Paraphrase Generation: A Survey of the State of the Art

Zhou, Jianhui; Bhat, Suma

doi:10.18653/v1/2021.emnlp-main.414

Cited by 35 publications

(32 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Both methods produce claims which have high overlap with the reference claims, though claims generated directly using BART are significantly closer to the reference claims than those generated using CLAIMGEN-ENTITY. Finally, we note the these scores are in the range of state-of-the-art models used for paraphrase generation, establishing a solid baseline for this task (Zhou and Bhat, 2021).…”

Section: Rq2: Claim Quality Evaluationmentioning

confidence: 79%

Generating Scientific Claims for Zero-Shot Scientific Fact Checking

Wright¹,

Wadden²,

Lo³

et al. 2022

Preprint

View full text Add to dashboard Cite

Automated scientific fact checking is difficult due to the complexity of scientific language and a lack of significant amounts of training data, as annotation requires domain expertise. To address this challenge, we propose scientific claim generation, the task of generating one or more atomic and verifiable claims from scientific sentences, and demonstrate its usefulness in zero-shot fact checking for biomedical claims. We propose CLAIMGEN-BART, a new supervised method for generating claims supported by the literature, as well as KBIN, a novel method for generating claim negations. Additionally, we adapt an existing unsupervised entity-centric method of claim generation to biomedical claims, which we call CLAIMGEN-ENTITY. Experiments on zero-shot fact checking demonstrate that both CLAIMGEN-ENTITY and CLAIMGEN-BART, coupled with KBIN, achieve up to 90% performance of fully supervised models trained on manually annotated claims and evidence. A rigorous evaluation study demonstrates significant improvement in generated claim and negation quality over existing baselines. 1

show abstract

Section: Rq2: Claim Quality Evaluationmentioning

confidence: 79%

Generating Scientific Claims for Zero-Shot Scientific Fact Checking

Wright¹,

Wadden²,

Lo³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Paraphrase Generation has proven to be useful for adversarial training and data augmentation (Zhou and Bhat, 2021). Early methods adopt hand-crafted rules (McKeown, 1983), synonym substitution (Bolshakov and Gelbukh, 2004), machine translation (Quirk et al, 2004), and deep learning (Gupta et al, 2018; to improve the quality of generated sentences.…”

Section: Related Workmentioning

confidence: 99%

Syntactically Robust Training on Partially-Observed Data for Open Information Extraction

Qi¹,

Chen²,

Hou³

et al. 2023

Preprint

View full text Add to dashboard Cite

Open Information Extraction models have shown promising results with sufficient supervision. However, these models face a fundamental challenge that the syntactic distribution of training data is partially observable in comparison to the real world. In this paper, we propose a syntactically robust training framework that enables models to be trained on a syntactic-abundant distribution based on diverse paraphrase generation. To tackle the intrinsic problem of knowledge deformation of paraphrasing, two algorithms based on semantic similarity matching and syntactic tree walking are used to restore the expressionally transformed knowledge. The training framework can be generally applied to other syntactic partial observable domains. Based on the proposed framework, we build a new evaluation set called CaRB-AutoPara, a syntactically diverse dataset consistent with the real-world setting for validating the robustness of the models. Experiments including a thorough analysis show that the performance of the model degrades with the increase of the difference in syntactic distribution, while our framework gives a robust boundary. The source code is publicly available at https://github.com/qijimrc/RobustOIE.

show abstract

“…The main contribution in this paper is to build a model (INTERACTION) capable of providing multiple explanations, reflecting the diversity in natural languages. The motivation is that a natural language usually works in a way such that humans often provide more than one explanation for their actions, and hence may find systems that reply 'monosyllabically', or too briefly, potentially frustrating, or even non-informative [15], [51]. Still, our approach raises other questions, e.g., do humans have enough time to read multiple explanations?…”

Section: Diversity Of Explanationmentioning

confidence: 99%

INTERACTION: A Generative XAI Framework for Natural Language Inference Explanations

Cristea

Harit

et al. 2022

2022 International Joint Conference on Neural Networks (IJCNN)

View full text Add to dashboard Cite

XAI with natural language processing aims to produce human-readable explanations as evidence for AI decisionmaking, which addresses explainability and transparency. However, from an HCI perspective, the current approaches only focus on delivering a single explanation, which fails to account for the diversity of human thoughts and experiences in language. This paper thus addresses this gap, by proposing a generative XAI framework, INTERACTION (explaIn aNd predicT thEn queRy with contextuAl CondiTional varIational autO-eNcoder). Our novel framework presents explanation in two steps: (step one) Explanation and Label Prediction; and (step two) Diverse Evidence Generation. We conduct intensive experiments with the Transformer architecture on a benchmark dataset, e-SNLI [1]. Our method achieves competitive or better performance against state-of-the-art baseline models on explanation generation (up to 4.7% gain in BLEU) and prediction (up to 4.4% gain in accuracy) in step one; it can also generate multiple diverse explanations in step two.

show abstract

Paraphrase Generation: A Survey of the State of the Art

Cited by 35 publications

References 39 publications

Generating Scientific Claims for Zero-Shot Scientific Fact Checking

Generating Scientific Claims for Zero-Shot Scientific Fact Checking

Syntactically Robust Training on Partially-Observed Data for Open Information Extraction

INTERACTION: A Generative XAI Framework for Natural Language Inference Explanations

Contact Info

Product

Resources

About