Papers with back translation
Improving Classification of Infrequent Cognitive Distortions: Domain-Specific Model vs. Data Augmentation (2022.naacl-srw)
Copied to clipboard
| Challenge: | Cognitive distortions are one of the targets of cognitive behavioral therapy (CBT). |
| Approach: | They propose to use Easy Data Augmentation, back translation, and mixup techniques to detect distortions in text-based therapy messages. |
| Outcome: | The proposed methods improve performance with optimized parameter settings for rare classes with an augmented model, MentalBERT. |
LM-CPPF: Paraphrasing-Guided Data Augmentation for Contrastive Prompt-Based Few-Shot Fine-Tuning (2023.acl-short)
Copied to clipboard
| Challenge: | Recent advances in pre-trained language models have been limited when fine-tuned on small datasets. |
| Approach: | They propose to add contrastive learning to prompt-based fine-tuning to improve model performance. |
| Outcome: | The proposed approach outperforms other methods on multiple text classification benchmarks. |
Boosting Text Augmentation via Hybrid Instance Filtering Framework (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing text augmentation methods generate instances with shifted feature spaces, which leads to a drop in performance on large datasets. |
| Approach: | They propose a hybrid instance-filtering framework that generates instances with shifted feature spaces, which leads to a drop in performance on augmented data. |
| Outcome: | The proposed framework outperforms state-of-the-art methods on three classification tasks and nine public datasets. |
PAWS: Paraphrase Adversaries from Word Scrambling (N19-1)
Copied to clipboard
| Challenge: | Existing paraphrase identification datasets lack sentence pairs with high word overlap without being paraphrases. |
| Approach: | They propose a workflow for generating pairs of sentences with high word overlap . they use controlled word swapping and back translation followed by fluency and paraphrase judgments . |
| Outcome: | The proposed dataset has 108,463 well-formed paraphrase and non-paraphrase pairs with high lexical overlap. |
Unsupervised Domain Adaptation for Neural Machine Translation with Domain-Aware Feature Embeddings (D19-1)
Copied to clipboard
| Challenge: | Recent studies have focused on domain adaptation for neural machine translation systems where in-domain data is scarce or nonexistent. |
| Approach: | They propose an approach that adapts models with domain-aware feature embeddings, which are learned via an auxiliary language modeling task. |
| Outcome: | The proposed model performs better in multiple experimental settings and with back translation. |
Knowing More About Questions Can Help: Improving Calibration in Question Answering (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing work on calibration focuses on model confidence, such as the max probability of the predicted class. |
| Approach: | They propose a calibration method which estimates whether model correctly predicts answer for each question. |
| Outcome: | The proposed calibration method achieves 5-10% gains on reading comprehension benchmarks. |
AMR-DA: Data Augmentation by Abstract Meaning Representation (2022.findings-acl)
Copied to clipboard
| Challenge: | Abstract Meaning Representation (AMR) is a semantic representation for NLP/NLU. |
| Approach: | They propose to use AMR-DA for data augmentation in NLP . they use sentence-level techniques like back translation and token-level methods like EDA . |
| Outcome: | The proposed method outperforms EDA and AEDA and improves on STS and text classification tasks. |
Back Translation for Speech-to-text Translation Without Transcripts (2023.acl-long)
Copied to clipboard
| Challenge: | End-to-end speech-totext translation (ST) is often achieved by utilizing source transcripts, but transcripts are only sometimes available since numerous unwritten languages exist worldwide. |
| Approach: | They propose an algorithm to synthesize pseudo ST data from monolingual target data to enhance ST without generating source transcripts. |
| Outcome: | The proposed method achieves an average boost of 2.3 BLEU on MuST-C En-De, En-Fr, and En-Es datasets. |
When and how to paraphrase for named entity recognition? (2023.acl-long)
Copied to clipboard
Saket Sharma, Aviral Joshi, Yiyun Zhao, Namrata Mukhija, Hanoz Bhathena, Prateek Singh, Sashank Santhanam
| Challenge: | Named entity recognition (NER) is a key component underpinning many industrial pipelines for a variety of downstream applications. |
| Approach: | They propose to use back translation to annotate entity spans in generations and propose a paraphraser with a larger dataset. |
| Outcome: | The proposed method improves NER performance across different datasets with gold annotations and paraphrasing strength. |
Exploiting Monolingual Data at Scale for Neural Machine Translation (D19-1)
Copied to clipboard
| Challenge: | Neural machine translation (NMT) is a well-known and expensive task. |
| Approach: | They propose a method to use target-side monolingual data for neural machine translation and propose 'synthetic bitext' they propose generating synthetic bitext by translating monolingual into the other domain using models pretrained on genuine bitext. |
| Outcome: | The proposed approach achieves state-of-the-art results on WMT16, WMT17, WTM18 EnglishGerman translations and WTM19 GermanFrench translations. |
Stylized Dialogue Generation with Feature-Guided Knowledge Augmentation (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods synthesize pseudo data through back translation but lack guidance on target style features. |
| Approach: | They propose a knowledge-augmented stylized dialogue generation model with a feature-guided style knowledge selection module that utilizes context and response features. |
| Outcome: | The proposed model produces a satisfactory performance on two public benchmarks on both semantic and stylized levels. |
BERT, mBERT, or BiBERT? A Study on Contextualized Embeddings for Neural Machine Translation (2021.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for incorporating pre-trained models into NMT systems are non-trivial and lack a comparison of the impact that other pre-trainers may have on translation performance. |
| Approach: | They propose to use the input of a bilingual pre-trained language model as the input for NMT encoders and a stochastic layer selection approach to ensure sufficient utilization of contextualized embeddings. |
| Outcome: | The proposed bilingual pre-trained language model outperforms all other pre-train models on the IWSLT’14 dataset and the proposed dual-directional translation model. |
Program Translation via Code Distillation (2023.emnlp-main)
Copied to clipboard
| Challenge: | Software version migration and program translation are costly parts of the lifecycle of large codebases. |
| Approach: | They propose a model that captures semantic and structural equivalence of code in a language agnostic intermediate representation. |
| Outcome: | The proposed model achieves state-of-the-art performance on CodeXGLUE and TransCoder GeeksForGeeks translation benchmarks. |