<html>
<head>
<meta http-equiv="Content-Type" content="text/html; charset=UTF-8">
</head>
<body style="font-size: 10pt; font-family: Verdana,Geneva,sans-serif">
<div dir="ltr">
<div dir="ltr">
<div dir="ltr">
<div dir="ltr">
<table width="640" cellspacing="0" cellpadding="0"
border="0" align="center">
<tbody>
<tr>
<td>
<table width="640" cellspacing="0" cellpadding="0"
border="0" bgcolor="#ffffff" align="center">
<tbody>
<tr>
<td>
<table style="width: 640px; min-width:
640px;" width="640" cellspacing="0"
cellpadding="0" border="0"
bgcolor="#ffffff" align="center">
<tbody>
<tr>
<td>
<table style="width: 640px;
min-width: 640px;" width="640"
cellspacing="0" cellpadding="0"
border="0" align="center">
<tbody>
<tr>
<td style="padding: 0px 40px;"
align="center">
<table width="100%"
cellspacing="0"
cellpadding="0" border="0"
align="center">
<tbody>
<tr>
<td width="110"
valign="middle"
align="left"><img
id="m_925030267947577449gmail-m_6504557075424313283gmail-m_-5089897522223699477logoBlock-4"
class="gmail_canned_response_image" style="display: block;"
src="https://bucket.mlcdn.com/a/3476/3476114/images/d542a766ebbbc112d5bc5d9e40be271b526a92c6.jpeg"
moz-do-not-send="true" width="110" border="0"></td>
<td width="20"
height="1"> </td>
<td valign="middle"
align="right">
<table width="100%"
cellspacing="0"
cellpadding="0"
border="0"
align="center">
<tbody>
<tr>
<td
style="font-family:
Poppins,sans-serif; font-size: 21px; line-height: 31.5px; font-weight:
bold; color:
#0080ad;"
align="right">CLASSLA
Mailing List</td>
</tr>
</tbody>
</table>
</td>
</tr>
</tbody>
</table>
</td>
</tr>
</tbody>
</table>
<table style="width: 640px;
min-width: 640px;" width="640"
cellspacing="0" cellpadding="0"
border="0" align="center">
<tbody>
<tr>
<td style="line-height: 10px;
min-height: 10px;"
height="10"> </td>
</tr>
</tbody>
</table>
</td>
</tr>
</tbody>
</table>
</td>
</tr>
</tbody>
</table>
<table width="640" cellspacing="0" cellpadding="0"
border="0" bgcolor="#ffffff" align="center">
<tbody>
<tr>
<td>
<table style="width: 640px; min-width:
640px;" width="640" cellspacing="0"
cellpadding="0" border="0"
bgcolor="#ffffff" align="center">
<tbody>
<tr>
<td>
<table style="width: 640px;
min-width: 640px;" width="640"
cellspacing="0" cellpadding="0"
border="0" align="center">
<tbody>
<tr>
<td align="center">
<table style="border-top:
3px double #ededf3;
border-collapse: initial;"
width="100%"
cellspacing="0"
cellpadding="0" border="0"
align="center">
<tbody>
<tr>
<td
style="line-height:
0px; min-height:
0px;" height="0"> </td>
</tr>
</tbody>
</table>
</td>
</tr>
</tbody>
</table>
</td>
</tr>
</tbody>
</table>
</td>
</tr>
</tbody>
</table>
<table width="640" cellspacing="0" cellpadding="0"
border="0" bgcolor="#ffffff" align="center">
<tbody>
<tr>
<td>
<table style="width: 640px; min-width:
640px;" width="640" cellspacing="0"
cellpadding="0" border="0"
bgcolor="#ffffff" align="center">
<tbody>
<tr>
<td>
<table style="width: 640px;
min-width: 640px;" width="640"
cellspacing="0" cellpadding="0"
border="0" align="center">
<tbody>
<tr>
<td style="line-height: 10px;
min-height: 10px;"
height="10"> </td>
</tr>
</tbody>
</table>
<table style="width: 640px;
min-width: 640px;" width="640"
cellspacing="0" cellpadding="0"
border="0" align="center">
<tbody>
<tr>
<td style="padding: 0px 40px;"
align="center">
<table style="border-radius:
2px;" width="560"
cellspacing="0"
cellpadding="0" border="0"
align="center">
<tbody>
<tr>
<td style="padding:
0px 40px; border:
1px solid #e6e6e6;
border-radius: 2px;"
bgcolor="#FCFCFC"
align="center">
<table width="100%"
cellspacing="0"
cellpadding="0"
border="0"
align="center">
<tbody>
<tr>
<td
height="30"> </td>
</tr>
<tr>
<td
