File:Figure 1- An Overview of WikiSP (from Xu et al. 2023).png
.png){kind=small}
Size of this preview: 367 × 598 pixels. Other resolutions: 147 × 240 pixels | 294 × 480 pixels | 471 × 768 pixels | 628 × 1,024 pixels | 1,386 × 2,260 pixels.
Original file (1,386 × 2,260 pixels, file size: 588 KB, MIME type: image/png)
 | This is a file from the Wikimedia Commons. Information from its description page there is shown below. Commons is a freely licensed media file repository. You can help. |
Summary
| Description |
English: "Figure 1: An Overview of WikiSP. An entity linker is used to link entities in the user query to their unique ID in Wikidata; e.g. “A Bronx Tale” is linked to entity ID “Q1130705”. The query and entity linker outputs are fed to the WikiSP semantic parser to produce a modified version of SPARQL, where property IDs (e.g. “P915”) are replaced by their unique string identifiers (e.g. “filming_location”). If applying the query to Wikidata fails to return a result, we default to GPT-3, labeling the result as a GPT-3 guess. Returned answers are presented in the context of the query, so the user can tell if the answer is acceptable; if not, we also show the guess from GPT-3. Here WikiSP mistakenly uses “filming_location” instead of “narrative_location”; the user detects the mistake, thumbs down the answer, and the GPT-3 answer is provided." |
| Date | |
| Source | Xu, Silei; Liu, Shicheng; Culhane, Theo; Pertseva, Elizaveta; Wu, Meng-Hsi; Semnani, Sina; Lam, Monica (December 2023). "Fine-tuned LLMs Know More, Hallucinate Less with Few-Shot Sequence-to-Sequence Semantic Parsing over Wikidata". Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing. EMNLP 2023. Singapore: Association for Computational Linguistics. pp. 5778–5791. doi:10.18653/v1/2023.emnlp-main.353 |
| Author | Xu, Silei; Liu, Shicheng; Culhane, Theo; Pertseva, Elizaveta; Wu, Meng-Hsi; Semnani, Sina; Lam, Monica |
Licensing
This file is licensed under the Creative Commons Attribution-Share Alike 4.0 International license.
- You are free:
- to share – to copy, distribute and transmit the work
- to remix – to adapt the work
- Under the following conditions:
- attribution – You must give appropriate credit, provide a link to the license, and indicate if changes were made. You may do so in any reasonable manner, but not in any way that suggests the licensor endorses you or your use.
- share alike – If you remix, transform, or build upon the material, you must distribute your contributions under the same or compatible license as the original.
File history
Click on a date/time to view the file as it appeared at that time.
| Date/Time | Thumbnail | Dimensions | User | Comment | |
|---|---|---|---|---|---|
| current | 20:29, 23 December 2023 | | 1,386 × 2,260 (588 KB) | HaeB | Uploaded a work by Xu, Silei; Liu, Shicheng; Culhane, Theo; Pertseva, Elizaveta; Wu, Meng-Hsi; Semnani, Sina; Lam, Monica from Xu, Silei; Liu, Shicheng; Culhane, Theo; Pertseva, Elizaveta; Wu, Meng-Hsi; Semnani, Sina; Lam, Monica (December 2023). "Fine-tuned LLMs Know More, Hallucinate Less with Few-Shot Sequence-to-Sequence Semantic Parsing over Wikidata". Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing. EMNLP 2023. Singapore: Association for Computatio... |
File usage
The following 2 pages use this file:
Global file usage
The following other wikis use this file:
.png){kind=link}