Deep Semantic Representation

This project  aims to capture abstract and concrete concepts, along with their relations, within plain text. A key objective of this project is to develop a meaning representation that can be seamlessly transformed into semantic graphs, enabling probabilistic reasoning in the context of dialogue. Our representation, WISeR (Widely Interpretable Semantic Representation) differentiates itself from the broader concept of Abstract Meaning Representation (AMR) through its unique features and characteristics such as:

• It provides deeper and richer levels of abstraction.
• It is Interpretable by non-experts in computational structures.
• It covers relations across utterances (e.g., referents, external arguments).

This project is funded by:

• Amazon Alexa AI  (01/2022 ~ 12/2022)
• Alexa Prize Socialbot Grand Challenge 4 (01/2021 ~ 12/2021)
• Electronics and Telecommunications Research Institute (01/2020 ~ 12/2020)
• Kindi Inc. (09/2016 ~ 05/2017)

Directors

• PI: Jinho Chxoi - Assistant Professor at Emory University
• Gregor Williamson - Postdoctoral Fellow at Emory University (01/2021~ 05/2022)

Related Projects

• Multi-genre/layer Annotation (09/2021 ~ 05/2022)
• WISeR Annotation (09/2020 ~ 08/2021)
• SwNE Annotation (05/2020 ~ 08/2020)

Distributions

• WISeR - corpus
• StreamSide - annotation tool for meaning representations

Publications

1. Exploring a Multi-Layered Cross-Genre Corpus of Document-Level Semantic Relations. Williamson, G.; Cao, A.; Chen, Y.; Ji, Y.; Xu, L.; and Choi, J. D. Information: Information Extraction and Language Discourse Processing, 2023.
2. Widely Interpretable Semantic Representation: Frameless Meaning Representation for Broader Applicability. Feng, L.; Williamson, G.; He, H.; Choi, J. D. arXiv, 2023.
   
3. Automatic Enrichment of Abstract Meaning Representations. Ji, Y.; Williamson, G.; Choi, J. D. Proceedings of the LREC Workshop on Linguistic Annotation (LAW), 2022.
4. A Cognitive Approach to Annotating Causal Constructions in a Cross-Genre Corpus. Cao, A.; Williamson, G.; Choi, J. D. Proceedings of the LREC Workshop on Linguistic Annotation (LAW), 2022.
5. StreamSide: A Fully-Customizable Open-Source Toolkit for Efficient Annotation of Meaning Representations. Choi, J. D. and Williamson, G. arXiv, 2109.09853, 2021.
   
6. UMR-Writer: A Web Application for Annotating Uniform Meaning Representations. Zhao, J.; Xue, N.; Gysel, J. V.; and Choi, J. D. Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP): System Demonstrations, 2021.
   
7. Intensionalizing Abstract Meaning Representations: Non-veridicality and Scope. Williamson, G.; Elliott, P.; Ji, Y. Proceedings of the EMNLP Workshop on Linguistic Annotation Workshop (LAW) and Designing Meaning Representations (DMR), 2021.
8. Deep Dependency Graph Conversion in English. Choi, J. D. Proceedings of the International Workshop on Treebanks and Linguistic Theories (TLT), 2017.