File:Figure 1- An Overview of WikiSP (from Xu et al. 2023).png
From Wikimedia Commons, the free media repository
Jump to navigation
Jump to search
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)
File information
Structured data
Captions
Summary
[edit]DescriptionFigure 1- An Overview of WikiSP (from Xu et al. 2023).png |
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
[edit]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 (talk | contribs) | 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... |
You cannot overwrite this file.
File usage on Commons
There are no pages that use this file.
File usage on other wikis
The following other wikis use this file:
- Usage on en.wikipedia.org
- Usage on meta.wikimedia.org
Metadata
This file contains additional information such as Exif metadata which may have been added by the digital camera, scanner, or software program used to create or digitize it. If the file has been modified from its original state, some details such as the timestamp may not fully reflect those of the original file. The timestamp is only as accurate as the clock in the camera, and it may be completely wrong.
Software used | |
---|---|
Date and time of digitizing |
|
Hidden category: