Learning-Based Single-Document Summarization with Compression and Anaphoricity Constraints
Greg Durrett, Taylor Berg-Kirkpatrick, Dan Klein · Annual Meeting of the Association for Computational Linguistics (ACL) · 2016
We present a discriminative model for single-document summarization that integrally combines compression and anaphoricity constraints.Our model selects textual units to include in the summary based on a rich set of sparse features whose weights are learned on a large corpus.We allow for the deletion of content within a sentence when that deletion is licensed by compression rules; in our framework, these are implemented as dependencies between subsentential units of text.Anaphoricity constraints then improve cross-sentence coherence by guaranteeing that, for each pronoun included in the summary, the pronoun's antecedent is included as well or the pronoun is rewritten as a full mention.When trained end-to-end, our final system 1 outperforms prior work on both ROUGE as well as on human judgments of linguistic quality.
Cited by 146 works. doi:10.18653/v1/p16-1188 Open-access PDF
Authors
References
- Logic and Conversation
- Adaptive Subgradient Methods for Online Learning and Stochastic Optimization
- Rhetorical Structure Theory: Toward a functional theory of text organization
- Automatic evaluation of summaries using N-gram co-occurrence statistics
- The Use of MMR, Diversity-Based Reranking for Reordering Documents and Producing Summaries
- The use of MMR, diversity-based reranking for reordering documents and producing summaries
- Learning accurate, compact, and interpretable tree annotation
- Online large-margin training of dependency parsers
- Automatic Summarization
- Centering: A Framework for Modelling the Local Coherence of Discourse,