arXiv Open Access 2022

Document-aware Positional Encoding and Linguistic-guided Encoding for Abstractive Multi-document Summarization

Congbo Ma Wei Emma Zhang Pitawelayalage Dasun Dileepa Pitawela Yutong Qu Haojie Zhuang +1 lainnya
Lihat Sumber

Abstrak

One key challenge in multi-document summarization is to capture the relations among input documents that distinguish between single document summarization (SDS) and multi-document summarization (MDS). Few existing MDS works address this issue. One effective way is to encode document positional information to assist models in capturing cross-document relations. However, existing MDS models, such as Transformer-based models, only consider token-level positional information. Moreover, these models fail to capture sentences' linguistic structure, which inevitably causes confusions in the generated summaries. Therefore, in this paper, we propose document-aware positional encoding and linguistic-guided encoding that can be fused with Transformer architecture for MDS. For document-aware positional encoding, we introduce a general protocol to guide the selection of document encoding functions. For linguistic-guided encoding, we propose to embed syntactic dependency relations into the dependency relation mask with a simple but effective non-linear encoding learner for feature learning. Extensive experiments show the proposed model can generate summaries with high quality.

Topik & Kata Kunci

Penulis (6)

C

Congbo Ma

W

Wei Emma Zhang

P

Pitawelayalage Dasun Dileepa Pitawela

Y

Yutong Qu

H

Haojie Zhuang

H

Hu Wang

Format Sitasi

Ma, C., Zhang, W.E., Pitawela, P.D.D., Qu, Y., Zhuang, H., Wang, H. (2022). Document-aware Positional Encoding and Linguistic-guided Encoding for Abstractive Multi-document Summarization. https://arxiv.org/abs/2209.05929

Akses Cepat

Lihat di Sumber
Informasi Jurnal
Tahun Terbit
2022
Bahasa
en
Sumber Database
arXiv
Akses
Open Access ✓