We lifted 1 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 |
|---|---|---|
| OhadRubin/SmBop | canonical | 1 of 1 |
| Function | Status | Where it lives |
|---|---|---|
| to_string | Ran | OhadRubin/SmBop/exec.py code served (permissive licence) · get_code("837222315099211e") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
The de-facto standard decoding method for semantic parsing in recent years has been to autoregressively decode the abstract syntax tree of the target program using a top-down depth-first traversal. In this work, we propose an alternative approach: a Semi-autoregressive Bottom-up Parser (SmBoP) that constructs at decoding step $t$ the top-$K$ sub-trees of height $\leq t$. Our parser enjoys several benefits compared to top-down autoregressive parsing. From an efficiency perspective, bottom-up parsing allows to decode all sub-trees of a certain height in parallel, leading to logarithmic runtime complexity rather than linear. From a modeling perspective, a bottom-up parser learns representations for meaningful semantic sub-programs at each step, rather than for semantically-vacuous partial trees. We apply SmBoP on Spider, a challenging zero-shot semantic parsing benchmark, and show that SmBoP leads to a 2.2x speed-up in decoding time and a $\sim$5x speed-up in training time, compared to a semantic parser that uses autoregressive decoding. SmBoP obtains 71.1 denotation accuracy on Spider, establishing a new state-of-the-art, and 69.5 exact match, comparable to the 69.6 exact match of the autoregressive RAT-SQL+GraPPa.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2010.12412")
get_code_for_paper("2010.12412")
have("2010.12412")
Connect an agent — have() is free.