• Corpus ID: 222310232

ReviewRobot: Explainable Paper Review Generation based on Knowledge Synthesis

  title={ReviewRobot: Explainable Paper Review Generation based on Knowledge Synthesis},
  author={Qingyun Wang and Qi Zeng and Lifu Huang and Kevin Knight and Heng Ji and Nazneen Rajani},
To assist human review process, we build a novel ReviewRobot to automatically assign a review score and write comments for multiple categories such as novelty and meaningful comparison. A good review needs to be knowledgeable, namely that the comments should be constructive and informative to help improve the paper; and explainable by providing detailed evidence. ReviewRobot achieves these goals via three steps: (1) We perform domain-specific Information Extraction to construct a knowledge… 

Figures and Tables from this paper

Can We Automate Scientific Reviewing?
Comprehensive experimental results show that system-generated reviews tend to touch upon more aspects of the paper than human-written reviews, but the generated text can suffer from lower constructiveness for all aspects except the explanation of the core ideas of the papers, which are largely factually correct.
Controllable and Diverse Text Generation in E-commerce
A fine-grained controllable generative model that uses an algorithm borrowed from automatic control to precisely manipulate the diversity/accuracy trade-off of generated text and outperforms existing generative models in terms of diversity and relevance.
Automated scholarly paper review: Possibility and challenges
This review paper proposes the concept of automated scholarly paper review (ASPR) and reviews the relevant literature and technologies to discuss the possibility of achieving a full-scale computerized review process and concludes there are already corresponding research and technologies at each stage of ASPR.
Determining the Credibility of Science Communication
Some first steps towards addressing problems of ensuring that scientific publications are credible and that scientific findings are not misrepresented, distorted or outright misreported when communicated by journalists or the general public are presented.
Human Evaluation of Creative NLG Systems: An Interdisciplinary Survey on Recent Papers
These guidelines for future evaluation include clearly defining the goal of the generative system, asking questions as concrete as possible, testing the evaluation setup, using multiple different evaluation setups, reporting the entire evaluation process and potential biases clearly, and finally analyzing the evaluation results in a more profound way than merely reporting the most typical statistics.
We Can Explain Your Research in Layman's Terms: Towards Automating Science Journalism at Scale
This work creates a specialized dataset that contains scientific papers and their Science Daily press releases, and demonstrates numerous sequence to sequence (seq2seq) applications using Science Daily with the aim of facilitating further research on language generation.


PaperRobot: Incremental Draft Generation of Scientific Ideas
We present a PaperRobot who performs as an automatic research assistant by (1) conducting deep understanding of a large collection of human-written papers in a target domain and constructing
Unsupervised Opinion Summarization as Copycat-Review Generation
A generative model for a review collection is defined which capitalizes on the intuition that when generating a new review given a set of other reviews of a product, the authors should be able to control the “amount of novelty” going into the new review or, equivalently, vary the extent to which it deviates from the input.
Describing a Knowledge Base
This work builds a generation framework based on a pointer network which can copy facts from the input KB, and adds two attention mechanisms: (i) slot-aware attention to capture the association between a slot type and its corresponding slot value; and (ii) a new table position self-attention to captured the inter-dependencies among related slots.
Knowledge Aware Conversation Generation with Explainable Reasoning over Augmented Graphs
This work proposes a knowledge aware chatting machine with three components, an augmented knowledge graph with both triples and texts, knowledge selector, and knowledge aware response generator, and improves a state of the art reasoning algorithm with machine reading comprehension technology for knowledge selection on the graph.
Commonsense Knowledge Aware Conversation Generation with Graph Attention
This is the first attempt that uses large-scale commonsense knowledge in conversation generation, and unlike existing models that use knowledge triples (entities) separately and independently, this model treats each knowledge graph as a whole, which encodes more structured, connected semantic information in the graphs.
An Entity-Driven Framework for Abstractive Summarization
SENECA is introduced, a novel System for ENtity-drivEn Coherent Abstractive summarization framework that leverages entity information to generate informative and coherent abstracts and significantly outperforms previous state-of-the-art based on ROUGE and proposed coherence measures on New York Times and CNN/Daily Mail datasets.
A Dataset of Peer Reviews (PeerRead): Collection, Insights and NLP Applications
The first public dataset of scientific peer reviews available for research purposes (PeerRead v1) is presented and it is shown that simple models can predict whether a paper is accepted with up to 21% error reduction compared to the majority baseline.
Personalized Review Generation By Expanding Phrases and Attending on Aspect-Aware Representations
Experimental results show that the model successfully learns representations capable of generating coherent and diverse reviews and discover those aspects that users are more inclined to discuss and bias the generated text toward their personalized aspect preferences.
Knowledge Graph-Augmented Abstractive Summarization with Semantic-Driven Cloze Reward
ASGARD is presented, a novel framework for Abstractive Summarization with Graph-Augmentation and semantic-driven RewarD, and proposes the use of dual encoders—a sequential document encoder and a graph-structured encoder—to maintain the global context and local characteristics of entities, complementing each other.
TLDR: Extreme Summarization of Scientific Documents
This work introduces SCITLDR, a new multi-target dataset of 5.4K TLDRs over 3.2K papers, and proposes CATTS, a simple yet effective learning strategy for generatingTLDRs that exploits titles as an auxiliary training signal.