SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2104.04243 · NAACL · 2021

Incorporating External Knowledge to Enhance Tabular Reasoning

Vivek Gupta, Vivek Srikumar, J Neeraja

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 7 functions out of this paper's own repositories and ran 5 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
utahnlp/knowledge_infotabs canonical 5 of 7
FunctionStatusWhere it lives
category_from_keys Ran utahnlp/knowledge_infotabs/scripts/kg_extraction/extract_kg.py
code served (permissive licence) · get_code("f1eba1b799b61e7c")
compute_alignment_vector Ran utahnlp/knowledge_infotabs/scripts/preprocess/drr.py
code served (permissive licence) · get_code("209c9374be821542")
is_date Ran utahnlp/knowledge_infotabs/scripts/preprocess/bpr.py
code served (permissive licence) · get_code("682529bf0fda02fd")
sent_Emb Ran utahnlp/knowledge_infotabs/scripts/preprocess/drr.py
code served (permissive licence) · get_code("ee66d9592ac77597")
template Ran utahnlp/knowledge_infotabs/scripts/kg_extraction/extract_kg.py
code served (permissive licence) · get_code("3f5f061a6f930831")
Preprocess_QA_sentences Not yet run utahnlp/knowledge_infotabs/scripts/preprocess/drr.py
code served (permissive licence) · get_code("4f609f1d33e00926")
table_to_para Not yet run utahnlp/knowledge_infotabs/scripts/preprocess/bpr.py
code served (permissive licence) · get_code("8df7faae1ab29442")

Repositories linked to this paper

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

Abstract

Reasoning about tabular information presents unique challenges to modern NLP approaches which largely rely on pre-trained contextualized embeddings of text. In this paper, we study these challenges through the problem of tabular natural language inference. We propose easy and effective modifications to how information is presented to a model for this task. We show via systematic experiments that these strategies substantially improve tabular inference performance.

For agents

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

get_harvested_code_for_paper("2104.04243")
get_code_for_paper("2104.04243")
have("2104.04243")

Connect an agent — have() is free.