Comments (5)
WebQA released by Baidu which is in Chinese and contains quit amount of knowledge with accurate answer similar with SQuad.
I think the official download link is down. I can offer a backup link for you if you wanna play with it.
https://drive.google.com/open?id=1r5lNotgWvTw58Y9s3Xodisiw8TuKecRn
from bert-for-tf2.
I haven't look at the WebQA yet (do you have a download link for the dataset?), but I'm planning to commit a notebook on how to use bert-for-tf2 on SQuAD soon.
from bert-for-tf2.
I wanna saw kinda knowledge answer machine example which I believe it can be very fun such as:
Q: **的首都是哪里?
A: 北京
Q:**的首都是在哪个地方?
A: 北京
Q: **的首都是哪个城市?
A: 北京
from bert-for-tf2.
Thank you @jinfagang for the link!
I'll have to take a deeper look into it; currently I would say, it seems quite similar to SQuAD, i.e. given a question and a context (called evidence in the WebQA paper), predict a sequence tagging/labeling (i.e. where does the answer occur in the context sequence).
So if I understand correctly, in your example from above, you need to feed both a question and an evidence/context like (北京是**的首都) to predict the answer(北京).
from bert-for-tf2.
Yes for the conclusion but no, I think input can only be the question. Just using BERT pretrained model to make input sentence to a dense matrix then applying this as an input of a model (this model learns the knowledge from data). correct me if I am wrong.
the main insight is that using BERT to learn similar question station form which targets to a same answer.
However this maybe need another hard work on building such a model which learns on knowledge data.
I believe BERT able to do this quit well.
from bert-for-tf2.
Related Issues (20)
- ResourceExhaustedError: OOM when allocating tensor with shape[501153,768] and type float on /job:localhost/replica:0/task:0/device:GPU:0 by allocator GPU_0_bfc [Op:Mul]
- mixed precision HOT 3
- example (gpu_movie_reviews) has some mistake
- Failed to get weights from pretrained google model HOT 2
- Can not load pretrained bert weights when loading chinese_L-12_H-768_A-12/bert_model.ckpt HOT 3
- Paddings must be non-negative
- albert classification error(Failed copying input tensor from GPU in order to run Identity: GPU sync failed [Op:Identity])
- ValueError: Found unexpected keys that do not correspond to any Model output
- More comments for the code
- Can't train BERT with loaded weights on QA Task HOT 3
- Setting unexpected parameter 'name' in Params instance 'Params' HOT 2
- how to using this in functional model
- may be there is some problem work with tf hub
- AttributeError: module 'bert' has no attribute 'Layer'
- type error HOT 5
- Activation after bert-layer differs
- Count of weight not found[196]
- OSS License compatibility question
- tensorflow.python.keras.layer.input_spec should be replaced with tensorflow.keras.layers.InputSpec HOT 1
- setuptools.convert_path removed
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from bert-for-tf2.