id="m_925030267947577449gmail-m_6504557075424313283gmail-m_-5089897522223699477bodyText-8"
style="font-family: Poppins,sans-serif; font-size: 14px; line-height:
21px; color:
#000000;"> <b
style="font-weight:normal;"
id="docs-internal-guid-0e1ba3a1-7fff-437f-9695-5fff78774c03">
<p dir="ltr"
style="line-height:1.38;margin-top:0pt;margin-bottom:0pt;"><span style="font-size:11pt;font-family:Arial,sans-serif;color:#000000;background-color:transparent;font-weight:400;font-style:normal;font-variant:normal;text-decoration:none;vertical-align:baseline;white-space:pre;white-space:pre-wrap;"><font face="Arial">D</font>ear all,
</span></p>
<p dir="ltr"
style="line-height:1.38;margin-top:0pt;margin-bottom:0pt;"><span style="font-size:11pt;font-family:Arial,sans-serif;color:#000000;background-color:transparent;font-weight:400;font-style:normal;font-variant:normal;text-decoration:none;vertical-align:baseline;white-space:pre;white-space:pre-wrap;">
</span></p>
<p dir="ltr"
style="line-height:1.38;margin-top:0pt;margin-bottom:0pt;"><span style="font-size:11pt;font-family:Arial,sans-serif;color:#000000;background-color:transparent;font-weight:400;font-style:normal;font-variant:normal;text-decoration:none;vertical-align:baseline;white-space:pre;white-space:pre-wrap;">
</span></p>
<p dir="ltr"
style="line-height:1.38;margin-top:0pt;margin-bottom:0pt;"><span style="font-size:11pt;font-family:Arial,sans-serif;color:#000000;background-color:transparent;font-weight:400;font-style:normal;font-variant:normal;text-decoration:none;vertical-align:baseline;white-space:pre;white-space:pre-wrap;">
</span></p>
<p dir="ltr"
style="line-height:1.38;margin-top:0pt;margin-bottom:0pt;"><span style="font-size:11pt;font-family:Arial,sans-serif;color:#000000;background-color:transparent;font-weight:400;font-style:normal;font-variant:normal;text-decoration:none;vertical-align:baseline;white-space:pre;white-space:pre-wrap;">The </span><a
href="https://www.clarin.si/info/k-centre/"
style="text-decoration:none;"
moz-do-not-send="true"><span style="font-size:11pt;font-family:Arial,sans-serif;color:#1155cc;background-color:transparent;font-weight:400;font-style:normal;font-variant:normal;text-decoration:underline;-webkit-text-decoration-skip:none;text-decoration-skip-ink:none;vertical-align:baseline;white-space:pre;white-space:pre-wrap;">CLASSLA Knowledge centre for South Slavic languages</span></a><span style="font-size:11pt;font-family:Arial,sans-serif;color:#000000;background-color:transparent;font-weight:400;font-style:normal;font-variant:normal;text-decoration:none;vertical-align:baseline;white-space:pre;white-space:pre-wrap;"> is delighted to announce the release of an improved </span><a
href="https://pypi.org/project/classla/" style="text-decoration:none;"
moz-do-not-send="true"><span style="font-size:11pt;font-family:Arial,sans-serif;color:#1155cc;background-color:transparent;font-weight:400;font-style:normal;font-variant:normal;text-decoration:underline;-webkit-text-decoration-skip:none;text-decoration-skip-ink:none;vertical-align:baseline;white-space:pre;white-space:pre-wrap;">CLASSLA-Stanza pipeline</span></a><span style="font-size:11pt;font-family:Arial,sans-serif;color:#000000;background-color:transparent;font-weight:400;font-style:normal;font-variant:normal;text-decoration:none;vertical-align:baseline;white-space:pre;white-space:pre-wrap;">, which enables state-of-the-art linguistic processing of Slovenian, Croatian, Serbian, Macedonian and Bulgarian language.</span></p>
<br>
<p dir="ltr"
