SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2407.14309 · ACL · 2024

How to Engage Your Readers?

Peng Cui, Mrinmaya Sachan, Xiaoyu Zhang, Vilém Zouhar

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 11 functions out of this paper's own repositories and ran 10 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
eth-lre/engage-your-readers canonical 10 of 11
FunctionStatusWhere it lives
factory_extract_likert Ran eth-lre/engage-your-readers/analysis/scripts_main/02-avg_quantitative.py
pointer only (licence: NONE) · get_code("7790b46b4d15c025")
factory_get_question_likert Ran eth-lre/engage-your-readers/analysis/scripts_main/02-avg_quantitative.py
pointer only (licence: NONE) · get_code("e990969e3fc2b479")
load_by_user Ran eth-lre/engage-your-readers/analysis/loader.py
pointer only (licence: NONE) · get_code("0c677c8251816be1")
load_by_user_prolific Ran eth-lre/engage-your-readers/analysis/loader.py
pointer only (licence: NONE) · get_code("45565769a4732963")
merge_list Ran eth-lre/engage-your-readers/src/common_utils.py
pointer only (licence: NONE) · get_code("47323200b80f2432")
my_collate Ran eth-lre/engage-your-readers/src/build_data.py
pointer only (licence: NONE) · get_code("5c8d7e5c7eec809d")
parse_output Ran eth-lre/engage-your-readers/src/common_utils.py
pointer only (licence: NONE) · get_code("17f5a8d5d5701f52")
remove_dup Ran eth-lre/engage-your-readers/src/evaluation.py
pointer only (licence: NONE) · get_code("5fbb544ef6e03a0b")
uid_to_group Ran eth-lre/engage-your-readers/analysis/scripts_main/02-avg_quantitative.py
pointer only (licence: NONE) · get_code("590f409e37d1d416")
uid_to_group Ran eth-lre/engage-your-readers/analysis/scripts_xiaoyu/02-avg_quantitative.py
pointer only (licence: NONE) · get_code("8b59243162da2669")
map_back Not yet run eth-lre/engage-your-readers/src/common_utils.py
pointer only (licence: NONE) · get_code("9f0e5dc3876be6ac")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Using questions in written text is an effective strategy to enhance readability. However, what makes an active reading question good, what the linguistic role of these questions is, and what is their impact on human reading remains understudied. We introduce GUIDINGQ, a dataset of 10K in-text questions from textbooks and scientific articles. By analyzing the dataset, we present a comprehensive understanding of the use, distribution, and linguistic characteristics of these questions. Then, we explore various approaches to generate such questions using language models. Our results highlight the importance of capturing inter-question relationships and the challenge of question position identification in generating these questions. Finally, we conduct a human study to understand the implication of such questions on reading comprehension. We find that the generated questions are of high quality and are almost as effective as human-written questions in terms of improving readers' memorization and comprehension. github.com/eth-lre/engage-your-readers How do Philosophers arrive at truth? Is there no quantum form of Einstein Gravity? Why do house-hunting ants recruit in both directions?

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2407.14309")
get_code_for_paper("2407.14309")
have("2407.14309")

Connect an agent — have() is free.