Robust Semantic Parsing with Adversarial Learning for Domain Generalization

10/01/2019
by   Gabriel Marzinotto, et al.
0

This paper addresses the issue of generalization for Semantic Parsing in an adversarial framework. Building models that are more robust to inter-document variability is crucial for the integration of Semantic Parsing technologies in real applications. The underlying question throughout this study is whether adversarial learning can be used to train models on a higher level of abstraction in order to increase their robustness to lexical and stylistic variations.We propose to perform Semantic Parsing with a domain classification adversarial task without explicit knowledge of the domain. The strategy is first evaluated on a French corpus of encyclopedic documents, annotated with FrameNet, in an information retrieval perspective, then on PropBank Semantic Role Labeling task on the CoNLL-2005 benchmark. We show that adversarial learning increases all models generalization capabilities both on in and out-of-domain data.

READ FULL TEXT
research
10/07/2019

Adapting a FrameNet Semantic Parser for Spoken Language Understanding Using Adversarial Learning

This paper presents a new semantic frame parsing model, based on Berkele...
research
12/19/2018

Semantic Frame Parsing for Information Extraction : the CALOR corpus

This paper presents a publicly available corpus of French encyclopedic h...
research
02/03/2023

Crucial Semantic Classifier-based Adversarial Learning for Unsupervised Domain Adaptation

Unsupervised Domain Adaptation (UDA), which aims to explore the transfer...
research
04/17/2019

CraftAssist Instruction Parsing: Semantic Parsing for a Minecraft Assistant

We propose a large scale semantic parsing dataset focused on instruction...
research
05/01/2018

Multitask Parsing Across Semantic Representations

The ability to consolidate information of different types is at the core...
research
10/01/2020

Understanding the Role of Adversarial Regularization in Supervised Learning

Despite numerous attempts sought to provide empirical evidence of advers...
research
09/11/2019

Multi-stage domain adversarial style reconstruction for cytopathological image stain normalization

The different stain styles of cytopathological images have a negative ef...

Please sign up or login with your details

Forgot password? Click here to reset