Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conferen 2019
DOI: 10.18653/v1/d19-1234
|View full text |Cite
|
Sign up to set email alerts
|

Weak Supervision for Learning Discourse Structure

Abstract: This paper provides a detailed comparison of a data programming approach with (i) off-the-shelf, state-of-the-art deep learning architectures that optimize their representations (BERT) and (ii) handcrafted-feature approaches previously used in the discourse analysis literature. We compare these approaches on the task of learning discourse structure for multi-party dialogue. The data programming paradigm offered by the Snorkel framework allows a user to label training data using expert-composed heuristics, whic… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
2
1

Citation Types

0
6
0

Year Published

2020
2020
2023
2023

Publication Types

Select...
5
2

Relationship

0
7

Authors

Journals

citations
Cited by 7 publications
(6 citation statements)
references
References 19 publications
0
6
0
Order By: Relevance
“…Various weak supervision approaches can be represented by labelling functions, such as distant supervision, heuristics or the results of crowd-sourcing annotations. Weak supervision has already been successfully applied in other problems in the area of natural language processing and information retrieval [4,13,16]. In this paper, we focus on the usage of heuristics to create the labelling functions for intent classification.…”
Section: Weak Supervisionmentioning
confidence: 99%
“…Various weak supervision approaches can be represented by labelling functions, such as distant supervision, heuristics or the results of crowd-sourcing annotations. Weak supervision has already been successfully applied in other problems in the area of natural language processing and information retrieval [4,13,16]. In this paper, we focus on the usage of heuristics to create the labelling functions for intent classification.…”
Section: Weak Supervisionmentioning
confidence: 99%
“…Our approach is based on the data-programming paradigm (Ratner et al, 2016), a weak supervision framework that has been applied mainly to information extraction problems in NLP, but also recently to discourse analysis (Badene et al, 2019), specifically for discourse structure prediction. We are unaware of similar work on discourse segmentation or on multi-modal text/speech classification problems.…”
Section: Related Workmentioning
confidence: 99%
“…Weak supervision is another approach for the curation of data for model training [36,46]. Weakly supervised learning is an umbrella term for a family of techniques for the mitigation of data scarcity.…”
Section: Weakly Supervised Learningmentioning
confidence: 99%