions and answers from a synthetic text corpus generated by an 8.3 billion parameter GPT-2 model and achieve 88.4 Exact Match (EM) and 93.9 F1 score on the SQuAD1.1 dev set.
Outcome:	The proposed model achieves higher accuracy than the SQUAD1.1 training set questions using synthetic questions and answers than the training set question.

Deterministic Reversible Data Augmentation for Neural Machine Translation (2024.findings-acl)

Copied to clipboard

Jiashu Yao, Heyan Huang, Zeming Liu, Yuhang Guo

A Lightweight Method to Generate Unanswerable Questions in English (2023.findings-emnlp)

Challenge:	Recent neural machine translation models have improved translation quality but they also introduce small perturbations like misspelling and paraphrasing.
Approach:	They propose a method that generates multi-granularity subword representations with reversible operations and deterministic segmentations.
Outcome:	The proposed method outperforms strong baselines on several translation tasks with a clear margin and exhibits good robustness in noisy, low-resource, and cross-domain datasets.

Copied to clipboard

Vagrant Gautam, Miaoran Zhang, Dietrich Klakow

EntityCS: Improving Zero-Shot Cross-lingual Transfer with Entity-Centric Code Switching (2022.findings-emnlp)

Challenge:	Existing approaches to build robust question answering models are too complex . antonym and entity swaps on answerable questions are used to build models .
Approach:	They propose a method for performing antonym and entity swaps on unanswerable questions.
Outcome:	The proposed method outperforms the previous state-of-the-art and has higher human-judged relatedness and readability.

Copied to clipboard

Chenxi Whitehouse, Fenia Christopoulou, Ignacio Iacobacci

New Datasets and Controllable Iterative Data Augmentation Method for Code-switching ASR Error Correction (2023.findings-emnlp)

Challenge:	Existing methods for CS use dictionaries or parallel sentences with word-alignment to generate CS data by randomly switching words in a sentence.
Approach:	They propose a method that focuses on Entity-level Code-Switching to capture fine-grained cross-lingual semantics without corrupting syntax.
Outcome:	The proposed method captures fine-grained cross-lingual semantics without corrupting syntax.

Copied to clipboard

Zhaohong Wan, Xiaojun Wan, Wei Peng, Rongjun Li

Multimodality

Challenge:	In bilingual or multilingual settings, code-switching ASR has greater challenges and research value.
Approach:	They propose a controllable iterative method for improving the performance of mainstream automatic speech recognition systems by using Chinese-English code-switching dialogues.
Outcome:	The proposed method achieves the best performance compared with the rule-based, back-translation-based data augmentation methods and large language model ChatGPT.

Soft Contextual Data Augmentation for Neural Machine Translation (P19-1)

Copied to clipboard

Fei Gao, Jinhua Zhu, Lijun Wu, Yingce Xia, Tao Qin, Xueqi Cheng, Wengang Zhou, Tie-Yan Liu

Does Your Model Classify Entities Reasonably? Diagnosing and Mitigating Spurious Correlations in Entity Typing (2022.emnlp-main)

Challenge:	Existing methods for enhancing training data are limited in natural language tasks due to text characteristics.
Approach:	They propose a data augmentation method that softly augments a randomly chosen word in a sentence by its contextual mixture of multiple related words.
Outcome:	The proposed method outperforms baseline methods on small and large scale machine translation datasets.

Copied to clipboard

Nan Xu, Fei Wang, Bangzheng Li, Mingtao Dong, Muhao Chen

Augmenting NLP models using Latent Feature Interpolations (2020.coling-main)

Challenge:	Existing entity typing models are subject to spurious correlations due to shortcuts and biased training.
Approach:	They propose a method to augment existing model biases by combining spurious correlations with debiasedcounterparts to improve generalization.
Outcome:	The proposed method improves generalization of different entity typing models on the original and debiased test sets.

Copied to clipboard

Amit Jindal, Arijit Ghosh Chowdhury, Aniket Didolkar, Di Jin, Ramit Sawhney, Rajiv Ratn Shah

On the Role of Supervision in Unsupervised Constituency Parsing (2020.emnlp-main)

Challenge:	Existing data augmentation methods with a large number of parameters are prone to over-fitting and often fail to capture the underlying input distribution.
Approach:	They propose a data augmentation technique that uses embeddings and hidden layer representations to construct virtual examples.
Outcome:	The proposed method outperforms existing methods in terms of accuracy and robustness to weight pruning.

Copied to clipboard

Haoyue Shi, Karen Livescu, Kevin Gimpel

SeqMix: Augmenting Active Sequence Labeling via Sequence Mixup (2020.emnlp-main)

Challenge:	Recent work on unsupervised constituency parsing uses labeled examples for tuning . a few-shot parser with labeles can outperform other approaches by a significant margin .
Approach:	They propose to use as few labeled examples as possible for model development . they propose to train existing models on the same labeles they access .
Outcome:	The proposed model outperforms other models on the WSJ development set by a significant margin . the proposed model can be further improved by augmentation and self-training .