style="line-height:1.38;margin-top:0pt;margin-bottom:0pt;"><span style="font-size:11pt;font-family:Arial,sans-serif;color:#000000;background-color:transparent;font-weight:400;font-style:normal;font-variant:normal;text-decoration:none;vertical-align:baseline;white-space:pre;white-space:pre-wrap;">In addition to covering standard varieties of five South Slavic languages, the pipeline also provides special modules for linguistic annotation of non-standard text and web corpora for Slovenian, Croatian and Serbian. The CLASSLA-Stanza annotation tool supports a total of six tasks: tokenization, morphosyntactic annotation, lemmatization, dependency parsing, semantic role labeling, and named-entity recognition. Some of the main improvements that separate CLASSLA-Stanza from the Stanza pipeline are:</span></p>
<ul
style="margin-top:0;margin-bottom:0;padding-inline-start:48px;">
<li dir="ltr" style="list-style-type:disc;font-size:11pt;font-family:Arial,sans-serif;color:#000000;background-color:transparent;font-weight:400;font-style:normal;font-variant:normal;text-decoration:none;vertical-align:baseline;white-space:pre;" aria-level="1"><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt;" role="presentation"><span style="font-size:11pt;font-family:Arial,sans-serif;color:#000000;background-color:transparent;font-weight:400;font-style:normal;font-variant:normal;text-decoration:none;vertical-align:baseline;white-space:pre;white-space:pre-wrap;">support of external inflectional lexicons which significantly increases performance on morphologically rich languages;</span></p></li>
<li dir="ltr" style="list-style-type:disc;font-size:11pt;font-family:Arial,sans-serif;color:#000000;background-color:transparent;font-weight:400;font-style:normal;font-variant:normal;text-decoration:none;vertical-align:baseline;white-space:pre;" aria-level="1"><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt;" role="presentation"><span style="font-size:11pt;font-family:Arial,sans-serif;color:#000000;background-color:transparent;font-weight:400;font-style:normal;font-variant:normal;text-decoration:none;vertical-align:baseline;white-space:pre;white-space:pre-wrap;">extended training datasets (beyond Universal Dependencies data) for all included models;</span></p></li>
<li dir="ltr" style="list-style-type:disc;font-size:11pt;font-family:Arial,sans-serif;color:#000000;background-color:transparent;font-weight:400;font-style:normal;font-variant:normal;text-decoration:none;vertical-align:baseline;white-space:pre;" aria-level="1"><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt;" role="presentation"><span style="font-size:11pt;font-family:Arial,sans-serif;color:#000000;background-color:transparent;font-weight:400;font-style:normal;font-variant:normal;text-decoration:none;vertical-align:baseline;white-space:pre;white-space:pre-wrap;">use of </span><a href="https://shorturl.at/ehwS2" style="text-decoration:none;" moz-do-not-send="true"><span style="font-size:11pt;font-family:Arial,sans-serif;color:#1155cc;background-color:transparent;font-weight:400;font-style:normal;font-variant:normal;text-decoration:underline;-webkit-text-decoration-skip:none;text-decoration-skip-ink:none;vertical-align:baseline;white-space:pre;white-space:pre-wrap;">CLARIN.SI-embed</span></a><span style="font-size:11pt;font-family:Arial,sans-serif;color:#000000;background-color:transparent;font-weight:400;font-style:normal;font-variant:normal;text-decoration:none;vertical-align:baseline;white-space:pre;white-space:pre-wrap;"> word embeddings, trained on significantly larger and more diverse datasets than embeddings used by Stanza;</span></p></li>
