PaperRobot: Incremental Draft Generation of Scientific Ideas

@article{Wang2019PaperRobotID,
  title={PaperRobot: Incremental Draft Generation of Scientific Ideas},
  author={Qingyun Wang and Lifu Huang and Zhiying Jiang and Kevin Knight and Heng Ji and Mohit Bansal and Yi Luan},
  journal={ArXiv},
  year={2019},
  volume={abs/1905.07870}
}
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 comprehensive background knowledge graphs (KGs); (2) creating new ideas by predicting links from the background KGs, by combining graph attention and contextual text attention; (3) incrementally writing some key elements of a new paper based on memory-attention networks: from the input title along with… Expand
How to Train Your Agent to Read and Write
TLDR
A Deep ReAder-Writer (DRAW) network, which consists of a Reader that can extract knowledge graphs from input paragraphs and discover potential knowledge, a graph-to-text Writer that generates a novel paragraph, and a Reviewer that reviews the generated paragraph from three different aspects. Expand
SciXGen: A Scientific Paper Dataset for Context-Aware Text Generation
TLDR
This work presents a novel challenging largescale Scientific Paper Dataset for ConteXtAware Text Generation (SciXGen), consisting of well-annotated 205,304 papers with full references to widely-used objects in a paper, aiming at exploiting the contributions of context in generated texts. Expand
Scientific Text Mining and Knowledge Graphs
TLDR
This tutorial introduces a series of text mining methods that extract phrases, entities, scientific concepts, relations, claims, and experimental evidence and focuses on scalable, effective, weakly supervised methods that work on text in sciences (e.g., chemistry, biology). Expand
CODA-19: Reliably Annotating Research Aspects on 10,000+ CORD-19 Abstracts Using a Non-Expert Crowd
TLDR
It is demonstrated that a non-expert crowd can be rapidly employed at scale to join the fight against COVID-19, a human-annotated dataset that codes the Background, Purpose, Method, Finding/Contribution, and Other sections of 10,966 English abstracts in the CO VID-19 Open Research Dataset. Expand
Predicting research trends with semantic and neural networks with an application in quantum physics
TLDR
The development of a semantic network for quantum physics, denoted SemNet, is demonstrated using 750,000 scientific papers and knowledge from books and Wikipedia, which is used to predict future trends in research and to inspire personalized and surprising seeds of ideas in science. Expand
Neural Language Generation: Formulation, Methods, and Evaluation
TLDR
There is no standard way to assess the quality of text produced by these generative models, which constitutes a serious bottleneck towards the progress of the field, so this survey will provide an informative overview of formulations, methods, and assessments of neural natural language generation. Expand
GAIA: A Fine-grained Multimedia Knowledge Extraction System
TLDR
The system, GAIA, enables seamless search of complex graph queries, and retrieves multimedia evidence including text, images and videos, and achieves top performance at the recent NIST TAC SM-KBP2019 evaluation. Expand
Sentence-Permuted Paragraph Generation
TLDR
A novel framework PermGen is proposed whose objective is to maximize the expected log-likelihood of output paragraph distributions with respect to all possible sentence orders to improve the content diversity of multi-sentence paragraph. Expand
PatentMiner: Patent Vacancy Mining via Context-enhanced and Knowledge-guided Graph Attention
  • Gaochen Wu, Bin Xu, +4 authors Dejie Chang
  • Computer Science
  • Knowledge Graph and Semantic Computing: Knowledge Graph Empowers New Infrastructure Construction
  • 2021
TLDR
A new patent vacancy prediction approach named PatentMiner is proposed to mine rich semantic knowledge and predict new potential patents based on knowledge graph (KG) and graph attention mechanism to mine hidden rich semantic relationships in existing patents and predictnew possible patents. Expand
BOLD: Dataset and Metrics for Measuring Biases in Open-Ended Language Generation
TLDR
To systematically study and benchmark social biases in open-ended language generation, the Bias in Open-Ended Language Generation Dataset (BOLD) is introduced, a large-scale dataset that consists of 23,679 English text generation prompts for bias benchmarking across five domains: profession, gender, race, religion, and political ideology. Expand
...
1
2
3
...

References

SHOWING 1-10 OF 65 REFERENCES
Paper Abstract Writing through Editing Mechanism
We present a paper abstract writing system based on an attentive neural sequence-to-sequence model that can take a title as input and automatically generate an abstract. We design a novelExpand
Describing a Knowledge Base
TLDR
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. Expand
Order-Planning Neural Text Generation From Structured Data
TLDR
This paper proposes an order-planning text generation model to capture the relationship between different fields and use such relationship to make the generated text more fluent and smooth. Expand
Learning to Generate Posters of Scientific Papers
TLDR
A data-driven framework, that utilizes graphical models, is proposed, that learns and inferred the key elements of a good poster, including panel layout and attributes of each panel, are learned and inferred from data. 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
Guided Neural Language Generation for Abstractive Summarization using Abstract Meaning Representation
TLDR
This paper extends previous work on abstractive summarization using Abstract Meaning Representation with a neural language generation stage which is guide using the source document and improves summarization results by 7.4 and 10.5 points in ROUGE-2 using gold standard AMR parses and parses obtained from an off-the-shelf parser respectively. Expand
A Global Model for Concept-to-Text Generation
TLDR
A joint model that captures content selection and surface realization in an unsupervised domain-independent fashion is presented and an algorithm for decoding is described that allows to intersect the grammar with additional information capturing fluency and syntactic well-formedness constraints. Expand
Generation from Abstract Meaning Representation using Tree Transducers
TLDR
This paper addresses generating English from the Abstract Meaning Representation (AMR), consisting of re-entrant graphs whose nodes are concepts and edges are relations, and consists of generating an appropriate spanning tree for the AMR and applying tree-tostring transducers to generate English. Expand
Neural Text Generation from Structured Data with Application to the Biography Domain
TLDR
A neural model for concept-to-text generation that scales to large, rich domains and significantly out-performs a classical Kneser-Ney language model adapted to this task by nearly 15 BLEU is introduced. Expand
Text-Enhanced Representation Learning for Knowledge Graph
TLDR
The rich textual context information in a text corpus is incorporated to expand the semantic structure of the knowledge graph and each relation is enabled to own different representations for different head and tail entities to better handle 1-to-N, N- to-1 and N-To-N relations. Expand
...
1
2
3
4
5
...