Paraphrase Generation

66 papers with code • 3 benchmarks • 16 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.

Paraphrase Types for Generation and Detection

jpwahle/emnlp23-paraphrase-types 23 Oct 2023

Current approaches in paraphrase generation and detection heavily rely on a single general similarity score, ignoring the intricate linguistic properties of language.

7
23 Oct 2023

A Quality-based Syntactic Template Retriever for Syntactically-controlled Paraphrase Generation

xzhang00/qstr 20 Oct 2023

Furthermore, for situations requiring multiple paraphrases for each source sentence, we design a Diverse Templates Search (DTS) algorithm, which can enhance the diversity between paraphrases without sacrificing quality.

2
20 Oct 2023

Multilingual Lexical Simplification via Paraphrase Generation

kpkqwq/lspg 28 Jul 2023

After feeding the input sentence into the encoder of paraphrase modeling, we generate the substitutes based on a novel decoding strategy that concentrates solely on the lexical variations of the complex word.

4
28 Jul 2023

Explicit Syntactic Guidance for Neural Text Generation

yafuly/syntacticgen 20 Jun 2023

Most existing text generation models follow the sequence-to-sequence paradigm.

14
20 Jun 2023

ParaAMR: A Large-Scale Syntactically Diverse Paraphrase Dataset by AMR Back-Translation

uclanlp/paraamr 26 May 2023

Paraphrase generation is a long-standing task in natural language processing (NLP).

1
26 May 2023

PIP: Parse-Instructed Prefix for Syntactically Controlled Paraphrase Generation

uclanlp/pip 26 May 2023

Existing fine-tuning methods for this task are costly as all the parameters of the model need to be updated during the training process.

0
26 May 2023

ChatGPT to Replace Crowdsourcing of Paraphrases for Intent Classification: Higher Diversity and Comparable Model Robustness

kinit-sk/crowd-vs-gpt-intent-class 22 May 2023

The emergence of generative large language models (LLMs) raises the question: what will be its impact on crowdsourcing?

3
22 May 2023

CoEdIT: Text Editing by Task-Specific Instruction Tuning

vipulraheja/coedit 17 May 2023

We present a large language model fine-tuned on a diverse collection of task-specific instructions for text editing (a total of 82K instructions).

85
17 May 2023

TESS: Text-to-Text Self-Conditioned Simplex Diffusion

allenai/tess-diffusion 15 May 2023

Diffusion models have emerged as a powerful paradigm for generation, obtaining strong performance in various continuous domains.

10
15 May 2023

Lost in Translationese? Reducing Translation Effect Using Abstract Meaning Representation

shirawein/amr-translationese 23 Apr 2023

Though individual translated texts are often fluent and preserve meaning, at a large scale, translated texts have statistical tendencies which distinguish them from text originally written in the language ("translationese") and can affect model performance.

0
23 Apr 2023