CTRLsum: Towards Generic Controllable Text Summarization

By Junxian He, Wojciech Kryscinski, Bryan McCann, Nazneen Rajani, Caiming Xiong. 2020

162 citations recorded by the source corpus.

Current summarization systems yield generic summaries that are disconnected from users’ preferences and expectations. To address this limitation, we present CTRLsum, a generic framework to control generated summaries through a set of keywords. During training keywords are extracted automatically without requiring additional human annotations. At test time CTRLsum features a control function to map control signal to keywords; through engineering the control function, the same trained model is able to be applied to control summaries on various dimensions, while neither affecting the model training process nor the pretrained models. We additionally explore the combination of keywords and text prompts for more control tasks. Experiments demonstrate the effectiveness of CTRLsum on three domains of summarization datasets and five control tasks: (1) entity-centric and (2) length-controllable summarization, (3) contribution summarization on scientific papers, (4) invention purpose summarization on patent filings, and (5) question-guided summarization on news articles. Moreover, when used in a standard, unconstrained summarization setting, CTRLsum is comparable or better than strong pretrained systems.

Subfields: Artificial Intelligence, Natural Language Processing

How researchers see this paper

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

In Artificial Intelligence

In Natural Language Processing

Citations in the corpus

Few-Shot Text Generation with Natural Language Instructions (2020, background): “Keskar et al. (2019) and He et al. (2020) similarly use prompts and keywords for controllable text generation, but require speciﬁc pretraining procedures and do so only in high-resource settings.”
PEER: A Collaborative Language Model (2022, methodology): “This enables us to use self-training techniques (e.g., Yarowsky, 1995; Sennrich et al., 2016; He et al., 2020a; Schick and Schütze, 2021a) for training PEER with synthetic plans, edits, explanations and documents.”
Self-Diagnosis and Self-Debiasing: A Proposal for Reducing Corpus-Based Bias in NLP (2021, background): “…(sdg, sdb 1 ) and §4.2 for bias types (sdb 2 ). proaches for controllable text generation (Keskar et al., 2019; Schick and Schütze, 2020; He et al., 2020) but these approaches (i) require either a customized pretraining objective or labeled training data, and (ii) use natural language…”
Planning with Learned Entity Prompts for Abstractive Summarization (2021, methodology): “, 2019), CTRLsum (He et al., 2020), GSum (Dou et al.”
News Summarization and Evaluation in the Era of GPT-3 (2022, methodology): “It includes summaries generated by GPT3-D2 and CTRLSum models.”
Few-Shot Text Generation with Pattern-Exploiting Training (2020, unknown): “Finally, our proposed variant of P ET is closely related to concurrent work by He et al. (2020) who use prompts and keywords for controllable text generation (but do so only in high-resource settings) and to preﬁx-constrained decoding (Knowles and Koehn, 2016; Wuebker et al., 2016; Keskar et al.,…”
Revisiting the Gold Standard: Grounding Summarization Evaluation with Robust Human Evaluation (2022, methodology): “CTRLSum (He et al., 2020) introduce a method for controllable summarization based on keyword or descriptive prompt control tokens.”
AdaPrompt: Adaptive Model Training for Prompt-based NLP (2022, background): “, 2020), summarization (Brown et al., 2020; He et al., 2020; Li and Liang, 2021), information extraction (Cui et al.”