REPOGEO REPORT · LITE

namisan/mt-dnn

Default branch master · commit 3228e7c2 · scanned 5/19/2026, 11:57:27 AM

GitHub: 2,256 stars · 408 forks

Scan history for this repo

Score trend below includes all ready runs (older left, newer right; scroll horizontally if needed). The table is collapsed by default—expand for newest-first rows, 10 per page.

Score trend (left → right: older → newer)

2 ready scans. Expand the table below for newest-first rows (10 per page, paginated).

AI VISIBILITY SCORE

35 /100

Critical

Category recall

0 / 2

Not recommended in any query

Rule findings

1 pass · 1 warn · 0 fail

Objective metadata checks

AI knows your name

3 / 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 namisan/mt-dnn, 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

Strengthen README's opening to highlight MT-DNN as a multi-task NLU framework

Why:

CURRENT

This PyTorch package implements the Multi-Task Deep Neural Networks (MT-DNN) for Natural Language Understanding, as described in:

COPY-PASTE FIX

This PyTorch package provides a robust and efficient framework for training Multi-Task Deep Neural Networks (MT-DNN) for Natural Language Understanding. Unlike fine-tuning separate models for each NLU task, MT-DNN simultaneously trains a shared Transformer-based encoder across multiple tasks, significantly enhancing generalization and performance.

mediumhomepage#2
Add a project homepage URL to the repository metadata
Why:
COPY-PASTE FIX
```
Add a relevant project or paper URL here.
```

lowtopics#3

Add topics emphasizing MT-DNN's role as a multi-task NLU framework

Why:

CURRENT

bert, deep-learning, machine-reading-comprehension, microsoft, multi-task-learning, named-entity-recognition, natural-language-understanding, nlp, pytorch, ranking

COPY-PASTE FIX

bert, deep-learning, machine-reading-comprehension, microsoft, multi-task-learning, named-entity-recognition, natural-language-understanding, nlp, pytorch, ranking, nlu-framework, multi-task-nlp

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 namisan/mt-dnn

Avg rank

—

Lower is better. #1 = top recommendation.

Share of voice

Of all named tools, what % are you?

Top rival

huggingface/transformers

Recommended in 1 of 2 queries

COMPETITOR LEADERBOARD

huggingface/transformers · recommended 1×
Lightning-AI/pytorch-lightning · recommended 1×
keras-team/keras · recommended 1×
allenai/allennlp · recommended 1×
explosion/spaCy · recommended 1×

CATEGORY QUERY
How can I train a single deep learning model for multiple natural language understanding tasks?
you: not recommended
AI recommended (in order):
1. Hugging Face Transformers (huggingface/transformers)
2. PyTorch Lightning (Lightning-AI/pytorch-lightning)
3. Keras (keras-team/keras)
4. AllenNLP (allenai/allennlp)
5. spaCy (explosion/spaCy)
6. spacy-transformers (explosion/spacy-transformers)
7. TensorFlow (tensorflow/tensorflow)
AI recommended 7 alternatives but never named namisan/mt-dnn. This is the gap to close.
Show full AI answer
CATEGORY QUERY
What are effective deep learning architectures for combining multiple NLP capabilities?
you: not recommended
AI recommended (in order):
1. T5
2. BART
3. XLM-R
4. Adapter-BERT
5. Adapter-T5
6. UniLM
7. M2M-100
8. Switch Transformers
9. Graphormer
AI recommended 9 alternatives but never named namisan/mt-dnn. This is the gap to close.
Show full AI answer

Objective checks

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

Metadata completeness
warn
Suggestion:
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 namisan/mt-dnn?
pass
AI named namisan/mt-dnn explicitly
AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?
If a team adopts namisan/mt-dnn in production, what risks or prerequisites should they evaluate first?
pass
AI named namisan/mt-dnn 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 namisan/mt-dnn solve, and who is the primary audience?
pass
AI named namisan/mt-dnn 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 namisan/mt-dnn. 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/namisan/mt-dnn.svg)](https://repogeo.com/en/r/namisan/mt-dnn)

HTML

<a href="https://repogeo.com/en/r/namisan/mt-dnn"><img src="https://repogeo.com/badge/namisan/mt-dnn.svg" alt="RepoGEO" /></a>

Pro

Subscribe to Pro for deep diagnoses

namisan/mt-dnn — 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