<div dir="ltr">Call for participation.<div><br></div><div><br></div><div>Dear list members,</div><div><br></div><div style>We invite any of you interested in the application of corpus linguistics methods to datasets which contain substantial "noise" (e.g. spelling variation in historical, learner and web corpora) to join us in <b>Lancaster</b> on <b>July 22nd</b> for the<b> Corpus Analysis with Noise in the Signal workshop (CANS 2013)</b>.</div>
<div style><br></div><div style>The workshop will offer participants the chance to gain insights into the characteristics of the noise in different language varieties, the effect of the noise on different corpus linguistic techniques and different methods to either negate the noise or to produce more robust tools that can accurately process noisy textual data. A wide range of presentations will be given, as the programme below shows.</div>
<div style><br></div><div style><br></div><div style>+++++++++++++++++++++++++++++++++++++++</div><div style><div><br></div><div>Turo Hiltunen & Jukka Tyrkkö</div><div>Tagging Early Modern English Medical Texts (1500-1700)</div>
<div><br></div><div>Marcel Bollmann</div><div>Spelling normalization of historical German with sparse training data</div><div><br></div><div>Felix Bildhauer & Roland Schäfer</div><div>Token-level noise in large Web corpora and nondestructive normalization for linguistic applications</div>
<div><br></div><div>Elena Klyachko, Timofey Arkhangelskiy, Olesya Kisselev & Ekaterina Rakhilina Automatic error detection in Russian learner language</div><div><br></div><div>Maura Ratia</div><div>Performing keyword analysis on automatically vs. manually VARDed corpora: The case of Stuart plague treatises</div>
<div><br></div><div>Verena Möller<br></div><div>Retrieving passive structures from the Secondary-Level Corpus of Learner English (SCooLE) - How can we make part-of-speech tagging more successful?</div><div><br></div><div>
+++++++++++++++++++++++++++++++++++++++<br></div><div><br></div><div style>There will also be software demonstrations and a round-table discussion of the challenges associated with corpus analysis with "noisy" data, including questions such as:</div>
<div style><div><ul style><li style>What are the key challenges of dealing with noisy textual data going forward?<br></li><li style>When should we leave "noise" where it is? And for what reason(s)?<br></li><li style>
What are the dangers of ignoring the noise?</li></ul><div><br></div></div><div style>Further details of the workshop are available here: <a href="http://ucrel.lancs.ac.uk/cans2013/">http://ucrel.lancs.ac.uk/cans2013/</a></div>
<div style><br></div><div style>The workshop is held prior to the Corpus Linguistics 2013 conference at Lancaster University. Details for registration for the workshop, and also the conference itself are here: <a href="http://ucrel.lancs.ac.uk/cl2013/register.php">http://ucrel.lancs.ac.uk/cl2013/register.php</a></div>
<div style><br></div><div style>We look forward to seeing you in Lancaster.</div><div style><br></div><div style>Thanks and best wishes,</div><div style><br></div><div style>Alistair Baron,</div><div style>Paul Rayson,</div>
<div style>Dawn Archer</div><div style>(CANS 2013 workshop organising committee)</div><div style><a href="mailto:cans2013@comp.lancs.ac.uk">cans2013@comp.lancs.ac.uk</a></div></div></div></div>