BriefGPT.xyz
May, 2022
测量神经Seq2Seq语义解析器的对齐偏差
Measuring Alignment Bias in Neural Seq2Seq Semantic Parsers
HTML
PDF
Davide Locatelli, Ariadna Quattoni
TL;DR
本文研究了seq2seq模型是否能够处理简单和复杂的对齐，通过增加对齐注释来改进了Geo语义分析数据集，结果显示seq2seq模型在单调对齐的情况下表现显著更好。
Abstract
Prior to
deep learning
the
semantic parsing
community has been interested in understanding and modeling the range of possible word alignments between natural language sentences and their corresponding meaning rep
→