SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2104.06828 · NAACL · 2021

Ask what's missing and what's useful: Improving Clarification Question Generation using Global Knowledge

Julian Mcauley, Michel Galley, Bodhisattwa Prasad Majumder, Sudha Rao

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 14 functions out of this paper's own repositories and ran 8 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
microsoft/clarification-qgen-globalinfo canonical 8 of 14
FunctionStatusWhere it lives
build_schema_from_desc Ran microsoft/clarification-qgen-globalinfo/amazon/get_schema.py
code served (permissive licence) · get_code("305f91dc9ae7c818")
build_schema_from_table Ran microsoft/clarification-qgen-globalinfo/amazon/get_schema.py
code served (permissive licence) · get_code("6ded62d9787204e8")
clean_html Ran microsoft/clarification-qgen-globalinfo/amazon/baselines/create_seq2seq_data.py
code served (permissive licence) · get_code("50991f7e06d740d2")
clf_predict Ran microsoft/clarification-qgen-globalinfo/amazon/predict_usefulness_score.py
code served (permissive licence) · get_code("ceae444d11bd25e4")
feedfoward_regr_model Ran microsoft/clarification-qgen-globalinfo/amazon/question_ranker.py
code served (permissive licence) · get_code("1840a84c3d80a3fa")
getDF Ran microsoft/clarification-qgen-globalinfo/amazon/create_split.py
code served (permissive licence) · get_code("ccc731d1ce007e01")
load_glove_vectors Ran microsoft/clarification-qgen-globalinfo/amazon/global_schema_utils.py
code served (permissive licence) · get_code("a38422b38b0a22c7")
svr_model Ran microsoft/clarification-qgen-globalinfo/amazon/question_ranker.py
code served (permissive licence) · get_code("bb028603164d4abd")
build_schema Not yet run microsoft/clarification-qgen-globalinfo/amazon/get_schema.py
code served (permissive licence) · get_code("1922d68fd519cffa")
create_keyword_embs Not yet run microsoft/clarification-qgen-globalinfo/amazon/global_schema_utils.py
code served (permissive licence) · get_code("8fa821a1e0e2be65")
get_glove_vector Not yet run microsoft/clarification-qgen-globalinfo/amazon/predict_usefulness_score.py
code served (permissive licence) · get_code("82bd4d8fb1a2c5b5")
get_glove_vector Not yet run microsoft/clarification-qgen-globalinfo/amazon/global_schema_utils.py
code served (permissive licence) · get_code("139874e879dde9b0")
svc_model Not yet run microsoft/clarification-qgen-globalinfo/amazon/question_ranker.py
code served (permissive licence) · get_code("78054b6fc43b80d3")
svc_model_predict Not yet run microsoft/clarification-qgen-globalinfo/amazon/predict_usefulness_score.py
code served (permissive licence) · get_code("0091bc81c2e128ca")

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 ability to generate clarification questions i.e., questions that identify useful missing information in a given context, is important in reducing ambiguity. Humans use previous experience with similar contexts to form a global view and compare it to the given context to ascertain what is missing and what is useful in the context. Inspired by this, we propose a model for clarification question generation where we first identify what is missing by taking a difference between the global and the local view and then train a model to identify what is useful and generate a question about it. Our model outperforms several baselines as judged by both automatic metrics and humans.

For agents

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

get_harvested_code_for_paper("2104.06828")
get_code_for_paper("2104.06828")
have("2104.06828")

Connect an agent — have() is free.