Abstractive Text Summarization based on Language Model Conditioning and Locality Modeling

Dmitrii Aksenov, Julian Moreno-Schneider, Peter Bourgonje, Robert Schwarzenberg, Leonhard Hennig, Georg Rehm


Abstract
We explore to what extent knowledge about the pre-trained language model that is used is beneficial for the task of abstractive summarization. To this end, we experiment with conditioning the encoder and decoder of a Transformer-based neural model on the BERT language model. In addition, we propose a new method of BERT-windowing, which allows chunk-wise processing of texts longer than the BERT window size. We also explore how locality modeling, i.e., the explicit restriction of calculations to the local context, can affect the summarization ability of the Transformer. This is done by introducing 2-dimensional convolutional self-attention into the first layers of the encoder. The results of our models are compared to a baseline and the state-of-the-art models on the CNN/Daily Mail dataset. We additionally train our model on the SwissText dataset to demonstrate usability on German. Both models outperform the baseline in ROUGE scores on two datasets and show its superiority in a manual qualitative analysis.
Anthology ID:
2020.lrec-1.825
Volume:
Proceedings of the 12th Language Resources and Evaluation Conference
Month:
May
Year:
2020
Address:
Marseille, France
Venue:
LREC
SIG:
Publisher:
European Language Resources Association
Note:
Pages:
6680–6689
Language:
English
URL:
https://aclanthology.org/2020.lrec-1.825
DOI:
Bibkey:
Cite (ACL):
Dmitrii Aksenov, Julian Moreno-Schneider, Peter Bourgonje, Robert Schwarzenberg, Leonhard Hennig, and Georg Rehm. 2020. Abstractive Text Summarization based on Language Model Conditioning and Locality Modeling. In Proceedings of the 12th Language Resources and Evaluation Conference, pages 6680–6689, Marseille, France. European Language Resources Association.
Cite (Informal):
Abstractive Text Summarization based on Language Model Conditioning and Locality Modeling (Aksenov et al., LREC 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.lrec-1.825.pdf
Code
 axenov/BERT-Summ-OpenNMT
Data
CNN/Daily Mail