تركز هذه الورقة على إعادة صياغة إعادة صياغة النص، وهي مهمة توليد اللغة الطبيعية المدروسة على نطاق واسع في NLP.مع تطور النماذج العصبية، أظهرت أبحاث توليد إعادة صياغة التحول التدريجي إلى الأساليب العصبية في السنوات الأخيرة.وقد قدم ذلك بهيئات تمثيل سياقي لنص المدخلات وتوليد صياغة تشبه الإنسان تشبه الإنسان بطلاقة.تقوم هذه الورقة بإجراء مناهج مختلفة لإعادة صياغة إعادة صياغة التركيز الرئيسي على الأساليب العصبية.
This paper focuses on paraphrase generation,which is a widely studied natural language generation task in NLP. With the development of neural models, paraphrase generation research has exhibited a gradual shift to neural methods in the recent years. This has provided architectures for contextualized representation of an input text and generating fluent, diverseand human-like paraphrases. This paper surveys various approaches to paraphrase generation with a main focus on neural methods.
References used
https://aclanthology.org/
Paraphrase generation is an important task in natural language processing. Previous works focus on sentence-level paraphrase generation, while ignoring document-level paraphrase generation, which is a more challenging and valuable task. In this paper
A long-standing issue with paraphrase generation is the lack of reliable supervision signals. In this paper, we propose a new unsupervised paradigm for paraphrase generation based on the assumption that the probabilities of generating two sentences w
While Yu and Poesio (2020) have recently demonstrated the superiority of their neural multi-task learning (MTL) model to rule-based approaches for bridging anaphora resolution, there is little understanding of (1) how it is better than the rule-based
We propose to control paraphrase generation through carefully chosen target syntactic structures to generate more proper and higher quality paraphrases. Our model, AESOP, leverages a pretrained language model and adds deliberately chosen syntactical
Paraphrase generation is a longstanding NLP task that has diverse applications on downstream NLP tasks. However, the effectiveness of existing efforts predominantly relies on large amounts of golden labeled data. Though unsupervised endeavors have be