Papers by Oleksandr Polozov
Learning Web-based Procedures by Reasoning over Explanations and Demonstrations in Context (2020.acl-main)
Copied to clipboard
| Challenge: | a new direction for semantic parsing that models explanations to demonstrations is proposed . bottom-up approach to generating logical forms is complicated in domains with rich composition . |
| Approach: | They propose a new direction for semantic parsing that models explanations in a context . they use inverse semantics to reason backwards from observed demonstrations . |
| Outcome: | The proposed approach shows better task completion rates than a baseline method . it is competitive with exploration-and-demonstration based methods, but requires no exploration of environment . |
KaggleDBQA: Realistic Evaluation of Text-to-SQL Parsers (2021.acl-long)
Copied to clipboard
| Challenge: | Recent large-scale datasets such as Spider and WikiSQL facilitated novel modeling techniques for text-to-SQl parsing. |
| Approach: | They propose a new cross-domain evaluation dataset of real Web databases . they examine the choice of evaluation tasks for text-to-SQL parsers . |
| Outcome: | The proposed model improves accuracy by 13.2% over state-of-the-art parsers in real-life environments. |
Structure-Grounded Pretraining for Text-to-SQL (2021.naacl-main)
Copied to clipboard
Xiang Deng, Ahmed Hassan Awadallah, Christopher Meek, Oleksandr Polozov, Huan Sun, Matthew Richardson
| Challenge: | STRUG is a weakly supervised structure-based pretraining framework for text-to-SQL . it can be used to learn to capture text-table alignment in a given database schema . |
| Approach: | They propose a weakly supervised structure-grounded pretraining framework for text-to-SQL that can effectively learn to capture text-table alignment based on a parallel text-tab corpus. |
| Outcome: | The proposed framework outperforms BERTLARGE and BERTLAGE on all text-to-SQL alignment settings. |
Natural Language to Code Generation in Interactive Data Science Notebooks (2023.acl-long)
Copied to clipboard
Pengcheng Yin, Wen-Ding Li, Kefan Xiao, Abhishek Rao, Yeming Wen, Kensen Shi, Joshua Howland, Paige Bailey, Michele Catasta, Henryk Michalewski, Oleksandr Polozov, Charles Sutton
| Challenge: | Data scientists use computational notebooks to perform data wrangling and analytic tasks. |
| Approach: | They build a benchmark program that synthesizes programs given NL intents from users by using a Python code language model. |
| Outcome: | The proposed model outperforms public code LMs in a dataset of 1078 code generation problems using the pandas data analysis framework in data science notebooks. |
RAT-SQL: Relation-Aware Schema Encoding and Linking for Text-to-SQL Parsers (2020.acl-main)
Copied to clipboard
| Challenge: | Existing semantic parsing models struggle to generalize to unseen database schemas. |
| Approach: | They propose a framework to address schema encoding, schema linking, and feature representation within a text-to-SQL encoder. |
| Outcome: | The proposed framework boosts the match accuracy to 57.2% on the spider dataset, surpassing its best counterparts by 8.7%. |