Open unhammer opened 6 years ago
Indeed, the DBLP entry is better. Thanks for pointing it out. I don't see any way to retrieve the better bibtex link in the API docs (https://arxiv.org/help/api/user-manual), and this is what the API returns for your example:
<?xml version="1.0" encoding="UTF-8"?>
<feed xmlns="http://www.w3.org/2005/Atom">
<link href="http://arxiv.org/api/query?search_query%3D%26id_list%3D1702.03859v1%26start%3D0%26max_results%3D10" rel="self" type="application/atom+xml"/>
<title type="html">ArXiv Query: search_query=&id_list=1702.03859v1&start=0&max_results=10</title>
<id>http://arxiv.org/api/8Leov/wRbSIWRIO4V8yzOvuAOug</id>
<updated>2018-03-22T00:00:00-04:00</updated>
<opensearch:totalResults xmlns:opensearch="http://a9.com/-/spec/opensearch/1.1/">1</opensearch:totalResults>
<opensearch:startIndex xmlns:opensearch="http://a9.com/-/spec/opensearch/1.1/">0</opensearch:startIndex>
<opensearch:itemsPerPage xmlns:opensearch="http://a9.com/-/spec/opensearch/1.1/">10</opensearch:itemsPerPage>
<entry>
<id>http://arxiv.org/abs/1702.03859v1</id>
<updated>2017-02-13T16:31:06Z</updated>
<published>2017-02-13T16:31:06Z</published>
<title>Offline bilingual word vectors, orthogonal transformations and the
inverted softmax</title>
<summary> Usually bilingual word vectors are trained "online". Mikolov et al. showed
they can also be found "offline", whereby two pre-trained embeddings are
aligned with a linear transformation, using dictionaries compiled from expert
knowledge. In this work, we prove that the linear transformation between two
spaces should be orthogonal. This transformation can be obtained using the
singular value decomposition. We introduce a novel "inverted softmax" for
identifying translation pairs, with which we improve the precision @1 of
Mikolov's original mapping from 34% to 43%, when translating a test set
composed of both common and rare English words into Italian. Orthogonal
transformations are more robust to noise, enabling us to learn the
transformation without expert bilingual signal by constructing a
"pseudo-dictionary" from the identical character strings which appear in both
languages, achieving 40% precision on the same test set. Finally, we extend our
method to retrieve the true translations of English sentences from a corpus of
200k Italian sentences with a precision @1 of 68%.
</summary>
<author>
<name>Samuel L. Smith</name>
</author>
<author>
<name>David H. P. Turban</name>
</author>
<author>
<name>Steven Hamblin</name>
</author>
<author>
<name>Nils Y. Hammerla</name>
</author>
<arxiv:comment xmlns:arxiv="http://arxiv.org/schemas/atom">Accepted to conference track at ICLR 2017</arxiv:comment>
<link href="http://arxiv.org/abs/1702.03859v1" rel="alternate" type="text/html"/>
<link title="pdf" href="http://arxiv.org/pdf/1702.03859v1" rel="related" type="application/pdf"/>
<arxiv:primary_category xmlns:arxiv="http://arxiv.org/schemas/atom" term="cs.CL" scheme="http://arxiv.org/schemas/atom"/>
<category term="cs.CL" scheme="http://arxiv.org/schemas/atom"/>
<category term="cs.AI" scheme="http://arxiv.org/schemas/atom"/>
<category term="cs.IR" scheme="http://arxiv.org/schemas/atom"/>
</entry>
Should we make a feature request?
Sounds like a good idea … is it a github project or where do they take requests? I didn't see anything immediately likely on arxiv.org
No github project AFAIK. There's a mailing list, which I think would be a good place to start (https://groups.google.com/forum/#!forum/arxiv-api)
I posted a request, though I think it needs to pass moderation to show up
Any update on this? :)
When I go to https://arxiv.org/abs/1702.03859v1 and click the bibtex link I get http://dblp.uni-trier.de/rec/bibtex/journals/corr/SmithTHH17 which says
but when I search for the same in biblio (
biblio-arxiv-lookup
) and hiti
, I getThe key is nicer though, no slashes.