Encoder-Decoder Model for Semantic Role Labeling (ICPSR doi:10.11588/data/TOI9NQ)

View:

Part 1: Document Description
Part 2: Study Description
Part 5: Other Study-Related Materials
Entire Codebook

Document Description

Citation

Title:

Encoder-Decoder Model for Semantic Role Labeling

Identification Number:

doi:10.11588/data/TOI9NQ

Distributor:

heiDATA

Date of Distribution:

2020-01-23

Version:

1

Bibliographic Citation:

Daza, Angel, 2020, "Encoder-Decoder Model for Semantic Role Labeling", https://doi.org/10.11588/data/TOI9NQ, heiDATA, V1

Study Description

Citation

Title:

Encoder-Decoder Model for Semantic Role Labeling

Identification Number:

doi:10.11588/data/TOI9NQ

Authoring Entity:

Daza, Angel (Leibniz Institute for the German Language)

Date of Production:

2019

Distributor:

heiDATA

Date of Distribution:

2020-01-23

Study Scope

Keywords:

Arts and Humanities, Computer and Information Science, Semantic Role Labeling, SRL, monolingual setting, multilingual setting, cross-lingual setting, semantic role annotation

Topic Classification:

Semantic Role Labeling

Abstract:

<p><strong>Abstract (Daza &amp; Frank 2019):</strong></p> <p>We propose a Cross-lingual Encoder-Decoder model that simultaneously translates and generates sentences with Semantic Role Labeling annotations in a resource-poor target language. Unlike annotation projection techniques, our model does not need parallel data during inference time. Our approach can be applied in monolingual, multilingual and cross-lingual settings and is able to produce dependency-based and span-based SRL annotations. We benchmark the labeling performance of our model in different monolingual and multilingual settings using well-known SRL datasets. We then train our model in a cross-lingual setting to generate new SRL labeled data. Finally, we measure the effectiveness of our method by using the generated data to augment the training basis for resource-poor languages and perform manual evaluation to show that it produces high-quality sentences and assigns accurate semantic role annotations. Our proposed architecture offers a flexible method for leveraging SRL data in multiple languages.</p>

Kind of Data:

program source code

Methodology and Processing

Other Study-Related Materials

Label:

README.md

Notes:

text/markdown

Other Study-Related Materials

Label:

SRL-S2S.zip

Notes:

application/zip