SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2108.02866 · ACL · 2021

Dual Reader-Parser on Hybrid Textual and Tabular Evidence for Open Domain Question Answering

Peng Xu, Alexander Li, Patrick Ng

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 7 functions out of this paper's own repositories and ran 1 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
awslabs/durepa-hybrid-qa canonical 1 of 7
FunctionStatusWhere it lives
trim_batch Ran awslabs/durepa-hybrid-qa/src/utils.py
code served (permissive licence) · get_code("eeb8dc60c6ef1fa4")
convert_examples_to_features Not yet run awslabs/durepa-hybrid-qa/src/utils_data.py
code served (permissive licence) · get_code("d740ff30dac46329")
convert_examples_to_features Not yet run awslabs/durepa-hybrid-qa/src/utils_fusion_in_decoder.py
code served (permissive licence) · get_code("9873b974777295b8")
convert_examples_to_features Not yet run awslabs/durepa-hybrid-qa/utils_ranking.py
code served (permissive licence) · get_code("8a50439c11aef377")
convert_examples_to_features_inference Not yet run awslabs/durepa-hybrid-qa/utils_ranking.py
code served (permissive licence) · get_code("9018ea848be77cce")
encode_file Not yet run awslabs/durepa-hybrid-qa/src/utils.py
code served (permissive licence) · get_code("f34974647bd20936")
lmap Not yet run awslabs/durepa-hybrid-qa/src/utils.py
code served (permissive licence) · get_code("e8f0c6a01a6823df")

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 state-of-the-art generative models for open-domain question answering (ODQA) have focused on generating direct answers from unstructured textual information. However, a large amount of world's knowledge is stored in structured databases, and need to be accessed using query languages such as SQL. Furthermore, query languages can answer questions that require complex reasoning, as well as offering full explainability. In this paper, we propose a hybrid framework that takes both textual and tabular evidence as input and generates either direct answers or SQL queries depending on which form could better answer the question. The generated SQL queries can then be executed on the associated databases to obtain the final answers. To the best of our knowledge, this is the first paper that applies Text2SQL to ODQA tasks. Empirically, we demonstrate that on several ODQA datasets, the hybrid methods consistently outperforms the baseline models that only take homogeneous input by a large margin. Specifically we achieve state-of-theart performance on OpenSQuAD dataset using a T5-base model. In a detailed analysis, we demonstrate that the being able to generate structural SQL queries can always bring gains, especially for those questions that requires complex reasoning.

For agents

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

get_harvested_code_for_paper("2108.02866")
get_code_for_paper("2108.02866")
have("2108.02866")

Connect an agent — have() is free.