TIIS (한국인터넷정보학회)
Current Result Document : 2 / 2
| 한글제목(Korean Title) |
KI-HABS: Key Information Guided Hierarchical Abstractive Summarization |
| 영문제목(English Title) |
KI-HABS: Key Information Guided Hierarchical Abstractive Summarization |
| 저자(Author) |
Mengli Zhang
Gang Zhou
Wanting Yu
Wenfen Liu
|
| 원문수록처(Citation) |
VOL 15 NO. 12 PP. 4275 ~ 4291 (2021. 12) |
한글내용
(Korean Abstract) |
|
영문내용
(English Abstract) |
With the unprecedented growth of textual information on the Internet, an efficient automatic summarization system has become an urgent need. Recently, the neural network models based on the encoder-decoder with an attention mechanism have demonstrated powerful capabilities in the sentence summarization task. However, for paragraphs or longer document summarization, these models fail to mine the core information in the input text, which leads to information loss and repetitions. In this paper, we propose an abstractive document summarization method by applying guidance signals of key sentences to the encoder based on the hierarchical encoder-decoder architecture, denoted as KI-HABS. Specifically, we first train an extractor to extract key sentences in the input document by the hierarchical bidirectional GRU. Then, we encode the key sentences to the key information representation in the sentence level. Finally, we adopt key information representation guided selective encoding strategies to filter source information, which establishes a connection between the key sentences and the document. We use the CNN/Daily Mail and Gigaword datasets to evaluate our model. The experimental results demonstrate that our method generates more informative and concise summaries, achieving better performance than the competitive models. |
| 키워드(Keyword) |
neural network
deep learning
NLP
abstractive summarization
selective encoding
|
| 파일첨부 |
PDF 다운로드
|
