REPOGEO REPORT · LITE

openai/deeptype

Default branch master · commit 11568183 · scanned 6/1/2026, 4:12:56 PM

GitHub: 655 stars · 143 forks

AI VISIBILITY SCORE

33 /100

Critical

Category recall

0 / 2

Not recommended in any query

Rule findings

2 pass · 0 warn · 0 fail

Objective metadata checks

AI knows your name

2 / 3

Direct prompts that named your repo

HOW TO READ THIS REPORT

Action plan is what to do next — copy-pasteable changes prioritized by impact. Category visibility is the real GEO test: when a user asks an AI a brand-free question that should surface openai/deeptype, does the AI actually recommend you — or your competitors? Objective checks verify the metadata signals AI engines weight first. Self-mention check detects whether AI even knows you exist by name.

Action plan — copy-paste fixes

3 prioritized changes generated by gemini-2.5-flash. Mark items done after you ship the fix.

OVERALL DIRECTION

highreadme#1

Reposition the README opening to clarify core functionality

Why:

CURRENT

**Status:** Archive (code is provided as-is, no updates expected)

DeepType: Multilingual Entity Linking through Neural Type System Evolution
This repository contains code necessary for designing, evolving type systems, and training neural type systems. To read more about this technique and our results see this blog post or read the paper.

COPY-PASTE FIX

**Status:** Archive (code is provided as-is, no updates expected)

DeepType: Multilingual Entity Linking through Neural Type System Evolution
This repository contains code for our research on applying neural type systems to **multilingual entity linking in natural language processing (NLP)**. This technique guides neural networks to understand documents and recognize entities by learning task-specific semantic constraints, achieving state-of-the-art accuracy. To read more about this technique and our results see this blog post or read the paper.

hightopics#2

Add specific topics to improve categorization

Why:

CURRENT

paper

COPY-PASTE FIX

entity-linking, nlp, natural-language-processing, machine-learning, deep-learning, knowledge-graphs, wikidata, information-extraction, multilingual, research-paper

mediumreadme#3

Clarify the project's license in the README

Why:

COPY-PASTE FIX

## License
Please refer to the `LICENSE` file in this repository for the specific terms of use. This project uses a custom license.

Category GEO backends resolved for this scan: google/gemini-2.5-flash, deepseek/deepseek-v4-flash

Category visibility — the real GEO test

Brand-free queries asked to google/gemini-2.5-flash. Did AI recommend you, or someone else?

Same questions for every model — switch tabs to compare answers and rankings.

Recall

0 / 2

0% of queries surface openai/deeptype

Avg rank

—

Lower is better. #1 = top recommendation.

Share of voice

Of all named tools, what % are you?

Top rival

Wikidata

Recommended in 2 of 2 queries

COMPETITOR LEADERBOARD

Wikidata · recommended 2×
DBpedia · recommended 2×
mGENRE (Multilingual Generative Entity Linker) · recommended 1×
BLINK (Bi-encoder for Language-agnostic Knowledge linking) · recommended 1×
XLM-R · recommended 1×

CATEGORY QUERY
How to achieve state-of-the-art accuracy in multilingual entity linking using semantic constraints?
you: not recommended
AI recommended (in order):
1. mGENRE (Multilingual Generative Entity Linker)
2. BLINK (Bi-encoder for Language-agnostic Knowledge linking)
3. XLM-R
4. mBERT
5. Wikidata
6. DBpedia
7. REL (Radboud Entity Linker)
8. BERT
9. OpenNRE (Open-source Neural Relation Extraction)
10. WatDiv (Web Annotation Tool for Diverse Knowledge Bases)
11. DBpedia Spotlight
12. SpaCy's Entity Linker
13. FastText
14. LaBSE
AI recommended 14 alternatives but never named openai/deeptype. This is the gap to close.
Show full AI answer
CATEGORY QUERY
What are effective methods for learning symbolic structures to improve natural language entity recognition?
you: not recommended
AI recommended (in order):
1. GATE
2. SpaCy's Matcher
3. DBpedia
4. Wikidata
5. Neo4j
6. SpaCy
7. NLTK
8. Stanford CoreNLP
9. PyTorch Geometric (PyG)
10. Deep Graph Library (DGL)
11. AllenNLP
12. SpaCy's experimental SRL
13. OpenAI GPT-4
14. Llama 2
15. Claude
AI recommended 15 alternatives but never named openai/deeptype. This is the gap to close.
Show full AI answer

Objective checks

Rule-based audits of metadata signals AI engines weight most.

Metadata completeness
pass
README presence
pass

Self-mention check

Does AI even know your repo exists when asked about it directly?

Compared to common alternatives in this category, what is the core differentiator of openai/deeptype?
pass
AI did not name openai/deeptype — likely talking about a different project
AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?
If a team adopts openai/deeptype in production, what risks or prerequisites should they evaluate first?
pass
AI named openai/deeptype explicitly
AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?
In one sentence, what problem does the repo openai/deeptype solve, and who is the primary audience?
pass
AI named openai/deeptype explicitly
AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?

Embed your GEO score

Drop this badge into the README of openai/deeptype. It auto-updates whenever the report is rescanned and links back to the latest report — easy public proof that you care about AI discoverability.

Live preview

MARKDOWN (README)

[![RepoGEO](https://repogeo.com/badge/openai/deeptype.svg)](https://repogeo.com/en/r/openai/deeptype)

HTML

<a href="https://repogeo.com/en/r/openai/deeptype"><img src="https://repogeo.com/badge/openai/deeptype.svg" alt="RepoGEO" /></a>

Pro

Subscribe to Pro for deep diagnoses

openai/deeptype — Lite scans stay free; this card itemizes Pro deep limits vs Lite.

Deep reports10 / month
Brand-free category queries5 vs 2 in Lite
Prioritized action items8 vs 3 in Lite