Automatically Paraphrasing via Sentence Reconstruction and  Round-trip Translation

Guo, Zilu; Huang, Zhongqiang; Zhu, Kenny Q.; Chen, Guandan; Zhang, Kaibo; Chen, Boxing; Huang, Fei

doi:10.24963/ijcai.2021/525

Cited by 7 publications

(8 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Unsupervised paraphrase generation methods often employ translation or denoising. and Guo et al (2021) employ a straightforward round-trip translation approach. Guo et al (2021) propose a hybrid decoder taking the hidden states of a set-to-sequence model (Vinyals et al, 2016) and a round-trip translation model.…”

Section: Related Workmentioning

confidence: 99%

“…and Guo et al (2021) employ a straightforward round-trip translation approach. Guo et al (2021) propose a hybrid decoder taking the hidden states of a set-to-sequence model (Vinyals et al, 2016) and a round-trip translation model. Hu et al (2019a) and Hu et al (2019b) expand translation datasets into paraphrase datasets with lexically constrained decoding (Hokamp and Liu, 2017;Post and Vilar, 2018).…”

Section: Related Workmentioning

confidence: 99%

“…The QQP dataset comprises over 400k lines of potential question duplicate pairs. We adopt the unsupervised setting as Guo et al (2021). For WikiAnswers, we randomly select 500k non-parallel sentences, 3k parallel paraphrases, and 20k parallel paraphrases for training, validation, and testing.…”

Section: Datasetsmentioning

confidence: 99%

“…Existing unsupervised paraphrase generation methods primarily employ round-trip translation Wieting and Gimpel, 2018;Guo et al, 2021) or denoising (Hegde and Patil, 2020;Guo et al, 2021;Niu et al, 2021), which leads to four flaws. Firstly, round-trip translation requires extra translation corpus.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Unifying Discrete and Continuous Representations for Unsupervised Paraphrase Generation

Xue,

Liu,

Lei

et al. 2023

Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing

View full text Add to dashboard Cite

Unsupervised paraphrase generation is a challenging task that benefits a variety of downstream NLP applications. Current unsupervised methods for paraphrase generation typically employ round-trip translation or denoising, which require translation corpus and result in paraphrases overly similar to the original sentences in surface structure. Most of these methods lack explicit control over the similarity between the original and generated sentences, and the entities are also less correctly kept. To obviate the reliance on translation data and prompt greater variations in surface structure, we propose a self-supervised pseudo-data construction method that generates diverse pseudo-paraphrases in distinct surface structures for a given sentence. To control the similarity and generate accurate entities, we propose an unsupervised paraphrasing model that encodes the sentence meaning and the entities with discrete and continuous variables, respectively. The similarity can be controlled by sampling discrete variables and the entities are kept substantially accurate due to the specific modeling of entities using continuous variables. Experimental results on two benchmark datasets demonstrate the advantages of our pseudo-data construction method compared to round-trip translation, and the superiority of our paraphrasing model over the state-of-the-art unsupervised methods.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Datasetsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Unifying Discrete and Continuous Representations for Unsupervised Paraphrase Generation

Xue,

Liu,

Lei

et al. 2023

Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing

View full text Add to dashboard Cite

show abstract

“…A special form of translation is round trip translation, which focuses on translating a given text from one language to the second and back to the first. Round trip translation has been increasingly used in several research areas, including correcting grammatical errors (Lichtarge et al, 2019;Madnani et al, 2012), evaluating machine translation models (Crone et al, 2021;Cao et al, 2020;Moon et al, 2020), paraphrasing (Guo et al, 2021) and rewriting questions (Chu et al, 2020). It is also used extensively as part of the quality assurance process in critical domains such as medical, legal and market search domains.…”

Section: Introductionmentioning

confidence: 99%

Lost In Translation: Generating Adversarial Examples Robust to Round-Trip Translation

Bhandari

Chen²

2023

ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

Language Models today provide a high accuracy across a large number of downstream tasks. However, they remain susceptible to adversarial attacks, particularly against those where the adversarial examples maintain considerable similarity to the original text. Given the multilingual nature of text, the effectiveness of adversarial examples across translations and how machine translations can improve the robustness of adversarial examples remain largely unexplored. In this paper, we present a comprehensive study on the robustness of current text adversarial attacks to round-trip translation. We demonstrate that 6 state-of-the-art text-based adversarial attacks do not maintain their efficacy after round-trip translation. Furthermore, we introduce an intervention-based solution 1 to this problem, by integrating Machine Translation into the process of adversarial example generation and demonstrating increased robustness to round-trip translation. Our results indicate that finding adversarial examples robust to translation can help identify the insufficiency of language models that is common across languages, and motivate further research into multilingual adversarial attacks.

show abstract

Diverse Paraphrasing with Insertion Models for Few-Shot Intent Detection

Chevasson¹,

Laclau²,

Gravier³

2023

Lecture Notes in Computer Science

View full text Add to dashboard Cite

In contrast to classic autoregressive generation, insertionbased models can predict in a order-free way multiple tokens at a time, which make their generation uniquely controllable: it can be constrained to strictly include an ordered list of tokens. We propose to exploit this feature in a new diverse paraphrasing framework: first, we extract important tokens or keywords in the source sentence; second, we augment them; third, we generate new samples around them by using insertion models. We show that the generated paraphrases are competitive with state of the art autoregressive paraphrasers, not only in diversity but also in quality. We further investigate their potential to create new pseudolabelled samples for data augmentation, using a meta-learning classification framework, and find equally competitive result. In addition to proving non-autoregressive (NAR) viability for paraphrasing, we contribute our open-source framework as a starting point for further research into controllable NAR generation.

show abstract

Automatically Paraphrasing via Sentence Reconstruction and Round-trip Translation

Cited by 7 publications

References 5 publications

Unifying Discrete and Continuous Representations for Unsupervised Paraphrase Generation

Unifying Discrete and Continuous Representations for Unsupervised Paraphrase Generation

Lost In Translation: Generating Adversarial Examples Robust to Round-Trip Translation

Diverse Paraphrasing with Insertion Models for Few-Shot Intent Detection

Contact Info

Product

Resources

About