<div dir="ltr">Dear Andrey, Thanks a ton. this worked perfectly, <div><br></div><div>Kind regards<br>Santosh</div></div><br><div class="gmail_quote"><div dir="ltr" class="gmail_attr">On Fri, Jan 29, 2021 at 12:42 PM Andrey Kutuzov <<a href="mailto:andreku@ifi.uio.no">andreku@ifi.uio.no</a>> wrote:<br></div><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex">Dear Santosh,<br>
<br>
The words in this model are lemmatized and augmented with their part of<br>
speech tags (thus, "king_NOUN").<br>
This information can be found in the metadata file inside the archive<br>
(meta.json) or in the global metadata file for all models<br>
(<a href="http://vectors.nlpl.eu/repository/latest.json" rel="noreferrer" target="_blank">http://vectors.nlpl.eu/repository/latest.json</a>).<br>
<br>
On 29.01.2021 12:29, Stephan Oepen wrote:<br>
> the NLPL infrastructure task force is the right contact address for<br>
> questions of this kind (please see below).<br>
> <br>
> best wishes, oe<br>
> <br>
> On Fri, Jan 29, 2021 at 12:20 PM Santosh SRINIVAS<br>
> <<a href="mailto:srinivas.hec@gmail.com" target="_blank">srinivas.hec@gmail.com</a>> wrote:<br>
>><br>
>> Dear NLPL Team, I am trying to use your pretrained Wiki[edia vectors. I used the following code mentioned on your page to load the vectors:<br>
>><br>
>> f= '3.zip'<br>
>> with zipfile.ZipFile(f, "r") as archive:<br>
>> stream= archive.open("model.txt")<br>
>> w2v= gensim.models.KeyedVectors.load_word2vec_format(stream, binary=False, unicode_errors='replace')<br>
>><br>
>> It loads fine. But it returns an error for any word. For example, 'king' in w2v returns False.<br>
>><br>
>> Not sure what I am doing wrong. Could you kindly help?<br>
>><br>
>> Thanks and regards<br>
>> Santosh<br>
<br>
<br>
-- <br>
Andrey<br>
Language Technology Group (LTG)<br>
University of Oslo<br>
</blockquote></div>