• Corpus ID: 227745074

CTRLsum: Towards Generic Controllable Text Summarization

@article{He2020CTRLsumTG,
  title={CTRLsum: Towards Generic Controllable Text Summarization},
  author={Junxian He and Wojciech Kryscinski and Bryan McCann and Nazneen Rajani and Caiming Xiong},
  journal={ArXiv},
  year={2020},
  volume={abs/2012.04281}
}
Current summarization systems yield generic summaries that are disconnected from users' preferences and expectations. To address this limitation, we present CTRLsum, a novel framework for controllable summarization. Our approach enables users to control multiple aspects of generated summaries by interacting with the summarization system through textual input in the form of a set of keywords or descriptive prompts. Using a single unified model, CTRLsum is able to achieve a broad scope of summary… 

Figures and Tables from this paper

EntSUM: A Data Set for Entity-Centric Extractive Summarization
TLDR
This work introduces a human-annotated data set EntSUM for controllable summarization with a focus on named entities as the aspects to control and proposes extensions to state-of-the-art summarization approaches that achieve substantially better results.
HydraSum - Disentangling Stylistic Features in Text Summarization using Multi-Decoder Models
TLDR
This work introduces HYDRASUM, a new summarization architecture that extends the single decoder framework of current models, e.g. BART, to a mixture-of-experts version consisting of multiple decoders, and shows that a guided version of the training process can explicitly govern which summary style is partitioned between decmoders, i.e. high abstractiveness vs. low specificity.
Unsupervised Summarization with Customized Granularities
TLDR
This paper proposes the first unsupervised multi-granularity summarization framework, GranuSum, which takes events as the basic semantic units of the source documents and proposes to rank these events by their salience, and develops a model to summarize input documents with given events as anchors and hints.
Question-Based Salient Span Selection for More Controllable Text Summarization
TLDR
A method for incorporating question-answering (QA) signals into a summarization model that identifies salient noun phrases in the input document by automatically generating wh-questions that are answered by the NPs and automatically determining whether those questions are answered in the gold summaries.
Towards Human-Centered Summarization: A Case Study on Financial News
TLDR
This work proposes to integrate a user interface with an underlying DL model, instead of tackling summarization as an isolated task from the end user, and presents a novel system, where the user can actively participate in the whole summarization process.
Aspect-Oriented Summarization through Query-Focused Extraction
TLDR
This paper collects a dataset of realistic aspect-oriented test cases, ASPECTNEWS, and investigates how query-focused methods, for which it can construct synthetic data, can handle this aspect- oriented setting, and benchmarks extractive query- focused training schemes, and proposes a contrastive augmentation approach to train the model.
Planning with Learned Entity Prompts for Abstractive Summarization
TLDR
It is demonstrated empirically that the grounded generation with the planning objective improves entity specificity and planning in summaries for all datasets, and achieves state-of-the-art performance on XSum and SAMSum in terms of rouge.
Long-Span Summarization via Local Attention and Content Selection
TLDR
This work exploits large pre-trained transformer-based models and address long-span dependencies in abstractive summarization using two methods: local self-attention; and explicit content selection, which can achieve comparable or better results than existing approaches.
Controllable Neural Dialogue Summarization with Personal Named Entity Planning
TLDR
A controllable neural generation framework that can flexibly guide dialogue summarization with personal named entity planning and generates fluent and factually consistent summaries under various planning controls using both objective metrics and human evaluations is proposed.
ASPECTNEWS: Aspect-Oriented Summarization of News Documents
TLDR
This paper collects a dataset of realistic aspect-oriented summaries, AspectNews, which covers different subtopics about articles in news sub-domains, and compares several training schemes that differ in how strongly keywords are used and how oracle summaries are extracted.
...
1
2
3
...

References

SHOWING 1-10 OF 74 REFERENCES
Controllable Abstractive Summarization
TLDR
A neural summarization model with a simple but effective mechanism to enable users to specify high level attributes in order to control the shape of the final summaries to better suit their needs.
Length-controllable Abstractive Summarization by Guiding with Summary Prototype
TLDR
A new length-controllable abstractive summarization model that incorporates a word-level extractive module in the encoder-decoder model instead of length embeddings to generate an informative and length-controlled summary.
BIGPATENT: A Large-Scale Dataset for Abstractive and Coherent Summarization
TLDR
This work presents a novel dataset, BIGPATENT, consisting of 1.3 million records of U.S. patent documents along with human written abstractive summaries, which has the following properties: i) summaries contain a richer discourse structure with more recurring entities, ii) salient content is evenly distributed in the input, and iii) lesser and shorter extractive fragments are present in the summaries.
Neural Text Summarization: A Critical Evaluation
TLDR
This work critically evaluate key ingredients of the current research setup: datasets, evaluation metrics, and models, and highlights three primary shortcomings: automatically collected datasets leave the task underconstrained and may contain noise detrimental to training and evaluation.
Bottom-Up Abstractive Summarization
TLDR
This work explores the use of data-efficient content selectors to over-determine phrases in a source document that should be part of the summary, and shows that this approach improves the ability to compress text, while still generating fluent summaries.
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.
A Discourse-Aware Attention Model for Abstractive Summarization of Long Documents
TLDR
This work proposes the first model for abstractive summarization of single, longer-form documents (e.g., research papers), consisting of a new hierarchical encoder that models the discourse structure of a document, and an attentive discourse-aware decoder to generate the summary.
Neural Summarization by Extracting Sentences and Words
TLDR
This work develops a general framework for single-document summarization composed of a hierarchical document encoder and an attention-based extractor that allows for different classes of summarization models which can extract sentences or words.
SummaRuNNer: A Recurrent Neural Network Based Sequence Model for Extractive Summarization of Documents
We present SummaRuNNer, a Recurrent Neural Network (RNN) based sequence model for extractive summarization of documents and show that it achieves performance better than or comparable to
Guiding Generation for Abstractive Text Summarization Based on Key Information Guide Network
TLDR
A guiding generation model that combines the extractive method and the abstractive method, and introduces a Key Information Guide Network (KIGN), which encodes the keywords to the key information representation, to guide the process of generation.
...
1
2
3
4
5
...