Skip to Main content Skip to Navigation
Conference papers

Semi-Supervised Learning on Meta Structure: Multi-Task Tagging and Parsing in Low-Resource Scenarios

Abstract : Multi-view learning makes use of diverse models arising from multiple sources of input or different feature subsets for the same task. For example, a given natural language processing task can combine evidence from models arising from character, morpheme, lexical, or phrasal views. The most common strategy with multi-view learning, especially popular in the neural network community, is to unify multiple representations into one unified vector through concatenation, averaging, or pooling , and then build a single-view model on top of the unified representation. As an alternative, we examine whether building one model per view and then unifying the different models can lead to improvements, especially in low-resource scenarios. More specifically, taking inspiration from co-training methods, we propose a semi-supervised learning approach based on multi-view models through consensus promotion, and investigate whether this improves overall performance. To test the multi-view hypothesis, we use moderately low-resource scenarios for nine languages and test the performance of the joint model for part-of-speech tagging and dependency parsing. The proposed model shows significant improvements across the test cases, with average gains of −0.9 ∼ +9.3 labeled attachment score (LAS) points. We also investigate the effect of unlabeled data on the proposed model by varying the amount of training data and by using different domains of unlabeled data.
Complete list of metadata

Cited literature [23 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-02895835
Contributor : Thierry Poibeau <>
Submitted on : Friday, July 10, 2020 - 10:28:03 AM
Last modification on : Thursday, January 14, 2021 - 3:14:13 PM
Long-term archiving on: : Monday, November 30, 2020 - 7:24:49 PM

File

Cometa_AAAI20.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-02895835, version 1

Collections

Citation

Kyungtae Lim, Jay Yoon Lee, Jaime Carbonell, Thierry Poibeau. Semi-Supervised Learning on Meta Structure: Multi-Task Tagging and Parsing in Low-Resource Scenarios. Conference of the Association for the Advancement of Artificial Intelligence, Association for the Advancement of Artificial Intelligence, Feb 2020, New York, United States. ⟨hal-02895835⟩

Share

Metrics

Record views

76

Files downloads

130