Semantic Parsing
Semantic Parsing is the task of transducing natural language utterances into formal meaning representations. The target meaning representations can be defined according to a wide variety of formalisms. This include linguistically-motivated semantic representations that are designed to capture the meaning of any sentence such as λ-calculus or the abstract meaning representations. Alternatively, for more task-driven approaches to Semantic Parsing, it is common for meaning representations to represent executable programs such as SQL queries, robotic commands, smart phone instructions, and even general-purpose programming languages like Python and Java.
Source: Tranx: A Transition-based Neural Abstract Syntax Parser for Semantic Parsing and Code Generation
Papers
Showing 1–10 of 1202 papers
Benchmark Results
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | RESDSQL-3B + NatSQL | Accuracy | 84.1 | — | Unverified |
| 2 | code-davinci-002 175B (LEVER) | Accuracy | 81.9 | — | Unverified |
| 3 | RASAT+PICARD | Accuracy | 75.5 | — | Unverified |
| 4 | Graphix-3B + PICARD | Accuracy | 74 | — | Unverified |
| 5 | T5-3B + PICARD | Accuracy | 71.9 | — | Unverified |
| 6 | SADGA + GAP | Accuracy | 70.1 | — | Unverified |
| 7 | RATSQL + GAP | Accuracy | 69.7 | — | Unverified |
| 8 | RATSQL + Grammar-Augmented Pre-Training | Accuracy | 69.6 | — | Unverified |
| 9 | RATSQL + BERT | Accuracy | 65.6 | — | Unverified |
| 10 | Exact Set Matching | Accuracy | 19.7 | — | Unverified |