Peng Xu, Alexander Li, Patrick Ng
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.
| Repository | Role | Ran |
|---|---|---|
| awslabs/durepa-hybrid-qa | canonical | 1 of 7 |
| Function | Status | Where 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") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
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.
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.