Towards Improving Abstractive Summarization via Entailment Generation

By Ramakanth Pasunuru, Han Guo, Mohit Bansal. 2017

35 citations recorded by the source corpus.

Abstractive summarization, the task of rewriting and compressing a document into a short summary, has achieved considerable success with neural sequence-to-sequence models. However, these models can still benefit from stronger natural language inference skills, since a correct summary is logically entailed by the input document, i.e., it should not contain any contradictory or unrelated information. We incorporate such knowledge into an abstractive summarization model via multi-task learning, where we share its decoder parameters with those of an entailment generation model. We achieve promising initial improvements based on multiple metrics and datasets (including a test-only setting). The domain mismatch between the entailment (captions) and summarization (news) datasets suggests that the model is learning some domain-agnostic inference skills.

Subfields: Artificial Intelligence, Natural Language Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Natural Language Processing

Citations in the corpus

The Natural Language Decathlon: Multitask Learning as Question Answering (2018, methodology): “Reinforcement learning has pushed performance using common summarization metrics [Paulus et al., 2017] as well as alternative metrics that transfer knowledge from another task [Pasunuru et al., 2017, Pasunuru and Bansal, 2018].”
Ranking Generated Summaries by Correctness: An Interesting but Challenging Application for Natural Language Inference (2019, neutral): “multi-task learning with NLI (Li et al., 2018; Pasunuru et al., 2017) to successfully improve the correctness of abstractive sentence summaries.”
Soft Layer-Specific Multi-Task Summarization with Entailment and Question Generation (2018, background): “…new high-level layer-speciﬁc sharing approach is sig-niﬁcantly better than alternative layer-sharing approaches (including the decoder-only sharing by Pasunuru et al. (2017)); (3) Our new soft sharing parameter approach gives stat. signiﬁcant improvements over hard sharing; (4) We pro-pose a…”
Ensure the Correctness of the Summary: Incorporate Entailment Knowledge into Abstractive Sentence Summarization (2018, methodology): “Pasunuru et al. (2017) propose a multi-task learning (MTL) frame- work in which the decoder is shared for summarization generation and entailment generation task.”