Michael Wayne Goodman
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Michael Wayne Goodman has a total of 10 co-authors. Here are the top co-authors by number of shared publications:
- Francis Bond
Palacký University
3 shared publications - Alexandre Rademaker
IBM Research Brazil
2 shared publications - Emily M. Bender
University of Washington
2 shared publications - Ewa Rudnicka
Politechnika Wrocławska [Wrocław University of Science and Technology], Wrocław
2 shared publications - John Philip McCrae
DSI Insight Research Ireland Centre for Data Analytics University of Galway Ireland
2 shared publications - Luis Morgado Da Costa
University of Tsukuba Vrije Universiteit Amsterdam University of Oslo GeorgAugustUniversität Göttingen
2 shared publications
Latest Publications
- 1 January 2023
- Published by Association for Computational Linguistics (ACL)
- p. 150-157
Documenting the Open Multilingual Wordnet
In this project note we describe our work to make better documentation for the Open Multilingual Wordnet (OMW), a platform integrating many open wordnets. This includes the documentation of the OMW website itself as well as of semantic relations used by the component wordnets. Some of this documentation work was done with the support of the Google Season of Docs. The OMW project page, which links both to the actual OMW server and the documentation has been moved to a new location: https://omwn.org.
- 1 January 2023
- Published by Association for Computational Linguistics (ACL)
- p. 150-157
Documenting the Open Multilingual Wordnet
In this project note we describe our work to make better documentation for the Open Multilingual Wordnet (OMW), a platform integrating many open wordnets. This includes the documentation of the OMW website itself as well as of semantic relations used by the component wordnets. Some of this documentation work was done with the support of the Google Season of Docs. The OMW project page, which links both to the actual OMW server and the documentation has been moved to a new location: https://omwn.org.
- 1 January 2021
- Published by Association for Computational Linguistics (ACL)
- p. 100-107
Intrinsically Interlingual: The Wn Python Library for Wordnets
This paper introduces Wn, a new Python library for working with wordnets. Unlike previous libraries, Wn is built from the beginning to accommodate multiple wordnets-for multiple languages or multiple versions of the same wordnet-while retaining the ability to query and traverse them independently. It is also able to download and incorporate wordnets published online. These features are made possible through Wn's adoption of standard formats and methods for interoperability, namely the WN-LMF schema (Vossen et al., 2013; Bond et al., 2020) and the Collaborative Interlingual Index (Bond et al., 2016). Wn is open-source, easily available, 1 and well-documented. 2
- 1 January 2021
- Published by Association for Computational Linguistics (ACL)
- p. 100-107
Intrinsically Interlingual: The Wn Python Library for Wordnets
This paper introduces Wn, a new Python library for working with wordnets. Unlike previous libraries, Wn is built from the beginning to accommodate multiple wordnets-for multiple languages or multiple versions of the same wordnet-while retaining the ability to query and traverse them independently. It is also able to download and incorporate wordnets published online. These features are made possible through Wn's adoption of standard formats and methods for interoperability, namely the WN-LMF schema (Vossen et al., 2013; Bond et al., 2020) and the Collaborative Interlingual Index (Bond et al., 2016). Wn is open-source, easily available, 1 and well-documented. 2
- Open Access
- 1 January 2021
- Published by Association for Computational Linguistics (ACL)
- p. 91-99
The GlobalWordNet Formats: Updates for 2020
John P. McCrae, Michael Wayne Goodman, Francis Bond, Alexandre Rademaker, Ewa Rudnicka, Luis Morgado Da Costa. Proceedings of the 11th Global Wordnet Conference. 2021.
- 1 January 2021
- Published by Association for Computational Linguistics (ACL)
- p. 91-99
Open AccessThe GlobalWordNet Formats: Updates for 2020
John P. McCrae, Michael Wayne Goodman, Francis Bond, Alexandre Rademaker, Ewa Rudnicka, Luis Morgado Da Costa. Proceedings of the 11th Global Wordnet Conference. 2021.
- Open Access
AMR Normalization for Fairer Evaluation
Meaning Representation (AMR; Banarescu et al., 2013) encodes the meaning of sentences as a directed graph and Smatch (Cai and Knight, 2013) is the primary metric for evaluating AMR graphs. Smatch, however, is unaware of some meaning-equivalent variations in graph structure allowed by the AMR Specification and gives different scores for AMRs exhibiting these variations. In this paper I propose four normalization methods for helping to ensure that conceptually equivalent AMRs are evaluated as equivalent. Equivalent AMRs with and without normalization can look quite different---comparing a gold corpus to itself with relation reification alone yields a difference of 25 Smatch points, suggesting that the outputs of two systems may not be directly comparable without normalization. The algorithms described in this paper are implemented on top of an existing open-source Python toolkit for AMR and will be released under the same license.
Open AccessAMR Normalization for Fairer Evaluation
Meaning Representation (AMR; Banarescu et al., 2013) encodes the meaning of sentences as a directed graph and Smatch (Cai and Knight, 2013) is the primary metric for evaluating AMR graphs. Smatch, however, is unaware of some meaning-equivalent variations in graph structure allowed by the AMR Specification and gives different scores for AMRs exhibiting these variations. In this paper I propose four normalization methods for helping to ensure that conceptually equivalent AMRs are evaluated as equivalent. Equivalent AMRs with and without normalization can look quite different---comparing a gold corpus to itself with relation reification alone yields a difference of 25 Smatch points, suggesting that the outputs of two systems may not be directly comparable without normalization. The algorithms described in this paper are implemented on top of an existing open-source Python toolkit for AMR and will be released under the same license.
- Open Access
Neural Text Generation from Rich Semantic Representations
We propose neural models to generate high-quality text from structured representations based on Minimal Recursion Semantics (MRS). MRS is a rich semantic representation that encodes more precise semantic detail than other representations such as Abstract Meaning Representation (AMR). We show that a sequence-to-sequence model that maps a linearization of Dependency MRS, a graph-based representation of MRS, to English text can achieve a BLEU score of 66.11 when trained on gold data. The performance can be improved further using a high-precision, broad coverage grammar-based parser to generate a large silver training corpus, achieving a final BLEU score of 77.17 on the full test set, and 83.37 on the subset of test data most closely matching the silver data domain. Our results suggest that MRS-based representations are a good choice for applications that need both structured semantics and the ability to produce natural language text as output.
Open AccessNeural Text Generation from Rich Semantic Representations
We propose neural models to generate high-quality text from structured representations based on Minimal Recursion Semantics (MRS). MRS is a rich semantic representation that encodes more precise semantic detail than other representations such as Abstract Meaning Representation (AMR). We show that a sequence-to-sequence model that maps a linearization of Dependency MRS, a graph-based representation of MRS, to English text can achieve a BLEU score of 66.11 when trained on gold data. The performance can be improved further using a high-precision, broad coverage grammar-based parser to generate a large silver training corpus, achieving a final BLEU score of 77.17 on the full test set, and 83.37 on the subset of test data most closely matching the silver data domain. Our results suggest that MRS-based representations are a good choice for applications that need both structured semantics and the ability to produce natural language text as output.
- 10 September 2014
- Published by Springer Nature in Language Resources and Evaluation
- Vol. 49 (2) , 455-485
Xigt: extensible interlinear glossed text for natural language processing
- 10 September 2014
- Published by Springer Nature in Language Resources and Evaluation
- Vol. 49 (2) , 455-485
Xigt: extensible interlinear glossed text for natural language processing