SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2010.07792 · NeurIPS · 2020

Hierarchical Poset Decoding for Compositional Generalization in Language

Jian-Guang Lou, Zeqi Lin, Dongmei Zhang, Yinuo Guo

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. We have no repository linked to it either. That is a statement about our graph, not about the paper.

Abstract

We formalize human language understanding as a structured prediction task where the output is a partially ordered set (poset). Current encoder-decoder architectures do not take the poset structure of semantics into account properly, thus suffering from poor compositional generalization ability. In this paper, we propose a novel hierarchical poset decoding paradigm for compositional generalization in language. Intuitively: (1) the proposed paradigm enforces partial permutation invariance in semantics, thus avoiding overfitting to bias ordering information; (2) the hierarchical mechanism allows to capture high-level structures of posets. We evaluate our proposed decoder on Compositional Freebase Questions (CFQ), a large and realistic natural language question answering dataset that is specifically designed to measure compositional generalization. Results show that it outperforms current decoders.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2010.07792")
get_code_for_paper("2010.07792")
have("2010.07792")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2010.07792.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2010.07792.svg)](https://syntology.ai/paper/2010.07792)

Connect an agent — have() is free.