Where communities thrive


  • Join over 1.5M+ people
  • Join over 100K+ communities
  • Free without limits
  • Create your own community
People
Activity
  • Sep 09 07:53
    stalgiag closed #177
  • Aug 31 05:23
    chenguowang1 opened #214
  • Aug 23 12:15
    1024064118 opened #213
  • Jul 21 15:57
    aimoip closed #212
  • Jul 21 15:57
    aimoip opened #212
  • Jul 16 13:08
    aimoip closed #211
  • Jul 16 13:08
    aimoip opened #211
  • Jul 11 03:16
    ChenYaChu opened #210
  • May 31 02:31
    CharmingWang opened #209
  • May 23 05:47
    sabuhish commented #178
  • May 13 01:49
    Hexagram-King commented #145
  • Mar 30 02:41
    yfliao edited #208
  • Mar 30 02:27
    yfliao edited #208
  • Mar 30 02:26
    yfliao opened #208
  • Mar 25 05:31
    Jiangchenglin521 opened #207
  • Mar 15 03:09
    Wangkaichn closed #206
  • Mar 15 02:56
    Wangkaichn opened #206
  • Feb 24 13:10
    johnpaul89 commented #187
  • Feb 20 23:04
    tathagatankit commented #205
  • Feb 19 04:22
    jacklxf commented #182
NB
@huachengyu
nobody...
Prateek Srivastava
@prateeksri123
Hello, I want to develop a chat bot and I was following https://github.com/Conchylicultor/DeepQA, can anyone suggest how to retrain chatbot with our domain data
Rahul Kumaresan
@rahul-kumi
hey guys.
@Conchylicultor , I want to create a model that could crunch out short relevant answers, I plan to use the opensubs dataset, can you share the hyperparameter values to get the best results from the model.
Rifhan Akram
@rifhanakram
hey guys
i tried the deepQA for the cornell dataset and it worked fine on the terminal
but when i follow instructions and setup the web app the chatbot acts weird
feihuiwu123
@feihuiwu123
hi
Yongli Chen
@saiyan86
@Samurais Do you want to Chinese support together?
Utkarsh Deep
@utkarshdeep
hi group. I am planning to develop a chatbot. Most probably will be using either Java or Scala. Any help or suggestions are appreciated.
gustavoverneque
@gustavoverneque
hi
Gunjan Karamchandani
@troublemagnet
Hi
need help
rui
@RuiDu93
hi
is this the place to put some question about DeepQA ?
yangshichong
@yangshichong
hi
Zhong Peixiang
@zhongpeixiang
the website hosting OpenSustitles dataset is down, where did you guys download it?
Julien Chaumond
@julien-c
Hi all!
@Conchylicultor @eschnou Hope you both are doing great. What's new for you guys?
I think this (new-ish) dataset would make a lot of sense for DeepQA, reading the paper made me think of you :) http://yanran.li/dailydialog
vaibhav
@vaibhavch
hi
ChavesLiu
@ChavesLiu
Is anybody there?
Liu Peng
@DevilRocer_twitter
yeah
proszx
@proszx
@Conchylicultor some bug interrupts,about django and channels.can you tell me the version of channels
wujiajia2017scnu
@wujiajia2017scnu
hi,i had a error:django.core.exceptions.ImproperlyConfigured: Cannot import ASGI_APPLICATION module 'chatbot_website.routing'。
oumy
@oumitoux
Hello everyone can i make this chatbot interact with database to get data
Pushkar Pushp Yadav
@nature_pushp07_twitter
hey
anybody here?
Ricky Andika SP
@RickyAndikaSP20
How to create confusion matrix for models chatbot in keras python?
Will Hoffman
@WillWammer
hey
Samrakshak Karki
@SamrakshakK_twitter
hello
1000sprites
@1000sprites
hello
qianye0905
@qianye0905
hi, anybody
LALADIDADI
@LALADIDADI
Hello
maybe524
@maybe524
are you ok
hi, anybody
阿斯弗
2325
yejianfeng2014
@yejianfeng2014
hi
Alexey Kuzyashin
@Kuzyashin
hi, anybody
khanh97mh
@khanh97mh
Does anyone have training data DeepQA?
Alexey Kuzyashin
@Kuzyashin
can i use for embeddingSource *.w2v files ?
Maxrang
@Maxrang
hello everyone i know this seem to be a dead chat channel but i believe if at least two persons are active then this can be helpful for everyone especially since that deep learning doesn't have alot of chatting communities to support it
@zhongpeixiang i believe this link is still active, i've found it on the readme in the opensubs folder
http://opus.lingfil.uu.se/download.php?f=OpenSubtitles/en.tar.gz
Maxrang
@Maxrang
@rahul-kumi i've tried using the default parameters with opensubs dataset
trained on my own gtx 980 ti card,took 30 epochs for about 6 hours
the results are okay but i hope to produce more as there's alot of concepts that can be used to improve the model
here's some examples
model_predictions.txt
Maxrang
@Maxrang

does anyone know how to get the logits (predictions) from the embedding_rnn_seq2seq
i need it so i could eventually calculate the accuracy
i've tried doing

correct_prediction = tf.equal(tf.argmax(decoderOutputs, 1), tf.argmax(self.decoderTargets, 1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))

but the decoderOutputs are not of the same shape of decoderTargets

have anyone tried calculating accuracy from the output of a seq2seq function before?

Jennifer03333333332
@Jennifer03333333332
can you help me?
Kim jong-un
@AC-Unicorn
tensorflow.python.framework.errors_impl.NotFoundError:Tensor name "embedding_rnn_seq2seq/embedding_rnn_decoder/rnn_decoder/output_projection_wrapper/bias" not found in checkpoint files
anyone met this kind of problem before
?
kojingbo
@kojingbo
hi