SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2302.02962 · 2023

LoFT: Enhancing Faithfulness and Diversity for Table-to-Text Generation via Logic Form Control

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 13 functions out of this paper's own repositories and ran 9 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
yale-lily/loft canonical 9 of 13
FunctionStatusWhere it lives
distinct Ran yale-lily/loft/LoFT_evaluation/diversity_metrics.py
code served (permissive licence) · get_code("9a8250b6202d0aaf")
evaluate Ran yale-lily/loft/LoFT_framework/tapex/model_eval.py
code served (permissive licence) · get_code("1b98d89684c0bb11")
extract_orig_inference_dict Ran yale-lily/loft/LoFT_framework/prepare_verifier_input.py
code served (permissive licence) · get_code("e579ce3de5f6f366")
extract_structure_data Ran yale-lily/loft/LoFT_framework/tapex/model_eval.py
code served (permissive licence) · get_code("665139839a94ca8f")
func_compute_bleu Ran yale-lily/loft/LoFT_evaluation/diversity_metrics.py
code served (permissive licence) · get_code("0771747dc8451c0b")
logicnlg_evaluate Ran yale-lily/loft/LoFT_framework/tapex/model_eval.py
code served (permissive licence) · get_code("8d1d37d893efe52b")
read_seqs Ran yale-lily/loft/LoFT_evaluation/diversity_metrics.py
code served (permissive licence) · get_code("56e06b573ddd7ba3")
read_verifier_output Ran yale-lily/loft/LoFT_framework/prepare_evaluation_data.py
code served (permissive licence) · get_code("aeef32be08be0770")
sample_output_for_logicnlg_evaluation Ran yale-lily/loft/LoFT_framework/prepare_evaluation_data.py
code served (permissive licence) · get_code("ea85ef1c2133c936")
build_abstract_tree Not yet run yale-lily/loft/LoFT_data_processing/inference/modules/templatize.py
code served (permissive licence) · get_code("9e349ec94a8be51d")
create_templates_single Not yet run yale-lily/loft/LoFT_data_processing/inference/modules/templatize.py
code served (permissive licence) · get_code("ec9b4f078e421bab")
extract_structure_data Not yet run yale-lily/loft/LoFT_framework/prepare_verifier_input.py
code served (permissive licence) · get_code("cae89a129d9d6aa3")
prepare_tapex_evaluation_data Not yet run yale-lily/loft/LoFT_evaluation/prepare_tapex_evaluation_data.py
code served (permissive licence) · get_code("6db7ab7efba8239e")

Repositories linked to this paper

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

Abstract

Logical Table-to-Text (LT2T) generation is tasked with generating logically faithful sentences from tables. There currently exists two challenges in the field: 1) Faithfulness: how to generate sentences that are factually correct given the table content; 2) Diversity: how to generate multiple sentences that offer different perspectives on the table. This work proposes LoFT, which utilizes logic forms as fact verifiers and content planners to control LT2T generation. Experimental results on the LogicNLG dataset demonstrate that LoFT is the first model that addresses unfaithfulness and lack of diversity issues simultaneously. Our code is publicly available at https://github.com/Yale-LILY/LoFT.

For agents

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

get_harvested_code_for_paper("2302.02962")
get_code_for_paper("2302.02962")
have("2302.02962")

Connect an agent — have() is free.