A Closer Look at Data Bias in Neural Extractive Summarization Models

Zhong, Ming; Wang, Danqing; Liu, Pengfei; Qiu, Xipeng; Huang, Xuanjing

doi:10.18653/v1/d19-5410

Cited by 39 publications

(18 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Multi-domain Setting Previous datasets are specified to one domain. However, the model trained on the summarization data of a single domain usually has poor generalization ability (Wang et al, 2019;Zhong et al, 2019b;. Therefore, QMSum contains meetings across multiple domains: Product, Academic and Committee meetings.…”

Section: Number Of Meetings and Summariesmentioning

confidence: 99%

QMSum: A New Benchmark for Query-based Multi-domain Meeting Summarization

Zhong¹,

Yin²,

Yu³

et al. 2021

Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Langua

Self Cite

View full text Add to dashboard Cite

Meetings are a key component of human collaboration. As increasing numbers of meetings are recorded and transcribed, meeting summaries have become essential to remind those who may or may not have attended the meetings about the key decisions made and the tasks to be completed. However, it is hard to create a single short summary that covers all the content of a long meeting involving multiple people and topics. In order to satisfy the needs of different types of users, we define a new query-based multi-domain meeting summarization task, where models have to select and summarize relevant spans of meetings in response to a query, and we introduce QMSum, a new benchmark for this task. QMSum consists of 1,808 query-summary pairs over 232 meetings in multiple domains. Besides, we investigate a locate-then-summarize method and evaluate a set of strong summarization baselines on the task. Experimental results and manual analysis reveal that QMSum presents significant challenges in long meeting summarization for future research. Dataset is available at https://github.com/Yale-LILY/ QMSum.

show abstract

Section: Number Of Meetings and Summariesmentioning

confidence: 99%

QMSum: A New Benchmark for Query-based Multi-domain Meeting Summarization

Zhong¹,

Yin²,

Yu³

et al. 2021

Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Langua

Self Cite

View full text Add to dashboard Cite

show abstract

“…Extractive Document Summarization With the development of neural networks, great progress has been made in extractive document summarization. Most of them focus on the encoderdecoder framework and use recurrent neural networks (Cheng and Lapata, 2016;Nallapati et al, 2017; or Transformer encoders (Zhong et al, 2019b;Wang et al, 2019a) for the sentential encoding. Recently, pre-trained language models are also applied in summarization for contextual word representations (Zhong et al, 2019a;Liu and Lapata, 2019b;Zhong et al, 2020).…”

Section: Related Workmentioning

confidence: 99%

Heterogeneous Graph Neural Networks for Extractive Document Summarization

Wang¹,

Liu²,

Zheng³

et al. 2020

Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

Self Cite

220

View full text Add to dashboard Cite

As a crucial step in extractive document summarization, learning cross-sentence relations has been explored by a plethora of approaches. An intuitive way is to put them in the graphbased neural network, which has a more complex structure for capturing inter-sentence relationships. In this paper, we present a heterogeneous graph-based neural network for extractive summarization (HETERSUMGRAPH), which contains semantic nodes of different granularity levels apart from sentences. These additional nodes act as the intermediary between sentences and enrich the cross-sentence relations. Besides, our graph structure is flexible in natural extension from a singledocument setting to multi-document via introducing document nodes. To our knowledge, we are the first one to introduce different types of nodes into graph-based neural networks for extractive document summarization and perform a comprehensive qualitative analysis to investigate their benefits. The code will be released on Github 1 .

show abstract

“…Recent research work on extractive summarization spans a large range of approaches. These works usually instantiate their encoder-decoder architecture by choosing RNN (Nallapati et al, 2017;Zhou et al, 2018), Transformer (Wang et al, 2019;Zhong et al, 2019b;Zhang et al, 2019b) or GNN Jia et al, 2020b) as encoder, autoregressive (Jadhav and Rajan, 2018; or RL-based (Narayan et al, 2018;Arumae and Liu, 2018;Luo et al, 2019) decoders. For two-stage summarization, Chen and Bansal (2018) and Bae et al (2019) follow a hybrid extract-then-rewrite architecture, with policy-based RL to bridge the two networks together.…”

Section: Extractive Summarizationmentioning

confidence: 99%

Deep Differential Amplifier for Extractive Summarization

Jia¹,

Cao²,

Fang³

et al. 2021

Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Confer

View full text Add to dashboard Cite

For sentence-level extractive summarization, there is a disproportionate ratio of selected and unselected sentences, leading to flatting the summary features when optimizing the classification. The imbalanced sentence classification in extractive summarization is inherent, which can't be addressed by data sampling or data augmentation algorithms easily. In order to address this problem, we innovatively consider the single-document extractive summarization as a rebalance problem and present a deep differential amplifier framework to enhance the features of summary sentences. Specifically, we calculate and amplify the semantic difference between each sentence and other sentences, and apply the residual unit to deepen the differential amplifier architecture. Furthermore, the corresponding objective loss of the minority class is boosted by a weighted cross-entropy. In this way, our model pays more attention to the pivotal information of one sentence, that is different from previous approaches which model all informative context in the source document. Experimental results on two benchmark datasets show that our summarizer performs competitively against state-of-the-art methods. Our source code will be available on Github.

show abstract

A Closer Look at Data Bias in Neural Extractive Summarization Models

Cited by 39 publications

References 27 publications

QMSum: A New Benchmark for Query-based Multi-domain Meeting Summarization

QMSum: A New Benchmark for Query-based Multi-domain Meeting Summarization

Heterogeneous Graph Neural Networks for Extractive Document Summarization

Deep Differential Amplifier for Extractive Summarization

Contact Info

Product

Resources

About