About

Benchmarks

TREND DATASET BEST METHOD PAPER TITLE PAPER CODE COMPARE

Datasets

Greatest papers with code

Paraphrase Generation with Latent Bag of Words

NeurIPS 2019 FranxYao/Deep-Generative-Models-for-Natural-Language-Processing

Inspired by variational autoencoders with discrete latent structures, in this work, we propose a latent bag of words (BOW) model for paraphrase generation.

PARAPHRASE GENERATION WORD EMBEDDINGS

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

NAACL 2018 lancopku/WEAN

The existing sequence-to-sequence model tends to memorize the words and the patterns in the training dataset instead of learning the meaning of the words.

ABSTRACTIVE TEXT SUMMARIZATION PARAPHRASE GENERATION TEXT SIMPLIFICATION WORD EMBEDDINGS

Reformulating Unsupervised Style Transfer as Paraphrase Generation

EMNLP 2020 martiansideofthemoon/style-transfer-paraphrase

Modern NLP defines the task of style transfer as modifying the style of a given sentence without appreciably changing its semantics, which implies that the outputs of style transfer systems should be paraphrases of their inputs.

PARAPHRASE GENERATION STYLE TRANSFER

Neural Syntactic Preordering for Controlled Paraphrase Generation

ACL 2020 tagoyal/sow-reap-paraphrasing

Paraphrasing natural language sentences is a multifaceted process: it might involve replacing individual words or short phrases, local rearrangement of content, or high-level restructuring like topicalization or passivization.

MACHINE TRANSLATION PARAPHRASE GENERATION

Learning Semantic Sentence Embeddings using Sequential Pair-wise Discriminator

COLING 2018 badripatro/PQG

One way to ensure this is by adding constraints for true paraphrase embeddings to be close and unrelated paraphrase candidate sentence embeddings to be far.

MACHINE READING COMPREHENSION MACHINE TRANSLATION PARAPHRASE GENERATION SENTENCE EMBEDDING SENTIMENT ANALYSIS

Syntax-guided Controlled Generation of Paraphrases

TACL 2020 malllabiisc/SGCP

In these methods, syntactic-guidance is sourced from a separate exemplar sentence.

PARAPHRASE GENERATION

Latent Template Induction with Gumbel-CRFs

NeurIPS 2020 FranxYao/Gumbel-CRF

Learning to control the structure of sentences is a challenging problem in text generation.

DATA-TO-TEXT GENERATION PARAPHRASE GENERATION

Learning Semantic Sentence Embeddings using Sequential Pair-wise Discriminator

COLING 2018 dev-chauhan/PQG-pytorch

One way to ensure this is by adding constraints for true paraphrase embeddings to be close and unrelated paraphrase candidate sentence embeddings to be far.

PARAPHRASE GENERATION SENTENCE EMBEDDING SENTIMENT ANALYSIS

Paraphrase Generation as Zero-Shot Multilingual Translation: Disentangling Semantic Similarity from Lexical and Syntactic Diversity

11 Aug 2020thompsonb/prism

Recent work has shown that a multilingual neural machine translation (NMT) model can be used to judge how well a sentence paraphrases another sentence in the same language (Thompson and Post, 2020); however, attempting to generate paraphrases from such a model using standard beam search produces trivial copies or near copies.

MACHINE TRANSLATION PARAPHRASE GENERATION SEMANTIC SIMILARITY SEMANTIC TEXTUAL SIMILARITY