Generating event descriptions under syntactic and semantic constraints
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910762079879168 |
|---|---|
| author | Cao, Angela Holt, Faye Chan, Jonas Richter, Stephanie Glass, Lelia White, Aaron Steven |
| author_facet | Cao, Angela Holt, Faye Chan, Jonas Richter, Stephanie Glass, Lelia White, Aaron Steven |
| contents | With the goal of supporting scalable lexical semantic annotation, analysis, and theorizing, we conduct a comprehensive evaluation of different methods for generating event descriptions under both syntactic constraints -- e.g. desired clause structure -- and semantic constraints -- e.g. desired verb sense. We compare three different methods -- (i) manual generation by experts; (ii) sampling from a corpus annotated for syntactic and semantic information; and (iii) sampling from a language model (LM) conditioned on syntactic and semantic information -- along three dimensions of the generated event descriptions: (a) naturalness, (b) typicality, and (c) distinctiveness. We find that all methods reliably produce natural, typical, and distinctive event descriptions, but that manual generation continues to produce event descriptions that are more natural, typical, and distinctive than the automated generation methods. We conclude that the automated methods we consider produce event descriptions of sufficient quality for use in downstream annotation and analysis insofar as the methods used for this annotation and analysis are robust to a small amount of degradation in the resulting event descriptions. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_18496 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Generating event descriptions under syntactic and semantic constraints Cao, Angela Holt, Faye Chan, Jonas Richter, Stephanie Glass, Lelia White, Aaron Steven Computation and Language With the goal of supporting scalable lexical semantic annotation, analysis, and theorizing, we conduct a comprehensive evaluation of different methods for generating event descriptions under both syntactic constraints -- e.g. desired clause structure -- and semantic constraints -- e.g. desired verb sense. We compare three different methods -- (i) manual generation by experts; (ii) sampling from a corpus annotated for syntactic and semantic information; and (iii) sampling from a language model (LM) conditioned on syntactic and semantic information -- along three dimensions of the generated event descriptions: (a) naturalness, (b) typicality, and (c) distinctiveness. We find that all methods reliably produce natural, typical, and distinctive event descriptions, but that manual generation continues to produce event descriptions that are more natural, typical, and distinctive than the automated generation methods. We conclude that the automated methods we consider produce event descriptions of sufficient quality for use in downstream annotation and analysis insofar as the methods used for this annotation and analysis are robust to a small amount of degradation in the resulting event descriptions. |
| title | Generating event descriptions under syntactic and semantic constraints |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2412.18496 |