NER-using-Deep-Learning
NER-using-Deep-Learning copied to clipboard
pandeydivesh15
how to use this NER
what is format of datset required for your NER . I wnat to use on my data set which is in SSF fromat. kindly help me for that.
You should see https://github.com/pandeydivesh15/NER-using-Deep-Learning/blob/master/Task%203:%20Hindi%20data/Convert%20SSF%20data%20to%20CoNLL%20form.ipynb The hindi dataset that I worked on was also in SSF. You will have to first convert your dataset into CoNLL form to be able to use this NER.
can you please support me in that if i want to convert data set which contain corefrence annotation into conll format then which file i have to change.
Sorry for late reply.
As I can see, you will have to design your own SSF->CoNLL converter. One ques, in line 21/22, the data shows,
उत्तरांचल NNP <fs af='उत्तरांचल,n,m,sg,3,o,0_का_ओर,0' drel='rd:खींचने' posn='210' vpos='vib_2_3' name='उत्तरांचल' chunkId='NP8' chunkType='head:NP8' cref='i1%1:t1' crefHead='उत्तरांचल:i1' crefChainHead='i1:t1' semprop='rest'>
Given this data, how do you know that this is a named entity for place? I am not able to understand.
could you help me out to do this.
On Wed, Aug 15, 2018 at 10:54 AM, Divesh Pandey [email protected] wrote:
Sorry for late reply.
As I can see, you will have to design your own SSF->CoNLL converter. One ques, in line 21/22, the data shows,
उत्तरांचल NNP
Given this data, how do you know that this is a named entity for place? I am not able to understand.
— You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub https://github.com/pandeydivesh15/NER-using-Deep-Learning/issues/3#issuecomment-413097436, or mute the thread https://github.com/notifications/unsubscribe-auth/AlRARLDHzVfvO8yhr4pzFqpRCi76ziiwks5uQ7CLgaJpZM4V6Jjl .
NNP is proper noun so i think in NER proper noun also having NER tag place.
On Thu, Aug 16, 2018 at 5:22 AM, pooja thakur [email protected] wrote:
could you help me out to do this.
On Wed, Aug 15, 2018 at 10:54 AM, Divesh Pandey [email protected] wrote:
Sorry for late reply.
As I can see, you will have to design your own SSF->CoNLL converter. One ques, in line 21/22, the data shows,
उत्तरांचल NNP
Given this data, how do you know that this is a named entity for place? I am not able to understand.
— You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub https://github.com/pandeydivesh15/NER-using-Deep-Learning/issues/3#issuecomment-413097436, or mute the thread https://github.com/notifications/unsubscribe-auth/AlRARLDHzVfvO8yhr4pzFqpRCi76ziiwks5uQ7CLgaJpZM4V6Jjl .
we have to make some distinction i think
On Thu, Aug 16, 2018 at 9:11 AM, pooja thakur [email protected] wrote:
NNP is proper noun so i think in NER proper noun also having NER tag place.
On Thu, Aug 16, 2018 at 5:22 AM, pooja thakur [email protected] wrote:
could you help me out to do this.
On Wed, Aug 15, 2018 at 10:54 AM, Divesh Pandey <[email protected]
wrote:
Sorry for late reply.
As I can see, you will have to design your own SSF->CoNLL converter. One ques, in line 21/22, the data shows,
उत्तरांचल NNP
Given this data, how do you know that this is a named entity for place? I am not able to understand.
— You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub https://github.com/pandeydivesh15/NER-using-Deep-Learning/issues/3#issuecomment-413097436, or mute the thread https://github.com/notifications/unsubscribe-auth/AlRARLDHzVfvO8yhr4pzFqpRCi76ziiwks5uQ7CLgaJpZM4V6Jjl .
But still no idea about LOCATION named entity. Do you wish to train a new NER classifier (using this dataset) or you wish to just find/predict named entities for this dataset?
i just want to find NER tag on my dataset in feature structure
On Thu, Aug 16, 2018 at 9:17 AM, Divesh Pandey [email protected] wrote:
But still no idea about LOCATION named entity. Do you wish to train a new NER classifier (using this dataset) or you wish to just find/predict named entities for this dataset?
— You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub https://github.com/pandeydivesh15/NER-using-Deep-Learning/issues/3#issuecomment-413416459, or mute the thread https://github.com/notifications/unsubscribe-auth/AlRARI44PGAFBtOLzB-wcmQLmbqD8xnMks5uROtngaJpZM4V6Jjl .
If you can help me i will be very thankful to you .
On Thu, Aug 16, 2018 at 9:43 PM, pooja thakur [email protected] wrote:
i just want to find NER tag on my dataset in feature structure
On Thu, Aug 16, 2018 at 9:17 AM, Divesh Pandey [email protected] wrote:
But still no idea about LOCATION named entity. Do you wish to train a new NER classifier (using this dataset) or you wish to just find/predict named entities for this dataset?
— You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub https://github.com/pandeydivesh15/NER-using-Deep-Learning/issues/3#issuecomment-413416459, or mute the thread https://github.com/notifications/unsubscribe-auth/AlRARI44PGAFBtOLzB-wcmQLmbqD8xnMks5uROtngaJpZM4V6Jjl .
For doing this, you would require already trained model for predicting NER tags. Currently my model isnt much powerful to predict better. You can see the results.
I have one lstm ner if you check on github
On Sat, 18 Aug 2018, 14:06 Divesh Pandey, [email protected] wrote:
For doing this, you would require already trained model for predicting NER tags. Currently my model isnt much powerful to predict better. You can see the results. [image: image] https://user-images.githubusercontent.com/16169561/44297484-cb825580-a2ef-11e8-92e3-6935a50b26cf.png
— You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub https://github.com/pandeydivesh15/NER-using-Deep-Learning/issues/3#issuecomment-414041990, or mute the thread https://github.com/notifications/unsubscribe-auth/AlRARJvLmlUO223Gq7Ag361tBsR73JiEks5uR9H2gaJpZM4V6Jjl .
Can i get your mail id
On Sat, 18 Aug 2018, 15:13 pooja thakur, [email protected] wrote:
I have one lstm ner if you check on github
On Sat, 18 Aug 2018, 14:06 Divesh Pandey, [email protected] wrote:
For doing this, you would require already trained model for predicting NER tags. Currently my model isnt much powerful to predict better. You can see the results. [image: image] https://user-images.githubusercontent.com/16169561/44297484-cb825580-a2ef-11e8-92e3-6935a50b26cf.png
— You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub https://github.com/pandeydivesh15/NER-using-Deep-Learning/issues/3#issuecomment-414041990, or mute the thread https://github.com/notifications/unsubscribe-auth/AlRARJvLmlUO223Gq7Ag361tBsR73JiEks5uR9H2gaJpZM4V6Jjl .