hugochan / bamnet Goto Github PK
View Code? Open in Web Editor NEWCode & data accompanying the NAACL 2019 paper "Bidirectional Attentive Memory Networks for Question Answering over Knowledge Bases"
License: Apache License 2.0
Code & data accompanying the NAACL 2019 paper "Bidirectional Attentive Memory Networks for Question Answering over Knowledge Bases"
License: Apache License 2.0
Hi, I just read your paper and find it very interesting. I want to try running the code but it seems you haven't uploaded it yet. May I know if you have any update plan?
Hello! Is there any support for testing the model on new questions after training it? If not, how would you recommend going about building that functionality? Ideally I would like to deploy the model as an API.
Hi! just trying to transfer your model to another dataset and KB, for the file entity2id.json/ entityType2id.json/ relation2id.json, is there any restrictions on assigining their IDs? Or just assigining a distinct ID to each relation/entity is OK?
the preprocessed data and the pretrained models can't be downloaded
Hi,
Thank you for your great work. I'm trying to run your code on FreebaseQA. Could you provide the freebase key file
?
Running any of the commands from the readme gives: FileNotFoundError: [Errno 2] No such file or directory: '../data/WebQ/train.json'
even though this file is not mentioned in the config and does not exist in the pretrained model. This file is probably hardcoded and the filename from the config should be used instead.
Hello, I can't visit onedrive website. Can you provide data and models in other ways, such as Google drive
the code:
ret = process.extract(topic_ent.replace('_', ' '), set(list(zip(*ent_types))[0]), scorer=fuzz.token_sort_ratio)
how to solve it please?
Hello! I download your dataste. The train/test/valid files (raw_train.json/raw_valid.json/raw_test.json) both contain the "freebaseKeyCands" data. Where does the data "freebaseKeyCands" come from? It is the entity linking results by using Freebase Search API ? Could you provide the entity linking results by using Freebase Search API for me ? Thanks a lot.
when i run train_entnet.py, i met a problem :
Traceback (most recent call last):
File "train_entnet.py", line 43, in <module>
[valid_memories, valid_queries, valid_query_lengths], valid_ent_inds)
File "/home/jzw/NLP/kbqa/BAMnet/src/core/bamnet/entnet.py", line 96, in train
train_loss += self.train_step(batch_xs, batch_ys) / num_batches
File "/home/jzw/NLP/kbqa/BAMnet/src/core/bamnet/entnet.py", line 174, in train_step
loss.backward()
File "/home/jzw/python3/lib/python3.6/site-packages/torch/tensor.py", line 93, in backward
torch.autograd.backward(self, gradient, retain_graph, create_graph)
File "/home/jzw/python3/lib/python3.6/site-packages/torch/autograd/__init__.py", line 90, in backward
allow_unreachable=True) # allow_unreachable flag
RuntimeError: CuDNN error: CUDNN_STATUS_INTERNAL_ERROR
i use torch 0.4.1, cuda 8, cudnn 7, how can i fix it?
Thank you.
You gave a link of your research data. I downloaded it and I saw a file called freebase_full.json. In this file, each element has its neighbors and paths directing to them. I checked the freebase dump which offered by google with sparql language, the paths that each element connects in your json file are not the all. Which means there are more paths should be connected by each element in freebase_full.json. I’m curious about how did you decide which path or neighbor should be added in each record? How did you build freebase_full.json file?
All the best, appreciate!
Siqi Lai
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.