Self reinforcement for important passage retrieval

By Ricardo Ribeiro, Luís Marujo, David Martins de Matos, João Paulo da Silva Neto, Anatole Gershman, Jaime G. Carbonell. 2013

18 citations recorded by the source corpus.

In general, centrality-based retrieval models treat all elements of the retrieval space equally, which may reduce their effectiveness. In the specific context of extractive summarization (or important passage retrieval), this means that these models do not take into account that information sources often contain lateral issues, which are hardly as important as the description of the main topic, or are composed by mixtures of topics. We present a new two-stage method that starts by extracting a collection of key phrases that will be used to help centrality-as-relevance retrieval model. We explore several approaches to the integration of the key phrases in the centrality model. The proposed method is evaluated using different datasets that vary in noise (noisy vs clean) and language (Portuguese vs English). Results show that the best variant achieves relative performance improvements of about 31% in clean data and 18% in noisy data.

Subfields: Artificial Intelligence, Information Systems

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

1. Yang Fang
2. Weidong Xiao
3. Yuheng Wang
4. Yong Zhang
5. Dan Li

Citations in the corpus

• Abstract Text Summarization with a Convolutional Seq2seq Model (2019, background): “Lots of previous work in summarization focuses on extractive methods, that is, directly extract key words or sentences from the original document and then reproduce them as summary [12–15].”