SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2104.07242 · NAACL · 2021

Designing a Minimal Retrieve-and-Read System for Open-Domain Question Answering

Sohee Yang, Minjoon Seo

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 5 functions out of this paper's own repositories and ran 4 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
clovaai/minimal-rnr-qa canonical 4 of 5
FunctionStatusWhere it lives
whitespace_tokenize Ran clovaai/minimal-rnr-qa/playground/workspace/minimal_rnr/tfserving/bert_tokenizer/tokenization_bert.py
code served (permissive licence) · get_code("cf9ffa02a42184af")
get_first_matched_file_path Ran clovaai/minimal-rnr-qa/playground/workspace/minimal_rnr/utils/inference.py
code served (permissive licence) · get_code("4f19f0dd0d6275a1")
load_vocab Ran clovaai/minimal-rnr-qa/playground/workspace/minimal_rnr/tfserving/bert_tokenizer/tokenization_bert.py
code served (permissive licence) · get_code("e7fbc7a74a3457c7")
read_txt Ran clovaai/minimal-rnr-qa/playground/workspace/minimal_rnr/utils/inference.py
code served (permissive licence) · get_code("fe09325ee5e2d803")
extend_span_to_full_words Not yet run clovaai/minimal-rnr-qa/playground/workspace/minimal_rnr/utils/inference.py
code served (permissive licence) · get_code("9d264e3b0a582677")

Repositories linked to this paper

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

Abstract

In open-domain question answering (QA), retrieve-and-read mechanism has the inherent benefit of interpretability and the easiness of adding, removing, or editing knowledge compared to the parametric approaches of closedbook QA models. However, it is also known to suffer from its large storage footprint due to its document corpus and index. Here, we discuss several orthogonal strategies to drastically reduce the footprint of a retrieve-andread open-domain QA system by up to 160x. Our results indicate that retrieve-and-read can be a viable option even in a highly constrained serving environment such as edge devices, as we show that it can achieve better accuracy than a purely parametric model with comparable docker-level system size. 1

For agents

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

get_harvested_code_for_paper("2104.07242")
get_code_for_paper("2104.07242")
have("2104.07242")

Connect an agent — have() is free.