Mutlitask Learning for Cross-Lingual Transfer of Semantic Dependencies

04/30/2020
by   Maryam Aminian, et al.
0

We describe a method for developing broad-coverage semantic dependency parsers for languages for which no semantically annotated resource is available. We leverage a multitask learning framework coupled with an annotation projection method. We transfer supervised semantic dependency parse annotations from a rich-resource language to a low-resource language through parallel data, and train a semantic parser on projected data. We make use of supervised syntactic parsing as an auxiliary task in a multitask learning framework, and show that with different multitask learning settings, we consistently improve over the single-task baseline. In the setting in which English is the source, and Czech is the target language, our best multitask model improves the labeled F1 score over the single-task baseline by 1.8 in the in-domain SemEval data (Oepen et al., 2015), as well as 2.5 in the out-of-domain test set. Moreover, we observe that syntactic and semantic dependency direction match is an important factor in improving the results.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 1

page 2

page 3

page 4

10/16/2021

Substructure Distribution Projection for Zero-Shot Cross-Lingual Dependency Parsing

We present substructure distribution projection (SubDP), a technique tha...
10/03/2017

Transferring Semantic Roles Using Translation and Syntactic Information

Our paper addresses the problem of annotation projection for semantic ro...
09/17/2019

Multimodal Multitask Representation Learning for Pathology Biobank Metadata Prediction

Metadata are general characteristics of the data in a well-curated and c...
08/26/2019

Partially-supervised Mention Detection

Learning to detect entity mentions without using syntactic information c...
09/03/2019

Towards Making a Dependency Parser See

We explore whether it is possible to leverage eye-tracking data in an RN...
08/14/2020

MLM: A Benchmark Dataset for Multitask Learning with Multiple Languages and Modalities

In this paper, we introduce the MLM (Multiple Languages and Modalities) ...
05/01/2018

Multitask Parsing Across Semantic Representations

The ability to consolidate information of different types is at the core...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.