<li dir="ltr" style="list-style-type:disc;font-size:11pt;font-family:Arial,sans-serif;color:#000000;background-color:transparent;font-weight:400;font-style:normal;font-variant:normal;text-decoration:none;vertical-align:baseline;white-space:pre;" aria-level="1"><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt;" role="presentation"><span style="font-size:11pt;font-family:Arial,sans-serif;color:#000000;background-color:transparent;font-weight:400;font-style:normal;font-variant:normal;text-decoration:none;vertical-align:baseline;white-space:pre;white-space:pre-wrap;">specific modules for standard, non-standard and web text.</span></p></li>
</ul>
<br>
<span style="font-size:11pt;font-family:Arial,sans-serif;color:#000000;background-color:transparent;font-weight:400;font-style:normal;font-variant:normal;text-decoration:none;vertical-align:baseline;white-space:pre;white-space:pre-wrap;">As a result, we are happy to report that the CLASSLA-Stanza significantly outperforms Stanza, with error reduction between 34% and 98% on the Slovenian official benchmark (see table below which reports the performance using the Micro F1 score). You can find more details on the pipeline improvements and training settings in a technical report “</span><a
href="https://arxiv.org/abs/2308.04255" style="text-decoration:none;"
moz-do-not-send="true"><span style="font-size:11pt;font-family:Arial,sans-serif;color:#1155cc;background-color:transparent;font-weight:400;font-style:normal;font-variant:normal;text-decoration:underline;-webkit-text-decoration-skip:none;text-decoration-skip-ink:none;vertical-align:baseline;white-space:pre;white-space:pre-wrap;">CLASSLA-Stanza: The Next Step for Linguistic Processing of South Slavic Languages</span></a><span style="font-size:11pt;font-family:Arial,sans-serif;color:#000000;background-color:transparent;font-weight:400;font-style:normal;font-variant:normal;text-decoration:none;vertical-align:baseline;white-space:pre;white-space:pre-wrap;">” (Terčon & Ljubešić, 2023).
</span></b><br>
<b
style="font-weight:normal;"
id="docs-internal-guid-0e1ba3a1-7fff-437f-9695-5fff78774c03"><span style="font-size:11pt;font-family:Arial,sans-serif;color:#000000;background-color:transparent;font-weight:400;font-style:normal;font-variant:normal;text-decoration:none;vertical-align:baseline;white-space:pre;white-space:pre-wrap;"><b style="font-weight:normal;" id="docs-internal-guid-e6d5aec1-7fff-370a-4503-1ef099d386db"><span style="font-size:11pt;font-family:Arial,sans-serif;color:#000000;background-color:transparent;font-weight:400;font-style:normal;font-variant:normal;text-decoration:none;vertical-align:baseline;white-space:pre;white-space:pre-wrap;"><span style="border:none;display:inline-block;overflow:hidden;width:602px;height:119px;"><img src="https://lh3.googleusercontent.com/uqUHPqtRZ4wHha7bH22-vU7QNLgUrPyXtsSlXQBM060Q-5AX_5I6B0FP_NJkvqb2ri-GDtTmFH32VdVDLz9cF80rbHCvkIsX3ElQs9xTWVzjWQIXlllCDVEuvN_Iy0HvsX_xmh-f-AiddMx3sFhFmqY" style="margin-left: 0px; margin-top: 0px;" moz-do-not-send="true" width="602" height="119"></span></span></b>
</span></b><br>
<b
style="font-weight:normal;"
id="docs-internal-guid-0e1ba3a1-7fff-437f-9695-5fff78774c03"><span style="font-size:11pt;font-family:Arial,sans-serif;color:#000000;background-color:transparent;font-weight:400;font-style:normal;font-variant:normal;text-decoration:none;vertical-align:baseline;white-space:pre;white-space:pre-wrap;"><b style="font-weight:normal;" id="docs-internal-guid-8d8470e8-7fff-9f07-6163-ad112fa16fb9"><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt;"><span style="font-size:11pt;font-family:Arial,sans-serif;color:#000000;background-color:transparent;font-weight:400;font-style:normal;font-variant:normal;text-decoration:none;vertical-align:baseline;white-space:pre;white-space:pre-wrap;">You can use CLASSLA-Stanza as a </span><a