Papers with synthetic data augmentation

7 papers
Towards building a Robust Industry-scale Question Answering System (2020.coling-industry)

Copied to clipboard

Challenge: Existing systems that use “zero-shot transfer learning” (ZSTL) are difficult to train and have observation biases.
Approach: They propose a production model called GAAMA which has two characteristics . it is robust and efficient, and trains on the recently introduced Natural Questions dataset .
Outcome: The proposed model performs on two benchmarks: BioASQ and CovidQA.
Sample, Translate, Recombine: Leveraging Audio Alignments for Data Augmentation in End-to-end Speech Translation (2022.acl-short)

Copied to clipboard

Challenge: End-to-end speech translation relies on data that pair source-language speech inputs with corresponding translations.
Approach: They propose a method that augments transcriptions by sampling from suffix memory and translating them into target languages.
Outcome: The proposed method delivers up to 0.9 and 1.1 BLEU points on top of augmentation with knowledge distillation on languages on CoVoST 2 and Europarl-ST.
TADA : Task Agnostic Dialect Adapters for English (2023.findings-acl)

Copied to clipboard

Challenge: Existing work on dialectal English NLP is task-specific, using manual annotated dialect data, weak supervision, or data augmentation.
Approach: They propose a method for task-agnostic dialect adaptation by aligning non-SAE dialects with task-specific adapters from SAE.
Outcome: The proposed method improves dialectal robustness on 4 dialectal variants of the GLUE benchmark without task-specific supervision.
Towards Robust Neural Retrieval with Source Domain Synthetic Pre-Finetuning (2022.coling-1)

Copied to clipboard

Challenge: Existing neural IR systems rely on lexical matching for query-passage alignment, while masked language models use a dual encoder architecture to encode passages and questions into continuous vector representations.
Approach: They propose to enhance the out-of-domain generalization of Dense Passage Retrieval (DPR) through synthetic data augmentation only in the source domain.
Outcome: The proposed model outperforms existing models in in-domain and zero-shot evaluations on Wikipedia-based datasets.
Visual Program Distillation with Template-Based Augmentation (2025.findings-emnlp)

Copied to clipboard

Challenge: Adapting visual programming to specialized tasks or domains remains challenging due to high annotation and inference costs.
Approach: They propose a low-cost visual program distillation method that can be used for models with at most 1 billion parameters and requires no human-generated program annotations.
Outcome: The proposed method can generate high-quality visual programs with no human-generated annotations with a relatively small amount of question/answer data.
FiE: Building a Global Probability Space by Leveraging Early Fusion in Encoder for Open-Domain Question Answering (2022.emnlp-main)

Copied to clipboard

Challenge: generative models tend to be larger than extractive models due to the need for a decoder, run slower during inference due to auto-regressive decoded beam search, and their generated output suffers from hallucinations.
Approach: They propose to extend transformer encoders with the ability to fuse information from multiple passages to provide cross-sample attention over all tokens across samples.
Outcome: The proposed method outperforms the current state-of-the-art method by 2.5 Exact Match score on the Natural Question dataset while using only 25% of parameters and 35% of the latency during inference.
Building A Proof-Oriented Programmer That Is 64% Better Than GPT-4o Under Data Scarcity (2025.findings-acl)

Copied to clipboard

Challenge: Existing proof-oriented programming languages struggle due to data scarcity . existing proof-based models struggle due a lack of sufficient corpora for proof-orientated programming languages such as F* .
Approach: They propose a method that synthesizes proof-oriented programming problems for proficiency in a language and incorporates diverse coding data for reasoning capability elicitation.
Outcome: The proposed method outperforms existing proof-oriented models in function- and repository-level proof-based programming by 64% relative margin and improves GPT-4o's performance by 54% by repairing outputs over GPT-4)

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations