MeanSum: A Neural Model for Unsupervised Multi-Document Abstractive Summarization

By Eric Chu, Peter J. Liu. 2018

214 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Natural Language Processing

Citations in the corpus

SummAE: Zero-Shot Abstractive Text Summarization using Length-Agnostic Auto-Encoders (2019, methodology): “3 Related Work Chu and Liu (2019) proposed a model for zero-shot multi-document abstractive summarization, where the mean of the representations from an auto-encoder for input documents is used to de-code a summary.”
Multi-News: A Large-Scale Multi-Document Summarization Dataset and Abstractive Hierarchical Model (2019, methodology): “…Cohan et al., 2018; C¸elikyilmaz et al., 2018; Gehrmann et al., 2018) In addition to the multi-document methods described above which address data sparsity, recent work has attempted unsupervised and weakly supervised methods in non-news domains (Chu and Liu, 2019; Angelidis and Lapata, 2018).”
A Distributional Approach to Controlled Text Generation (2020, methodology): “Continuous approximation using the Gumbel Softmax was developed for the training of Variational Autoencoders but several works have implemented it for natural language generation Shetty et al. (2017); Chu & Liu (2019); Kusner & Hernández-Lobato (2016).”
Improving Zero and Few-Shot Abstractive Summarization with Intermediate Fine-tuning and Data Augmentation (2020, methodology): “Unsupervised summarization approaches include autoencoders to mirror the information compression inherent in summarization (Baziotis et al., 2019; Chu and Liu, 2019; Braˇzinskas et al., 2020b) as well as large-scale pretraining for domain-speciﬁc adaptation (Yang et al., 2020).”
Multi-document Summarization via Deep Learning Techniques: A Survey (2020, methodology): “ al. Table 2. Deep Learning based Methods. DNN Architeture Works Construction Types Concatenation Methods Supervision Types Extractive Abstractive Hybrid Flat Hierarchical Supervised Unsupervised RNN [24] ✓ ✓ ✓ [146] ✓ ✓ ✓ [155] ✓ ✓ ✓ [90] ✓ ✓ ✓ [17] ✓ ✓ ✓ [3] ✓ ✓ ✓ [69] ✓ ✓ ✓ [134] ✓ ✓ ✓ [26] ✓ ✓ ✓”
Neural Data-to-Text Generation with LM-based Text Augmentation (2021, methodology): “On two data-to-text benchmarks E2E (Novikova et al., 2017) and WebNLG (Gardent et al., 2017), we show that our LM-augmented weakly supervised model succeeds on outperforming fully supervised seq2seq model, though utilizing less than 10% of the data annotations.”
Measuring Similarity of Opinion-bearing Sentences (2021, methodology): “…of reviews, NLP research has focused on methods to make sense of this vast data resource, including applications for opinion summarization (Suhara et al., 2020; Bražinskas et al., 2020b; Mukherjee et al., 2020; Chu and Liu, 2019; Angelidis and Lapata, 2018) and opinion search (Poddar et al., 2017).”
Unsupervised Neural Single-Document Summarization of Reviews via Learning Latent Discourse Structure and its Ranking (2019, methodology): “Furthermore, a third, novel unsupervised baseline model MeanSum-single is introduced, which is an extended version of the unsupervised neural multi-document summarization model (Chu and Liu, 2018).”
Hierarchical Transformers for Multi-Document Summarization (2019, methodology): “…model transfer (Zhang et al., 2018; Lebanoff and Liu, 2018), where a sequence-to-sequence model is pretrained on single-document summarization data and finetuned on DUC (multi-document) benchmarks, or unsupervised models relying on reconstruction objectives (Ma et al., 2016; Chu and Liu, 2018).”
Automatic Document Sketching: Generating Drafts from Analogous Texts (2021, background): “multiple input documents (Liu and Lapata, 2019; Chu and Liu, 2019), and multi-source machine translation (Nishimura et al.”
Aspect-Controllable Opinion Summarization (2021, methodology): “Abstractive systems include MEANSUM (Chu and Liu, 2019), an autoencoder that generates summaries by reconstructing the mean of review encodings, COPYCAT (Bražinskas et al.”
Few-Shot Learning for Opinion Summarization (2020, methodology): “Recently, a number of unsupervised abstractive multi-document models were introduced (e.g., COPYCAT; Bražinskas et al. 2020 and MEANSUM; Chu and Liu 2019) that are trained on large collections of unannotated product reviews.1 However, unsurprisingly perhaps, since the models are not exposed to the…”