Copied to clipboard

Rongzhi Zhang, Yue Yu, Chao Zhang

Data Augmentation for Cross-domain Parsing via Lightweight LLM Generation and Tree Hybridization (2025.coling-main)

Challenge:	Existing active sequence labeling methods use the queried samples alone in each iteration, which is inefficient for leveraging human annotations.
Approach:	They propose a data augmentation method to augment queried samples by generating extra labeled sequences in each iteration.
Outcome:	The proposed method improves the standard active sequence labeling method by 2.27%–3.75% in terms of F1 scores.

Copied to clipboard

Ziyan Zhang, Yang Hou, Chen Gong, Zhenghua Li

PreQuEL: Quality Estimation of Machine Translation Outputs in Advance (2022.emnlp-main)

Challenge:	Existing approaches for constituency parsing are expensive and lack high-quality labeled data.
Approach:	They propose a data augmentation method via lightweight large language model (LLM) generation and tree hybridization to generate a large number of structurally diverse instances.
Outcome:	The proposed method achieves significant improvements on five target domains with a lightweight LLM generation cost.

Copied to clipboard

Shachar Don-Yehiya, Leshem Choshen, Omri Abend

Generate then Refine: Data Augmentation for Zero-shot Intent Detection (2024.findings-emnlp)

Challenge:	A PreQuEL system predicts how well a given sentence will be translated without recourse to the actual translation.
Approach:	They propose a task that uses a model to predict how well a given sentence will be translated . they show that the model is sensitive to syntactic and semantic distinctions .
Outcome:	The proposed model improves on the Quality-Estimation task and on challenge sets and languages.

Copied to clipboard

I-Fan Lin, Faegheh Hasibi, Suzan Verberne

Paraphrasing as Zero-shot Translation with Feature-guided Diversity Enhancement (2026.acl-long)

Challenge:	Existing data augmentation methods rely on few labelled examples for each intent category, which can be expensive in settings with many possible intents.
Approach:	They propose a data augmentation method for intent detection in zero-resource domains by using an open-source large language model and a smaller sequence-to-sequence model.
Outcome:	The proposed method significantly improves the data utility and diversity over the zero-shot LLM baseline for unseen domains and over common baseline approaches.

Copied to clipboard

Ziyue Yan, Hongying Zan, Xinglin Lyu, Hongfei Xu

Prompt Tuning Pushes Farther, Contrastive Learning Pulls Closer: A Two-Stage Approach to Mitigate Social Biases (2023.acl-long)

Challenge:	Existing studies use parallel corpora for training, which results in less diverse paraphrases.
Approach:	They train a bidirectional multilingual neural machine translation model on a bilingual parallel corpus and use it as a paraphrasing model.
Outcome:	The proposed method generates paraphrases with higher semantic consistency, literal fluency and sentential diversity than existing parabanks and LLMs.

Copied to clipboard

Yingji Li, Mengnan Du, Xin Wang, Ying Wang

Code Needs Comments: Enhancing Code LLMs with Comment Augmentation (2024.findings-acl)

Challenge:	Existing debiasing techniques use Counterfactual Data Augmentation (CDA) to balance the training corpus, but this technique slightly modifies the original corpus limiting the representation distance between different demographic groups.
Approach:	They propose a two-stage debiasing model using Contrastive learning with Continuous Prompt Augmentation to mitigate social biases in PLMs’ encoding.
Outcome:	The proposed model outperforms baselines in terms of debiasing performance while maintaining the language modeling capability of PLMs.

Copied to clipboard

Demin Song, Honglin Guo, Yunhua Zhou, Shuhao Xing, Yudong Wang, Zifan Song, Wenwei Zhang, Qipeng Guo, Hang Yan, Xipeng Qiu, Dahua Lin

Programming Languages in NLP

Challenge:	Large Language Models (LLMs) require a deep understanding of programming languages and their correlation with natural languages (NLs).
Approach:	They propose a data augmentation method that generates comments for existing code and a filtering strategy that filters out code data poorly correlated with natural language.
Outcome:	The proposed method outperforms the model trained on the augmented data and the model further trained on data without augmentation on two widely-used programming skill benchmarks.

StyleFlow: Disentangle Latent Representations via Normalizing Flow for Unsupervised Text Style Transfer (2024.lrec-main)

Copied to clipboard

Kangchen Zhu, Zhiliang Tian, Jingyu Wei, Ruifeng Luo, Yiping Song, Xiaoguang Mao

Context-Driven and Reference-Guided Data Augmentation for Subtitle Translation (2026.findings-acl)

Challenge:	Existing methods to separate content from style but some words contain both content and style information.
Approach:	They propose a method which uses a reversible encoder to improve content disentanglement.
Outcome:	The proposed method outperforms baselines on sentiment transfer and formality transfer tasks.

Copied to clipboard

Hitoshi Ito, Naoto Shirai, Kazutaka Kinugawa, Hideya Mino, Rei Endo, Yoshihiko Kawai