Abstract
A Semi-Supervised Paraphrase Identification Model Based on Multi-Granularity Interaction Reasoning
Highlights
Paraphrase identification task aims to predict whether two sentences are semantically equivalent or not
This task is important since many natural language processing tasks, such as question answering, text summarization, information extraction or machine translation, rely on it explicitly or implicitly and could benefit from more accurate paraphrase identification (PI) systems
Pre-training acts as a regularization scheme, enabling better generalization in proposed model. (iii) We evaluate our approach on two tasks: paraphrase identification, semantic relatedness measurement, and achieve absolute improvements upon the two tasks studied
Summary
Paraphrase identification task aims to predict whether two sentences are semantically equivalent or not This task is important since many natural language processing tasks, such as question answering, text summarization, information extraction or machine translation, rely on it explicitly or implicitly and could benefit from more accurate PI systems. In order to solve the bottleneck of lack of training corpus, we adapt a language modeling task because it does not require human labels and use large corpora to pre-train word embeddings and network weights to find a good initialization point. This is followed by the supervised training, where pre-trained parameters are tuned for optimal performance on PI.
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
