A task in a suit and a tie: paraphrase generation with semantic augmentation
원문 초록
Paraphrasing is rooted in semantics. We show the effectiveness of transformers (Vaswani et al. 2017) for paraphrase generation and further improvements by incorporating PropBank labels via a multi-encoder. Evaluating on MSCOCO and WikiAnswers, we find that transformers are fast and effective, and that semantic augmentation for both transformers and LSTMs leads to sizable 2-3 point gains in BLEU, METEOR and TER. More importantly, we find surprisingly large gains on human evaluations compared to previous models. Nevertheless, manual inspection of generated paraphrases reveals ample room for improvement: even our best model produces human-acceptable paraphrases for only 28% of captions from the CHIA dataset (Sharma et al. 2018), and it fails spectacularly on sentences from Wikipedia. Overall, these results point to the potential for incorporating semantics in the task while highlighting the need for stronger evaluation.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Enhancing Paraphrase Type Generation: The Impact of DPO and RLHF Evaluated with Human-Ranked Data
A Large-Scale Benchmark for Vietnamese Sentence Paraphrases
SMAB: MAB based word Sensitivity Estimation Framework and its Applications in Adversarial Text Generation
Latent Paraphrasing: Perturbation on Layers Improves Knowledge Injection in Language Models
Retrieve, Generate, Evaluate: A Case Study for Medical Paraphrases Generation with Small Language Models
Action Controlled Paraphrasing
토론
이 논문과 연결된 포럼 글이 아직 없습니다.