Paraphrase Generation Based on VAE and Pointer-Generator Networks

Ravuru, Lohith; Choi, Hyungtak; Siddarth, K M; Lee, Hojung; Hwang, Inseok

doi:10.1109/asru46091.2019.9003874

Cited by 3 publications

(2 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our tagging technique aims to achieve a good paraphrase generation performance with a low-cost finetuning task that utilizes already published pretrained models. As compare to other Pointer Generator Network approaches like (Ravuru et al, 2019), our approach is cheaper and more flexible given pre-trained weights. Furthermore, easy modifications can be made based on our source code to make TAGPA work with other (future) pretrained encoder-decoder architectures.…”

Section: Why Mbart?mentioning

confidence: 99%

Don't Change Me! User-Controllable Selective Paraphrase Generation

Zhang¹,

Tan²,

Tu³

et al. 2020

Preprint

View full text Add to dashboard Cite

In this article, we propose a paraphrase generation technique to keep the key phrases in source sentences during paraphrasing. We also develop a model called TAGPA with such technique, which has multiple pre-configured or trainable key phrase detector and a paraphrase generator. The paraphrase generator aims to keep the key phrases and increase the diversity of the paraphrased sentences. The key phrases can be entities provided by our user, like company names, people's names, domain-specific terminologies, etc., or can be learned from a given dataset.

show abstract

Section: Why Mbart?mentioning

confidence: 99%

Don't Change Me! User-Controllable Selective Paraphrase Generation

Zhang¹,

Tan²,

Tu³

et al. 2020

Preprint

View full text Add to dashboard Cite

show abstract

“…PGN and a new loss function are also introduced to address these issues. Ravuru et al proposed combining VAE [12] and the PGN [8] and applying them to the task of paraphrasing [16]. Zhang et al combined the Transformer architecture with the PGN [17].…”

Section: B Pointer Generator Network (Pgn)mentioning

confidence: 99%

Paraphrase Generation Model Integrating Transformer Architecture, Part-of-Speech Features, and Pointer Generator Network

Tsai

Lin

2023

IEEE Access

View full text Add to dashboard Cite

In recent years, hardware advancements have enabled natural language processing tasks that were previously difficult to achieve due to their intense computing requirements. This study focuses on paraphrase generation, which entails rewriting a sentence using different words and sentence structures while preserving its original meaning. This increases sentence diversity, thereby improving the performance of downstream tasks, such as question-answering systems and machine translation. This study proposes a novel paraphrase generation model that combines the Transformer architecture with part-of-speech features, and this model is trained using a Chinese corpus. New features are incorporated to improve the performance of the Transformer architecture, and the pointer generation network is used when the training data contain lowfrequency words. This allows the model to focus on input words with important information according to their attention distributions.

show abstract