Adapting Neural Single-Document Summarization Model for Abstractive Multi-Document Summarization: A Pilot Study

@inproceedings{Zhang2018AdaptingNS,
  title={Adapting Neural Single-Document Summarization Model for Abstractive Multi-Document Summarization: A Pilot Study},
  author={Jianmin Zhang and Jiwei Tan and Xiaojun Wan},
  booktitle={INLG},
  year={2018}
}
Till now, neural abstractive summarization methods have achieved great success for single document summarization (SDS). However, due to the lack of large scale multi-document summaries, such methods can be hardly applied to multi-document summarization (MDS). In this paper, we investigate neural abstractive methods for MDS by adapting a state-of-the-art neural abstractive summarization model for SDS. We propose an approach to extend the neural abstractive model trained on large scale SDS data… Expand
Multi-News: A Large-Scale Multi-Document Summarization Dataset and Abstractive Hierarchical Model
TLDR
This work introduces Multi-News, the first large-scale MDS news dataset, and proposes an end-to-end model which incorporates a traditional extractive summarization model with a standard SDS model and achieves competitive results on MDS datasets. Expand
Multi-document Summarization via Deep Learning Techniques: A Survey
TLDR
This survey structurally overviews the recent deep learning based multi-document summarization models via a proposed taxonomy and proposes a novel mechanism to summarize the design strategies of neural networks and conduct a comprehensive summary of the state-of-the-art. Expand
Learning to Consider Relevance and Redundancy Dynamically for Abstractive Multi-document Summarization
TLDR
This paper proposes an end-to-end abstractive model based on Transformer to generate summaries, considering relevance and redundancy dynamically and jointly, and employs sentence masks and design a sentence-level transformer layer for learning sentence representations in a hierarchical manner. Expand
Multi-Document Summarization with Determinantal Point Process Attention
TLDR
This work proposes an attention mechanism which encourages greater focus on relevance and diversity and integrates DPP-based attention with various seq-to-seq architectures ranging from CNNs to LSTMs, and Transformers. Expand
Hierarchical Transformers for Multi-Document Summarization
TLDR
A neural summarization model which can effectively process multiple input documents and distill Transformer architecture with the ability to encode documents in a hierarchical manner is developed. Expand
Multi-document Summarization with Maximal Marginal Relevance-guided Reinforcement Learning
TLDR
RL-MMR, Maximal Margin Relevance-guided Reinforcement Learning for MDS is presented, which unifies advanced neural SDS methods and statistical measures used in classical MDS and shows the benefits of incorporating MMR into end-to-end learning when adapting SDS to MDS in terms of both learning effectiveness and efficiency. Expand
Nutri-bullets Hybrid: Consensual Multi-document Summarization
TLDR
Compared to conventional methods, the hybrid generation approach inspired by traditional concept-to-text systems leads to more faithful, relevant and aggregation-sensitive summarization – while being equally fluent. Expand
Enhance Content Selection for Multi-Document Summarization with Entailment Relation
TLDR
The main contribution of the approach is to use the entailment relation to obtain key content in multiple articles to improve the accuracy of MDS. Expand
PoBRL: Optimizing Multi-Document Summarization by Blending Reinforcement Learning Policies
TLDR
This work proposes a novel reinforcement learning based framework PoBRL for solving multidocument summarization that decouples this multi-objective optimization into different sub-problems that can be solved individually by reinforcement learning. Expand
Generating Representative Headlines for News Stories
TLDR
The first manually curated benchmark dataset on headline generation for news stories, NewSHead, is published, which contains 367K stories, 6.5 times larger than the current largest multi-document summarization dataset. Expand
...
1
2
...

References

SHOWING 1-10 OF 36 REFERENCES
Abstractive Document Summarization with a Graph-Based Attentional Neural Model
TLDR
A novel graph-based attention mechanism in the sequence-to-sequence framework to address the saliency factor of summarization, which has been overlooked by prior works and is competitive with state-of-the-art extractive methods. Expand
Abstractive Text Summarization using Sequence-to-sequence RNNs and Beyond
TLDR
This work proposes several novel models that address critical problems in summarization that are not adequately modeled by the basic architecture, such as modeling key-words, capturing the hierarchy of sentence-to-word structure, and emitting words that are rare or unseen at training time. Expand
A Neural Attention Model for Abstractive Sentence Summarization
TLDR
This work proposes a fully data-driven approach to abstractive sentence summarization by utilizing a local attention-based model that generates each word of the summary conditioned on the input sentence. Expand
Query Focused Abstractive Summarization: Incorporating Query Relevance, Multi-Document Coverage, and Summary Length Constraints into seq2seq Models
TLDR
The method (Relevance Sensitive Attention for QFS) is compared to extractive baselines and with various ways to combine abstractive models on the DUC QFS datasets and with solid improvements on ROUGE performance. Expand
Recent advances in document summarization
TLDR
Significant contributions made in recent years are emphasized, including progress on modern sentence extraction approaches that improve concept coverage, information diversity and content coherence, as well as attempts from summarization frameworks that integrate sentence compression, and more abstractive systems that are able to produce completely new sentences. Expand
Towards Multidocument Summarization by Reformulation: Progress and Prospects
TLDR
The evaluation of system components shows that learning over multiple extracted linguistic features is more effective than information retrieval approaches at identifying similar text units for summarization and that it is possible to generate a fluent summary that conveys similarities among documents even when full semantic interpretations of the input text are not available. Expand
A Deep Reinforced Model for Abstractive Summarization
TLDR
A neural network model with a novel intra-attention that attends over the input and continuously generated output separately, and a new training method that combines standard supervised word prediction and reinforcement learning (RL) that produces higher quality summaries. Expand
Multiple Aspect Summarization Using Integer Linear Programming
TLDR
Experimental results on the TAC-08 data set show that the model achieves state-of-the-art performance using ROUGE and significantly improves the informativeness of the summaries. Expand
Using Supervised Bigram-based ILP for Extractive Summarization
TLDR
A bigram based supervised method for extractive document summarization in the integer linear programming (ILP) framework that consistently outperforms the previous ILP method on different TAC data sets, and performs competitively compared to the best results in the TAC evaluations. Expand
Get To The Point: Summarization with Pointer-Generator Networks
TLDR
A novel architecture that augments the standard sequence-to-sequence attentional model in two orthogonal ways, using a hybrid pointer-generator network that can copy words from the source text via pointing, which aids accurate reproduction of information, while retaining the ability to produce novel words through the generator. Expand
...
1
2
3
4
...