Summarization Using Reinforcement Learning

By Seonggi Ryang, Takeshi Abekawa. 2012

Subfields: Natural Language Processing, Reinforcement Learning

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

In Reinforcement Learning

Citations in the corpus

Learning to Extract Coherent Summary via Deep Reinforcement Learning (2018, background): “Although (Ryang and Abekawa 2012; Rioux, Hasan, and Chali 2014; Henb, Mieskes, and Gurevych 2015) use value-based RL algorithms for extractive summarization, all of them are based on handcrafted features and do not consider coherence as the part of the reward.”
Ranking Sentences for Extractive Summarization with Reinforcement Learning (2018, methodology): “maries. Reinforcement learning has been previously used in the context of traditional multi-document summarization as a means of selecting a sentence or a subset of sentences from a document cluster. Ryang and Abekawa (2012) cast the sentence selection task as a search problem. Their agent observes ”
BanditSum: Extractive Summarization as a Contextual Bandit (2018, methodology): “The use of reinforcement learning (RL) in extractive summarization was ﬁrst explored by Ryang and Abekawa (2012), who proposed to use the TD( λ ) algorithm to learn a value function for sentence selection.”
Quark: Controllable Text Generation with Reinforced Unlearning (2022, background): “Recent works have explored applying RL on tasks such as question-answering [85, 86, 48, 84, 85], summarization [59, 54, 71, 61, 17, 52], and machine translation [59, 88, 80, 83, 82, 13, 67, 5, 50].”
Fear the REAPER: A System for Automatic Multi-Document Summarization with Reinforcement Learning (2014, methodology): “We ﬁrst evaluate our systems using the DUC2004 dataset for comparison with the results in Ryang and Abekawa (2012).”
APRIL: Interactively Learning to Summarise by Combining Active Preference Learning and Reinforcement Learning (2018, methodology): “Ryang and Abekawa (2012) formulated EMDS as a Markov Decision Process (MDP), designed a heuristics-based reward function considering both information coverage rate and redundancy level, and used the Temporal Difference (TD) algorithm (Sutton, 1984) to solve the MDP.”
Reward Learning for Efficient Reinforcement Learning in Extractive Document Summarisation (2019, methodology): “This explains the poor performance of input-speciﬁc RL summarisers [Ryang and Abekawa, 2012].”
Sentence Simplification with Deep Reinforcement Learning (2017, methodology): “Reinforcement learning has been previously applied to extractive summarization (Ryang and Abekawa, 2012), information extraction (Narasimhan et al., 2016), dialogue generation (Li et al., 2016), machine translation, and image caption generation (Ranzato et al., 2016).”
An Overview of Natural Language State Representation for Reinforcement Learning (2020, methodology): “Initial works applying RL used tuples of features to represent the state, composed of the summary at each time step, a history of actions and a binary variable indicating the terminal state (Ryang & Abekawa, 2012; Rioux et al., 2014; Henß et al., 2015).”
Preference-based interactive multi-document summarisation (2019, methodology): “Most existing RL-based document sum-marisation systems either use heuristic functions (e.g., Ryang and Abekawa 2012; Rioux et al. 2014), which do not rely on reference summaries, or ROUGE scores requiring reference summaries as the rewards for RL (Paulus et al. 2017; Pasunuru and Bansal 2018;…”