Augmenting Scientific Papers with Just-in-Time, Position-Sensitive Definitions of Terms and Symbols

@article{Head2020AugmentingSP,
  title={Augmenting Scientific Papers with Just-in-Time, Position-Sensitive Definitions of Terms and Symbols},
  author={Andrew Head and Kyle Lo and Dongyeop Kang and Raymond Fok and Sam Skjonsberg and Daniel S. Weld and Marti A. Hearst},
  journal={Proceedings of the 2021 CHI Conference on Human Factors in Computing Systems},
  year={2020},
  url={https://api.semanticscholar.org/CorpusID:222066998}
}
This work introduces ScholarPhi, an augmented reading interface with four novel features: tooltips that surface position-sensitive definitions from elsewhere in a paper, a filter over the paper that “declutters” it to reveal how the term or symbol is used across the paper, automatic equation diagrams that expose multiple definitions in parallel, and an automatically generated glossary of important terms and symbols.
View on ACM
[PDF] Semantic Reader

Figures and Tables from this paper

106 Citations

CiteRead: Integrating Localized Citation Contexts into Scientific Paper Reading

A novel paper reading experience that integrates relevant information about follow-on work directly into a paper, allowing readers to learn about newer papers and see how a paper is discussed by its citing papers in the context of the reference paper.

H❤️rtDown: Document Processor for Executable Linear Algebra Papers

H❤️rtDown is a document processor, authoring environment, and paper reading environment for scientific documents, designed to support existing scientific writing practices: editing in plain text, using and defining symbols in prose-determined order, and context-dependent symbol re-use.

i-LaTeX : Manipulating Transitional Representations between LaTeX Code and Generated Documents

i-LaTeX is presented, a LaTeX editor equipped with Transitional Representations of formulae, tables, images, and grid layouts, and a 16-participant experiment shows that Transitionalrepresentations let them complete common editing tasks significantly faster, with fewer compilations, and with a lower workload.

TreeReader: A Hierarchical Academic Paper Reader Powered by Language Models

TreeReader decomposes papers into an interactive tree structure where each section is initially represented by an LLM-generated concise summary, with underlying details accessible on demand, allowing users to quickly grasp core ideas, selectively explore sections of interest, and verify summaries against the source text.

Scim: Intelligent Faceted Highlights for Interactive, Multi-Pass Skimming of Scientific Papers

Scim is presented, an AI-augmented reading interface designed to help researchers skim papers by automatically identifying, classifying, and highlighting salient sentences, organized into rhetorical facets rooted in common information needs.

The Semantic Reader Project

The Semantic Reader Project is described, a collaborative effort across multiple institutions to explore automatic creation of dynamic reading interfaces for research papers, and a collection of novel reading interfaces are developed and evaluated and evaluated them with study participants and real-world users to show improved reading experiences for scholars.

Document-Level Definition Detection in Scholarly Documents: Existing Models, Error Analyses, and Future Directions

This paper develops a new definition detection system, HEDDEx, that utilizes syntactic features, transformer encoders, and heuristic filters, and evaluates it on a standard sentence-level benchmark and notes that performance on the high-recall document-level task is much lower than in the standard evaluation approach.

Contextualized Programming Language Documentation

A system is described that automatically generates contextualized language documentation, structured based on the study of language documentation but specialized to the particular code at the cursor, integrated into the structure editor of Hazel, a live functional environment.

Qlarify: Recursively Expandable Abstracts for Dynamic Information Retrieval over Scientific Papers

Recursively expandable abstracts are introduced, a novel interaction paradigm that dynamically expands abstracts by progressively incorporating additional information from the papers’ full text during their dive into the full text.

ReaderQuizzer: Augmenting Research Papers with Just-In-Time Learning Questions to Facilitate Deeper Understanding

Academic reading is a key component of higher education, and serves as a basis for critical thinking, knowledge acquisition and effective communication. Research shows many students struggle with…
...

119 References

Document-Level Definition Detection in Scholarly Documents: Existing Models, Error Analyses, and Future Directions

This paper develops a new definition detection system, HEDDEx, that utilizes syntactic features, transformer encoders, and heuristic filters, and evaluates it on a standard sentence-level benchmark and notes that performance on the high-recall document-level task is much lower than in the standard evaluation approach.

Beyond paper: supporting active reading with free form digital ink annotations

The XLibris “active reading machine” demonstrates that computers can help active readers organize and find information while retaining many of the advantages of reading on paper.

Mathematical Language Processing Project

Two approaches to discover identifier-definition tuples are compared and a simple pattern matching approach is used and a approach that uses part-of-speech tag based distances as well as sentence positions to calculate identifier- definition probabilities is presented.

PaperQuest: A Visualization Tool to Support Literature Review

PaperQuest is presented, a visualization tool that supports efficient reading decisions, by only displaying the information useful at a given step of the review, in order to find and sort papers that are likely to be relevant to users.

SideNoter: Scholarly Paper Browsing System based on PDF Restructuring and Text Annotation

This system provides ways to extract natural language sentences from PDF files together with their logical structures, and also to map arbitrary textual spans to their corresponding regions on page images, and is planned to make widely available to NLP researchers.

The reader's helper: a personalized document reading environment

A anew document reading environment is introduced called the Readers HelperTM, which supports the reading of electronic and paper documents and produces arelevance score for each of the readers topics of interest, thereby helping the reader decide whether the document is actually worthskimming or reading.

Elastic Documents: Coupling Text and Tables through Contextual Visualizations for Enhanced Document Reading

This paper parse the text content and data tables, cross-link the components using a keyword-based matching algorithm, and generate on-demand visualizations based on the reader's current focus within a document that couples text content with data tables contained in the document.

Mining Scientific Terms and their Definitions: A Study of the ACL Anthology

DefMiner is presented, a supervised sequence labeling system that identifies scientific terms and their accompanying definitions and achieves 85% F1 on a Wikipedia benchmark corpus, significantly improving the previous state-of-the-art by 8%.

Stencils-based tutorials: design and evaluation

Stencils, an interaction technique for presenting tutorials that uses translucent colored stencils containing holes that direct the user's attention to the correct interface component and prevent the user from interacting with other components, is introduced.

Hypertext: An Introduction and Survey

A survey of existing hypertext systems, their applications, and their design is both an introduction to the world of hypertext and a survey of some of the most important design issues that go into fashioning a hypertext environment.
...