Paraphrase Identification

72 papers with code • 10 benchmarks • 17 datasets

The goal of Paraphrase Identification is to determine whether a pair of sentences have the same meaning.

Source: Adversarial Examples with Difficult Common Words for Paraphrase Identification

Image source: On Paraphrase Identification Corpora

Libraries

Use these libraries to find Paraphrase Identification models and implementations

Latest papers with no code

Is Modularity Transferable? A Case Study through the Lens of Knowledge Distillation

no code yet • 27 Mar 2024

Moreover, we propose a method that allows the transfer of modules between incompatible PLMs without any change in the inference complexity.

SMoA: Sparse Mixture of Adapters to Mitigate Multiple Dataset Biases

no code yet • 28 Feb 2023

Recent studies reveal that various biases exist in different NLP tasks, and over-reliance on biases results in models' poor generalization ability and low adversarial robustness.

Paraphrase Identification with Deep Learning: A Review of Datasets and Methods

no code yet • 13 Dec 2022

The rapid advancement of AI technology has made text generation tools like GPT-3 and ChatGPT increasingly accessible, scalable, and effective.

Towards Structure-aware Paraphrase Identification with Phrase Alignment Using Sentence Encoders

no code yet • COLING 2022

Therefore, we here propose to combine sentence encoders with an alignment component by representing each sentence as a list of predicate-argument spans (where their span representations are derived from sentence encoders), and decomposing the sentence-level meaning comparison into the alignment between their spans for paraphrase identification tasks.

Improving Large-scale Paraphrase Acquisition and Generation

no code yet • 6 Oct 2022

This paper addresses the quality issues in existing Twitter-based paraphrase datasets, and discusses the necessity of using two separate definitions of paraphrase for identification and generation tasks.

Paraphrasing, textual entailment, and semantic similarity above word level

no code yet • 10 Aug 2022

This dissertation explores the linguistic and computational aspects of the meaning relations that can hold between two or more complex linguistic expressions (phrases, clauses, sentences, paragraphs).

PerPaDa: A Persian Paraphrase Dataset based on Implicit Crowdsourcing Data Collection

no code yet • LREC 2022

In this paper we introduce PerPaDa, a Persian paraphrase dataset that is collected from users' input in a plagiarism detection system.

Balanced Adversarial Training: Balancing Tradeoffs Between Oversensitivity and Undersensitivity in NLP Models

no code yet • ACL ARR January 2022

Traditional (\emph{oversensitive}) adversarial examples involve finding a small perturbation that does not change an input's true label but confuses the classifier into outputting a different prediction.

Explaining Predictive Uncertainty by Looking Back at Model Explanations

no code yet • 11 Jan 2022

Explaining predictive uncertainty is an important complement to explaining prediction labels in helping users understand model decision making and gaining their trust on model predictions, while has been largely ignored in prior works.

BnPC: A Corpus for Paraphrase Detection in Bangla

no code yet • ACL ARR December 2022

In this paper, we present the first benchmark dataset for paraphrase detection in Bangla language.