A major proportion of a text summary includes important entities found in the original text. These entities build up the topic of the summary. Moreover, they hold commonsense information once they are linked to a knowledge base. Based on these observations, this paper investigates the usage of linked entities to guide the decoder of a neural text summarizer to generate concise and better summaries. To this end, we leverage on an off-The-shelf entity linking system (ELS) to extract linked entities and propose Entity2Topic (E2T), a module easily attachable to a sequence-To-sequence model that transforms a list of entities into a vector representation of the topic of the summary. Current available ELS's are still not sufficiently effective, possibly introducing unresolved ambiguities and irrelevant entities. We resolve the imperfections of the ELS by (a) encoding entities with selective disambiguation, and (b) pooling entity vectors using firm attention. By applying E2T to a simple sequenceto-sequence model with attention mechanism as base model, we see significant improvements of the performance in the Gigaword (sentence to title) and CNN (long document to multi-sentence highlights) summarization datasets by at least 2 ROUGE points.
|Title of host publication||Long Papers|
|Publisher||Association for Computational Linguistics (ACL)|
|Number of pages||11|
|Publication status||Published - 2018|
|Event||2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2018 - New Orleans, United States|
Duration: 2018 Jun 1 → 2018 Jun 6
|Name||NAACL HLT 2018 - 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies - Proceedings of the Conference|
|Conference||2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2018|
|Period||18/6/1 → 18/6/6|
Bibliographical noteFunding Information:
We would like to thank the three anonymous reviewers for their valuable feedback. This work was supported by Microsoft Research, and Institute for Information communications Technology Promotion (IITP) grant funded by the Korea government (MSIT) (No.2017-0-01778 , Development of Explainable Humanlevel Deep Machine Learning Inference Framework). S. Hwang is a corresponding author.
© 2018 The Association for Computational Linguistics.
All Science Journal Classification (ASJC) codes
- Linguistics and Language
- Language and Linguistics
- Computer Science Applications