SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2203.13602 · NAACL · 2022

ZS4IE: A toolkit for Zero-Shot Information Extraction with simple Verbalizations

Oscar Sainz, Oier Lopez De Lacalle, Eneko Agirre, Haoling Qiu, Bonan Min

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 12 functions out of this paper's own repositories and ran 7 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
BBN-E/ZS4IE canonical 4 of 4
osainz59/Ask2Transformers — 3 of 8
FunctionStatusWhere it lives
apply_threshold Ran osainz59/Ask2Transformers/a2t/tasks/base.py
code served (permissive licence) · get_code("cf39fb09b4f7e706")
f1_score_ Ran osainz59/Ask2Transformers/a2t/tasks/base.py
code served (permissive licence) · get_code("2d43ff1db5ca20c8")
find_optimal_threshold Ran osainz59/Ask2Transformers/a2t/tasks/base.py
code served (permissive licence) · get_code("134e416b45e3ce29")
generate_entity_relation_key Ran BBN-E/ZS4IE/backend/a2t_service_backend.py
code served (permissive licence) · get_code("7d5e6da0f3787e3a")
generate_mention_key Ran BBN-E/ZS4IE/backend/a2t_service_backend.py
code served (permissive licence) · get_code("9f22a50bbb4a17d1")
serifxml_to_string Ran BBN-E/ZS4IE/backend/a2t_service_backend.py
code served (permissive licence) · get_code("7be655036a05fb30")
sigmoid Ran BBN-E/ZS4IE/serif/model/entity_linker.py
code served (permissive licence) · get_code("a590d62785c3fa33")
BinaryFeatures Not yet run osainz59/Ask2Transformers/a2t/tasks/base.py
code served (permissive licence) · get_code("b7800bf465c4ead0")
BinaryTask Not yet run osainz59/Ask2Transformers/a2t/tasks/base.py
code served (permissive licence) · get_code("e26beb437c1b9eca")
Features Not yet run osainz59/Ask2Transformers/a2t/tasks/base.py
code served (permissive licence) · get_code("ac45f0bf994e8aaf")
IncorrectFeatureTypeError Not yet run osainz59/Ask2Transformers/a2t/tasks/base.py
code served (permissive licence) · get_code("0d3c1b57b3dc81b1")
Task Not yet run osainz59/Ask2Transformers/a2t/tasks/base.py
code served (permissive licence) · get_code("c9033c25890f4270")

Repositories linked to this paper

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

Abstract

The current workflow for Information Extraction (IE) analysts involves the definition of the entities/relations of interest and a training corpus with annotated examples. In this demonstration we introduce a new workflow where the analyst directly verbalizes the entities/relations, which are then used by a Textual Entailment model to perform zero-shot IE. We present the design and implementation of a toolkit with a user interface, as well as experiments on four IE tasks that show that the system achieves very good performance at zero-shot learning using only 5-15 minutes per type of a user's effort. Our demonstration system is open-sourced at https:// github.com/BBN-E/ZS4IE. A demonstration video is available at https:// vimeo.com/676138340.

For agents

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

get_harvested_code_for_paper("2203.13602")
get_code_for_paper("2203.13602")
have("2203.13602")

Connect an agent — have() is free.