Wenting Zhao, Claire Cardie, Weiqi Sun, Konstantine Arkoudas
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Task-oriented parsing (TOP) aims to convert natural language into machine-readable representations of specific tasks, such as setting an alarm. A popular approach to TOP is to apply seq2seq models to generate linearized parse trees. A more recent line of work argues that pretrained seq2seq models are better at generating outputs that are themselves natural language, so they replace linearized parse trees with canonical natural-language paraphrases that can then be easily translated into parse trees, resulting in so-called naturalized parsers. In this work we continue to explore naturalized semantic parsing by presenting a general reduction of TOP to abstractive question answering that overcomes some limitations of canonical paraphrasing. Experimental results show that our QA-based technique outperforms stateof-the-art methods in full-data settings while achieving dramatic improvements in few-shot settings.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2205.02068")
get_code_for_paper("2205.02068")
have("2205.02068")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2205.02068.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2205.02068)
Connect an agent — have() is free.