Augmenting scientific papers with just-in-time, position-sensitive definitions of terms and symbols

A Head, K Lo, D Kang, R Fok, S Skjonsberg… - Proceedings of the …, 2021 - dl.acm.org
Despite the central importance of research papers to scientific progress, they can be difficult
to read. Comprehension is often stymied when the information needed to understand a …

Lean-star: Learning to interleave thinking and proving

H Lin, Z Sun, Y Yang, S Welleck - arxiv preprint arxiv:2407.10040, 2024 - arxiv.org
Traditional language model-based theorem proving assumes that by training on a sufficient
amount of formal proof data, a model will learn to prove theorems. Our key observation is …

What does this acronym mean? introducing a new dataset for acronym identification and disambiguation

APB Veyseh, F Dernoncourt, QH Tran… - arxiv preprint arxiv …, 2020 - arxiv.org
Acronyms are the short forms of phrases that facilitate conveying lengthy sentences in
documents and serve as one of the mainstays of writing. Due to their importance, identifying …

Naturalproofs: Mathematical theorem proving in natural language

S Welleck, J Liu, RL Bras, H Hajishirzi, Y Choi… - arxiv preprint arxiv …, 2021 - arxiv.org
Understanding and creating mathematics using natural mathematical language-the mixture
of symbolic and natural language used by humans-is a challenging and important problem …

The semantic reader project: Augmenting scholarly documents through ai-powered interactive reading interfaces

K Lo, JC Chang, A Head, J Bragg, AX Zhang… - arxiv preprint arxiv …, 2023 - arxiv.org
Scholarly publications are key to the transfer of knowledge from scholars to others. However,
research papers are information-dense, and as the volume of the scientific literature grows …

Do the math: Making mathematics in wikipedia computable

A Greiner-Petter, M Schubotz… - … on Pattern Analysis …, 2022 - ieeexplore.ieee.org
Wikipedia combines the power of AI solutions and human reviewers to safeguard article
quality. Quality control objectives include detecting malicious edits, fixing typos, and spotting …

Understanding jargon: Combining extraction and generation for definition modeling

J Huang, H Shao, KCC Chang, J **ong… - arxiv preprint arxiv …, 2021 - arxiv.org
Can machines know what twin prime is? From the composition of this phrase, machines may
guess twin prime is a certain kind of prime, but it is still difficult to deduce exactly what twin …

Living papers: A language toolkit for augmented scholarly communication

J Heer, M Conlen, V Devireddy, T Nguyen… - Proceedings of the 36th …, 2023 - dl.acm.org
Computing technology has deeply shaped how academic articles are written and produced,
yet article formats and affordances have changed little over centuries. The status quo …

The Semantic Reader Project

K Lo, JC Chang, A Head, J Bragg, AX Zhang… - Communications of the …, 2024 - dl.acm.org
Scholarly publications are key to the transfer of knowledge from scholars to others. However,
research papers are information-dense, and as the volume of the scientific literature grows …

At-bert: Adversarial training bert for acronym identification winning solution for sdu@ aaai-21

D Zhu, W Lin, Y Zhang, Q Zhong, G Zeng, W Wu… - arxiv preprint arxiv …, 2021 - arxiv.org
Acronym identification focuses on finding the acronyms and the phrases that have been
abbreviated, which is crucial for scientific document understanding tasks. However, the …