href="https://pypi.org/project/classla/" style="text-decoration:none;" moz-do-not-send="true"><span style="font-size:11pt;font-family:Arial,sans-serif;color:#1155cc;background-color:transparent;font-weight:400;font-style:normal;font-variant:normal;text-decoration:underline;-webkit-text-decoration-skip:none;text-decoration-skip-ink:none;vertical-align:baseline;white-space:pre;white-space:pre-wrap;">python library</span></a><span style="font-size:11pt;font-family:Arial,sans-serif;color:#000000;background-color:transparent;font-weight:400;font-style:normal;font-variant:normal;text-decoration:none;vertical-align:baseline;white-space:pre;white-space:pre-wrap;"> (documentation is available </span><a href="https://github.com/clarinsi/classla" style="text-decoration:none;" moz-do-not-send="true"><span style="font-size:11pt;font-family:Arial,sans-serif;color:#1155cc;background-color:transparent;font-weight:400;font-style:normal;font-variant:normal;text-decoration:underline;-webkit-text-decoration-skip:none;text-decoration-skip-ink:none;vertical-align:baseline;white-space:pre;white-space:pre-wrap;">here</span></a><span style="font-size:11pt;font-family:Arial,sans-serif;color:#000000;background-color:transparent;font-weight:400;font-style:normal;font-variant:normal;text-decoration:none;vertical-align:baseline;white-space:pre;white-space:pre-wrap;">) or via an </span><a href="https://orodja.cjvt.si/oznacevalnik/eng/" style="text-decoration:none;" moz-do-not-send="true"><span style="font-size:11pt;font-family:Arial,sans-serif;color:#1155cc;background-color:transparent;font-weight:400;font-style:normal;font-variant:normal;text-decoration:underline;-webkit-text-decoration-skip:none;text-decoration-skip-ink:none;vertical-align:baseline;white-space:pre;white-space:pre-wrap;">online service</span></a><span style="font-size:11pt;font-family:Arial,sans-serif;color:#000000;background-color:transparent;font-weight:400;font-style:normal;font-variant:normal;text-decoration:none;vertical-align:baseline;white-space:pre;white-space:pre-wrap;"> (currently available for Slovenian, other languages and modules coming soon). Separate models are also freely available at the </span><a href="https://shorturl.at/iquyX" style="text-decoration:none;" moz-do-not-send="true"><span style="font-size:11pt;font-family:Arial,sans-serif;color:#1155cc;background-color:transparent;font-weight:400;font-style:normal;font-variant:normal;text-decoration:underline;-webkit-text-decoration-skip:none;text-decoration-skip-ink:none;vertical-align:baseline;white-space:pre;white-space:pre-wrap;">CLARIN.SI repository</span></a><span style="font-size:11pt;font-family:Arial,sans-serif;color:#000000;background-color:transparent;font-weight:400;font-style:normal;font-variant:normal;text-decoration:none;vertical-align:baseline;white-space:pre;white-space:pre-wrap;">.</span></p>
<p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt;"><span style="font-size:11pt;font-family:Arial,sans-serif;color:#000000;background-color:transparent;font-weight:400;font-style:normal;font-variant:normal;text-decoration:none;vertical-align:baseline;white-space:pre;white-space:pre-wrap;">
</span></p><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt;"><span style="font-size:11pt;font-family:Arial,sans-serif;color:#000000;background-color:transparent;font-weight:400;font-style:normal;font-variant:normal;text-decoration:none;vertical-align:baseline;white-space:pre;white-space:pre-wrap;">These results would not be possible without immense efforts in developing high-quality training datasets together with our collaborators all around Europe. We wish to use this opportunity to most warmly thank all of them!</span></p></b>
Best regards,
