Abstract
Sentence simplification aims to simplify a complex sentences while retaining its main idea. It is one of the most important tasks in natural language processing. Recent works addressed the task with sequence-to-sequence(Seq2seq) model. However, these conventional Seq2seq models usually based on a single-stage encoder, which only read the source complex sentence once, as a result, it was hard to extract the representational features of the source sentence precisely. To resolve the problem, we proposed a multi-stage encoder based Seq2seq model for sentence simplification. Specificly, there were three stages in the encoder of proposed model, namely N-gram reading stage, glance-over stage and final encoding stage. The N-gram reading stage catched N-gram feature embedding for other stage and the glance-over stage extracted local and global information about the source sentence. The final encoding stage took advantage of the information extracted by the former two stage to encode source sentence better. Then, it introduced a novel attention connection method which could help the decoder to make full use of the information of encoder. Experiments on three public datasets demonstrated the proposed model that outperforms state-of-the-art baseline simplification systems.
Highlights
Natural Language Processing (NLP) is one of major techniques in artificial intelligence, and it has a lot of applications, such as machine translation [1], summarization [2] and natural language inference [3] etc
Following the works of [18], [19], this paper proposed a multi-stage encoder based Seq2seq model which considered the fact that when humans read a complex sentence, they would read the sentence two or more times and when they read a word, they would read other words around the word to get more precise meaning of it
In order to resolve this problem, this paper proposed a multi-stage encoder based Seq2seq model, and introduced a weak attention connection method for our decoder which can make full use of the features extracted from the multi-stage encoder
Summary
Natural Language Processing (NLP) is one of major techniques in artificial intelligence, and it has a lot of applications, such as machine translation [1], summarization [2] and natural language inference [3] etc. The main purpose of sentence simplification is to simplify the linguistic complexity of text and makes it easier to understand and accept while retaining its original idea. Sentence simplification has many application scenarios in practice. It provides reading aids to people with low-literacy skills, such as non-native speakers, children as well as patients with linguistic and cognitive disabilities [4], [5]. It can be a downstream task to improve the performance of other NLP tasks [6]–[8]
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.
