Bringing replication and reproduction together with generalisability in NLP : Three reproduction studies for Target Dependent Sentiment Analysis

Moore, Andrew and Rayson, Paul Edward (2018) Bringing replication and reproduction together with generalisability in NLP : Three reproduction studies for Target Dependent Sentiment Analysis. In: Proceedings of the 27th International Conference on Computational Linguistics :. Association for Computational Linguistics, USA, pp. 1132-1134. ISBN 9781948087506

[thumbnail of bringing_replication_reproduction]
Preview
PDF (bringing_replication_reproduction)
bringing_replication_reproduction.pdf - Submitted Version
Available under License Creative Commons Attribution.

Download (546kB)
[thumbnail of bringing-replication-reproduction]
Preview
PDF (bringing-replication-reproduction)
bringing_replication_reproduction.pdf - Accepted Version
Available under License Creative Commons Attribution.

Download (548kB)

Abstract

Lack of repeatability and generalisability are two significant threats to continuing scientific development in Natural Language Processing. Language models and learning methods are so complex that scientific conference papers no longer contain enough space for the technical depth required for replication or reproduction. Taking Target Dependent Sentiment Analysis as a case study, we show how recent work in the field has not consistently released code, or described settings for learning methods in enough detail, and lacks comparability and generalisability in train, test or validation data. To investigate generalisability and to enable state of the art comparative evaluations, we carry out the first reproduction studies of three groups of complementary methods and perform the first large-scale mass evaluation on six different English datasets. Reflecting on our experiences, we recommend that future replication or reproduction experiments should always consider a variety of datasets alongside documenting and releasing their methods and published code in order to minimise the barriers to both repeatability and generalisability. We have released our code with a model zoo on GitHub with Jupyter Notebooks to aid understanding and full documentation, and we recommend that others do the same with their papers at submission time through an anonymised GitHub account.

Item Type:
Contribution in Book/Report/Proceedings
Uncontrolled Keywords:
/dk/atira/pure/subjectarea/asjc/1700/1702
Subjects:
?? nlp sentiment analysisreproducibilityartificial intelligencecomputer science (miscellaneous) ??
ID Code:
125854
Deposited By:
Deposited On:
22 Jun 2018 12:46
Refereed?:
Yes
Published?:
Published
Last Modified:
15 Sep 2024 23:43