Nikola, Taja, and many other CLASSLAers</span></b><br>
</td>
</tr>
<tr>
<td
height="30"> </td>
</tr>
</tbody>
</table>
</td>
</tr>
</tbody>
</table>
</td>
</tr>
</tbody>
</table>
<table style="width: 640px;
min-width: 640px;" width="640"
cellspacing="0" cellpadding="0"
border="0" align="center">
<tbody>
<tr>
<td style="line-height: 10px;
min-height: 10px;"
height="10"> </td>
</tr>
</tbody>
</table>
</td>
</tr>
</tbody>
</table>
</td>
</tr>
</tbody>
</table>
<table width="640" cellspacing="0" cellpadding="0"
border="0" bgcolor="#e6f4ff" align="center">
<tbody>
<tr>
<td>
<table style="width: 640px; min-width:
640px;" width="640" cellspacing="0"
cellpadding="0" border="0"
bgcolor="#e6f4ff" align="center">
<tbody>
<tr>
<td>
<table style="width: 640px;
min-width: 640px;" width="640"
cellspacing="0" cellpadding="0"
border="0" align="center">
<tbody>
<tr>
<td style="line-height: 20px;
min-height: 20px;"
height="20"> </td>
</tr>
</tbody>
</table>
<table style="width: 640px;
min-width: 640px;" width="640"
cellspacing="0" cellpadding="0"
border="0" align="center">
<tbody>
<tr>
<td style="padding: 0px 40px;"
align="center">
<table width="100%"
cellspacing="0"
cellpadding="0" border="0"
align="center">
<tbody>
<tr>
<td
style="font-family:
Poppins,sans-serif;
font-size: 14px;
font-weight: bold;
line-height: 21px;
color: #111111;"
align="left"><a
href="https://www.clarin.si/info/k-centre/"
target="_blank"
rel="noopener
noreferrer"
moz-do-not-send="true">CLASSLA:
The Knowledge
Centre for South
Slavic Languages</a></td>
</tr>
</tbody>
</table>
</td>
</tr>
</tbody>
</table>
<table style="width: 640px;
min-width: 640px;" width="640"
cellspacing="0" cellpadding="0"
border="0" align="center">
<tbody>
<tr>
<td height="10"> </td>
</tr>
</tbody>
</table>
<table style="width: 640px;
min-width: 640px;" width="640"
cellspacing="0" cellpadding="0"
border="0" align="center">
<tbody>
<tr>
<td style="padding: 0px 40px;"
align="center">
<table width="100%"
cellspacing="0"
cellpadding="0" border="0"
align="center">
<tbody>
<tr>
<td align="center">
<table style="width:
267px; min-width:
267px;"
width="267"
cellspacing="0"
cellpadding="0"
border="0"
align="left">
<tbody>
<tr>
<td
id="m_925030267947577449gmail-m_6504557075424313283gmail-m_-5089897522223699477footerText-10"
style="font-family: Poppins,sans-serif; font-size: 12px; line-height:
18px; color:
#111111;"
align="left">
<p
style="margin-top:
0px;
margin-bottom:
10px;"><a
href="http://clarin.si/"
target="_blank" rel="noopener noreferrer" moz-do-not-send="true">CLARIN.SI</a></p>
<p
style="margin-top:
0px;
margin-bottom:
10px;">Jožef
Stefan
Institute</p>
<p
style="margin-top:
0px;
margin-bottom:
0px;">Jamova
cesta 39,
Ljubljana<br>
Slovenia</p>
</td>
</tr>
<tr>
<td
height="25"> </td>
</tr>
</tbody>
</table>
<table style="width:
267px; min-width:
267px;"
width="267"
cellspacing="0"
cellpadding="0"
border="0"
align="right">
<tbody>
<tr>
<td
id="m_925030267947577449gmail-m_6504557075424313283gmail-m_-5089897522223699477footerUnsubscribeText-10"
style="font-family: Poppins,sans-serif; font-size: 12px; line-height:
18px; color:
#111111;"
align="right">
<p
style="margin-top:
0px;
margin-bottom:
0px;"><br>
<span
style="font-size:
10px;"></span></p>
</td>
</tr>
<tr>
<td
height="10"> </td>
</tr>
<tr>
<td
style="font-family:
Poppins,sans-serif; font-size: 12px; line-height: 18px; color: #111111;"
align="right"> </td>
</tr>
</tbody>
</table>
</td>
</tr>
</tbody>
</table>
</td>
</tr>
</tbody>
</table>
</td>
</tr>
</tbody>
</table>
</td>
</tr>
</tbody>
</table>
</td>
</tr>
</tbody>
</table>
</div>
</div>
<div dir="ltr"> </div>
</div>
</div>
<div class="pre" style="margin: 0; padding: 0; font-family:
monospace;"> </div>
</body>
</html>