Summarizing Answers in Non-Factoid Community Question-Answering

Song, Hongya; Zhang, Ren; Liang, Shangsong; Li, Piji; Ma, Jun; Rijke, Maarten de

doi:10.1145/3018661.3018704

Cited by 42 publications

(34 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Automatic summarization is the process of automatically generating a summary that retains the most important content of the original text document (Nenkova and McKeown, 2012). Traditionally, the summarization methods can be classified into three categories: extraction-based methods (Erkan and Radev, 2004;Goldstein et al, 2000;Wan et al, 2007;Min et al, 2012;Nallapati et al, 2017;Cheng and Lapata, 2016;Cao et al, 2016;Song et al, 2017), compression-based methods (Li et al, 2013;Wang et al, 2013;Li et al, 2015, and abstraction-based methods. In fact, previous investigations show that human-written summaries are more abstractive (Barzilay and McKeown, 2005;.…”

Section: Related Workmentioning

confidence: 99%

Deep Recurrent Generative Decoder for Abstractive Text Summarization

Lam

Wang

2017

Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing

Self Cite

181

105

View full text Add to dashboard Cite

We propose a new framework for abstractive text summarization based on a sequence-to-sequence oriented encoderdecoder model equipped with a deep recurrent generative decoder (DRGN). Latent structure information implied in the target summaries is learned based on a recurrent latent random model for improving the summarization quality. Neural variational inference is employed to address the intractable posterior inference for the recurrent latent variables. Abstractive summaries are generated based on both the generative latent variables and the discriminative deterministic states. Extensive experiments on some benchmark datasets in different languages show that DRGN achieves improvements over the state-ofthe-art methods.

show abstract

Section: Related Workmentioning

confidence: 99%

Deep Recurrent Generative Decoder for Abstractive Text Summarization

Lam

Wang

2017

Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing

Self Cite

181

105

View full text Add to dashboard Cite

show abstract

“…The work discussed various features affecting the quality of asked question. Such analysis of features are useful for forums to help users in formulating improved question so as to retrieve most prompt information they are searching for.Zhao et al, [32] considered the problem of expert finding from the view point of learning ranking metric embedding. The ranking metric network learning framework has integrated users' relative quality rank to given questions and their social relations for expert identification.…”

Section: Community Question Answering Systemmentioning

confidence: 99%

“…As a part of the survey, the study also highlighted current trends and the areasthat need to pave further attention from the research community. Song et al, [32] aimed at non-factoid question-answering that usually expects passages as answers. A sparse coding-based summarization strategy has been proposed that includes three core features: short document expansion, sentence vectorization, and a sparse-coding optimization framework.…”

Section: Community Question Answering Systemmentioning

confidence: 99%

Different Facets of Text Based Automated Question Answering System

Singh¹

2018

IJRASET

View full text Add to dashboard Cite

The exponential growth of online information has led to the development of technologies that help to deal with it. One of those information retrieval technologies is Question Answering (QA), a research field that has emerged at the intersection of information retrieval and natural language processing techniques, which allows users to find the answers to their questions in precise way. However, to cope up with changing needs of user, the recent QA system differ widely in the manner they interact to the user than the conventional one. Therefore, this paper attempts to present the state-of-the-art in the field of text based automatic question answering systems and provide a qualitative analysis of different facets. Finally, a summarized representation of these facets based on certain features of QA system has been done, to bring an insight for the future research.

show abstract

“…For example, Mihalcea and Tarau (2004) and Erkan and Radev (2004a) estimated sentence salience by applying the PageRank algorithm to the sentence graph. He et al (2012), Liu et al (2015), Li et al (2015) and Song et al (2017) employed sparse coding techniques for finding the salient sentences as summaries. conducted salience estimation jointly considering reconstructions on several different vector spaces generated by a variational auto-ecoder framework.…”

Section: Related Workmentioning

confidence: 99%

Cascaded Attention based Unsupervised Information Distillation for Compressive Summarization

Li¹,

Lam²,

Guo³

et al. 2017

Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing

Self Cite

View full text Add to dashboard Cite

When people recall and digest what they have read for writing summaries, the important content is more likely to attract their attention. Inspired by this observation, we propose a cascaded attention based unsupervised model to estimate the salience information from the text for compressive multi-document summarization. The attention weights are learned automatically by an unsupervised data reconstruction framework which can capture the sentence salience. By adding sparsity constraints on the number of output vectors, we can generate condensed information which can be treated as word salience. Fine-grained and coarse-grained sentence compression strategies are incorporated to produce compressive summaries. Experiments on some benchmark data sets show that our framework achieves better results than the state-of-the-art methods.

show abstract

Summarizing Answers in Non-Factoid Community Question-Answering

Cited by 42 publications

References 36 publications

Deep Recurrent Generative Decoder for Abstractive Text Summarization

Deep Recurrent Generative Decoder for Abstractive Text Summarization

Different Facets of Text Based Automated Question Answering System

Cascaded Attention based Unsupervised Information Distillation for Compressive Summarization

Contact Info

Product

Resources

About