Home Research Papers Datasets State of the Art Pricing

Discover, visualize, and connect AI research papers. Explore the latest trends and insights in artificial intelligence research.

Product

Home
Research Papers
About

Support

Contact
Terms of Service
Privacy Policy

© 2026 Papersgraph. All rights reserved.

natural-language-processing-10

Paraphrase Generation

3260 papers • 126 benchmarks • 313 datasets

Paraphrase Generation involves transforming a natural language sentence to a new sentence, that has the same semantic meaning but a different syntactic or lexical surface form.

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in paraphrase-generation-10

Trend

Dataset

Best Model

Actions

Paralex

Paralex

Quora Question Pairs

Quora Question Pairs

MSCOCO

MSCOCO

Libraries

i

Use these libraries to find paraphrase-generation-10 models and implementations

Datasets

GLUE

Quora Question Pairs

Quora Question Pairs

Paralex

Opusparcus

ParaBank

PARANMT-50M

Subtasks

No subtasks available.

Most implemented papers

Learning Semantic Sentence Embeddings using Sequential Pair-wise Discriminator

Vinay P. Namboodiri, B. N. Patro, V. Kurmi, Sandeep Kumar•Sat Jun 02 2018

The proposed method results in semantic embeddings and outperforms the state-of-the-art on the paraphrase generation and sentiment analysis task on standard datasets and is shown to be statistically significant.

34

Content

Introduction Benchmarks Datasets Subtasks Libraries Papers

Duolingo STAPLE Shared Task

Duolingo STAPLE Shared Task

StyleKQC

Quda

0

Paraphrase Generation with Latent Bag of Words

Yansong Feng, Yao Fu, J. Cunningham•Mon Jan 06 2020

This work proposes a latent bag of words (BOW) model for paraphrase generation that ground the semantics of a discrete latent variable by the target BOW to build a fully differentiable content planning and surface realization pipeline.

102 0

Neural Syntactic Preordering for Controlled Paraphrase Generation

Greg Durrett, Tanya Goyal•Mon May 04 2020

This work uses syntactic transformations to softly “reorder” the source sentence and guide the neural paraphrasing model, which retains the quality of the baseline approaches while giving a substantial increase in the diversity of the generated paraphrases.

111 0

Syntax-Guided Controlled Generation of Paraphrases

Kabir Ahuja, P. Talukdar, Ashutosh Kumar, Raghuram Vadapalli•Sun May 17 2020

Syntax Guided Controlled Paraphraser (SGCP), an end-to-end framework for syntactic paraphrase generation, is proposed and it is found that Sgcp can generate syntax-conforming sentences while not compromising on relevance.

99 0

Neural Paraphrase Generation with Stacked Residual LSTM Networks

Sadid A. Hasan, Aaditya (Adi) Prakash, Kathy Lee, Vivek Datla, Ashequl Qadir, Joey Liu, Oladimeji Farri•Fri Sep 30 2016

This work is the first to explore deep learning models for paraphrase generation with a stacked residual LSTM network, where it adds residual connections between L STM layers for efficient training of deep LSTMs.

274 0

Building a Non-Trivial Paraphrase Corpus Using Multiple Machine Translation Systems

Mamoru Komachi, Tomoyuki Kajiwara, Yui Suzuki•Fri Jun 30 2017

This work built and released the first evaluation corpus for Japanese paraphrase identiﬁcation, which comprises 655 sentence pairs, and proposes a novel sentential paraphrase acquisition method that uses multiple machine translation systems and a monolingual corpus to extract negative candidates.

15 0

A Deep Generative Framework for Paraphrase Generation

Piyush Rai, Ankush Gupta, Arvind Agarwal, Prawaan Singh•Thu Aug 31 2017

Quantitative evaluation of the proposed method on a benchmark paraphrase dataset demonstrates its efficacy, and its performance improvement over the state-of-the-art methods by a significant margin, whereas qualitative human evaluation indicate that the generated paraphrases are well-formed, grammatically correct, and are relevant to the input sentence.

266 0

Query and Output: Generating Words by Querying Distributed Word Representations for Paraphrase Generation

Wenjie Li, Xu Sun, Wei Li, Shuming Ma, Xuancheng Ren, Sujian Li•Wed Feb 28 2018

This work introduces a novel model based on the encoder-decoder framework, called Word Embedding Attention Network (WEAN), which generates the words by querying distributed word representations (i.e. neural word embeddings), hoping to capturing the meaning of the according words.

63 0

Discriminating between Lexico-Semantic Relations with the Specialization Tensor Model

Ivan Vulic, Goran Glavas•Thu May 31 2018

The proposed model can transfer the prediction of lexico-semantic relations to a resource-lean target language without any training data and outperforms more complex state-of-the-art architectures on two benchmark datasets and exhibits stable performance across languages.

21 0

Adding a benchmark result helps the community track progress.

Paraphrase Generation | State-of-the-Art