[Adapt] [Seminar] Adapting the Neural Encoder-Decoder Framework from Single to Multi-Document Summarization

Yizhu Liu 337363896 at qq.com
Tue Mar 26 22:29:48 CST 2019


Hi Adapters,


I will give a talk about paper  "Adapting the Neural Encoder-Decoder Framework from Single to Multi-Document Summarization" which is accepted by emnlp 2018.


Generating a text abstract from a set of documents remains a challenging task. The neural encoder-decoder framework has recently been exploited to summarize single documents, but its success can in part be attributed to the availability of large parallel data automatically acquired from the Web. In contrast, data for multi-document summarization are scarce and costly to obtain. There is a pressing need to adapt an encoder-decoder model trained on single-document summarization data to work with multiple-document input. In this paper, we present an initial investigation into a novel adaptation method. It exploits the maximal marginal relevance method to select representative sentences from multi-document input, and leverages an abstractive encoder-decoder model to fuse disparate sentences to an abstractive summary. The adaptation method is robust and itself requires no training data. Our system compares favorably to state-of-the-art extractive and abstractive approaches judged by automatic metrics and human assessors.


Time: 17:00 March 27
Venue: SEIEE 3-414


Best,
Yizhu
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://cs.sjtu.edu.cn/pipermail/adapt/attachments/20190326/fba06904/attachment-0001.html>


More information about the Adapt mailing list