paper-with-me

Papers

Scientific Statement Classification over arXiv.org

2019-08-29 · LREC 2020 5 · Deyan Ginev, Bruce R. Miller

We introduce a new classification task for scientific statements and release a large-scale dataset for supervised learning. Our resource is derived from a machine-readable representation of the arXiv.org collection of preprint articles. We explore fifty author-annotated categories and empirically motivate a task design of grouping 10.5 million annotated paragraphs into thirteen classes. We demonstrate that the task setup aligns with known success rates from the state of the art, peaking at a 0.91 F1-score via a BiLSTM encoder-decoder model. Additionally, we introduce a lexeme serialization for mathematical formulas, and observe that context-aware models could improve when also trained on the symbolic modality. Finally, we discuss the limitations of both data and task design, and outline potential directions towards increasingly complex models of scientific discourse, beyond isolated statements.

📄 PDF Abstract BibTeX arXiv:1908.10993

Code (6)

dginev/arxiv-statement-classification 공식 구현 tf
dginev/showcase-statement-classification 공식 구현 tf
dginev/arxiv-ams-env-bilstm tf
dginev/arxiv-ams-paragraph-classification tf
dginev/dginev
dginev/web-scipara-demo tf

Tasks

ArticlesDecoderGeneral Classification

Methods 이 논문이 사용한 방법론

Sigmoid Activation 설명 없음
Tanh Activation 설명 없음
LSTM An LSTM is a type of recurrent neural network that addresses the vanishing gradient problem in vanilla…
BiLSTM A Bidirectional LSTM, or biLSTM, is a sequence processing model that consists of two LSTMs: one taking the input in a forward direction, and the other in a backwards…

Similar Papers 제목 키워드 기반

Reply to 'Comments on Graphon Signal Processing' [arXiv:2310.14683]

2024-01-05 · Luana Ruiz, Luiz F. O. Chamon, Alejandro Ribeiro

This technical note addresses an issue [arXiv:2310.14683] with the proof (but not the statement) of [arXiv:2003.05030, Proposition 4]. The statement of the proposition is correct, but the proof as written in [arXiv:2003.…

LEMMAvalid

Multimodal ArXiv: A Dataset for Improving Scientific Comprehension of Large Vision-Language Models

2024-03-01 · Lei LI, Yuqi Wang, Runxin Xu, Peiyi Wang 외

Large vision-language models (LVLMs) excel across diverse tasks involving concrete images from natural scenes. However, their ability to interpret abstract figures, such as geometry shapes and scientific plots, remains l…

BenchmarkingMathematical ReasoningQuestion Answering

arXivEdits: Understanding the Human Revision Process in Scientific Writing

2022-10-26 · Chao Jiang, Wei Xu, Samuel Stevens

Scientific publications are the primary means to communicate research discoveries, where the writing quality is of crucial importance. However, prior work studying the human editing process in this domain mainly focused …

intent-classificationIntent ClassificationSentence

On the Use of ArXiv as a Dataset

2019-04-30 · Colin B. Clement, Matthew Bierbaum, Kevin P. O'Keeffe, Alexander A. Alemi

The arXiv has collected 1.5 million pre-print articles over 28 years, hosting literature from scientific fields including Physics, Mathematics, and Computer Science. Each pre-print features text, figures, authors, citati…

ArticlesAuthor AttributionBenchmarkingInformation Retrieval+8

Automated Statement Extraction from Press Briefings

2023-02-23 · Jüri Keller, Meik Bittkowski, Philipp Schaer

Scientific press briefings are a valuable information source. They consist of alternating expert speeches, questions from the audience and their answers. Therefore, they can contribute to scientific and fact-based media …