Label Ranking under Ambiguous Supervision for Learning Semantic Correspondences
Lists
Only you see this
Abstract
This paper studies the problem of learning from ambiguous supervision, focusing on the task of learning semantic correspondences. A learning problem is said to be ambiguously supervised when, for a given training input, a set of output candidates is provided with no prior of which one is correct. We propose to tackle this problem by solving a related unambiguous task with a label ranking approach and show how and why this performs well on the original task, via the method of task-transfer. We apply it to learning to match natural language sentences to a structured representation of their meaning and empirically demonstrate that this competes with the state-of-the-art on two benchmarks. 1.
BibTeX
@inproceedings{bordes2010label,
author = {Antoine Bordes and Nicolas Usunier and Jason Weston},
title = {{Label Ranking under Ambiguous Supervision for Learning Semantic Correspondences}},
booktitle = {International Conference on Machine Learning},
year = {2010},
url = {https://openreview.net/forum?id=Sk-YFoZdbS},
}Loading related content...