Self reinforcement for important passage retrieval

Abstract

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.

Diversity driven attention model for query-based abstractive summarization

“…Summarization has been studied in the context of text ( (Mani, 2001), (Das and Martins, 2007), (Nenkova and McKeown, 2012)) as well as speech ((Zhu and Penn, 2006), (Zhu et al, 2009)). A vast majority of this work has focused on extractive summarization where the idea is to construct a summary by selecting the most relevant sentences from the document ( (Neto et al, 2002), (Erkan and Radev, 2004), (Filippova and Altun, 2013), (Colmenares et al, 2015), (Riedhammer et al, 2010), (Ribeiro et al, 2013)). There has been some work on abstractive summarization in the context of DUC-2003 and DUC-2004 contests (Zajic et al).…”

Extending a Single-Document Summarizer to Multi-Document: a Hierarchical Approach

“…To retrieve the most important sentences of an information source, we used the KP-CENTRALITY method (Ribeiro et al, 2013). We chose this model for its adaptability to different types of information sources (e.g., text, audio and video), while supporting privacy (Marujo et al, 2014), and offering stateof-art performance.…”

“…Our multi-document approach is built upon a centrality and coverage-based single-document summarization method, KP-CENTRALITY (Ribeiro et al, 2013). This method, through the use of key phrases, is easily adaptable and has been shown to be robust in the presence of noisy input.…”

Abstract Text Summarization with a Convolutional Seq2seq Model

“…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][13][14][15].…”