<html>
<head>
<meta http-equiv="Content-Type" content="text/html; charset=us-ascii">
</head>
<body style="word-wrap: break-word; -webkit-nbsp-mode: space; -webkit-line-break: after-white-space; ">
<br>
<div><br>
<blockquote type="cite">
<div style="word-wrap: break-word; -webkit-nbsp-mode: space; -webkit-line-break: after-white-space; ">
</div>
</blockquote>
<div style="word-wrap: break-word; -webkit-nbsp-mode: space; -webkit-line-break: after-white-space; ">
<div>
<div>NOTE: This email was sent earlier, but the link provided pointed to the wrong paper - this has now been corrected. Apologies for any inconvenience caused. </div>
<div><span class="Apple-style-span" style="border-collapse: separate; font-family: Helvetica; font-style: normal; font-variant: normal; font-weight: normal; letter-spacing: normal; line-height: normal; orphans: 2; text-align: -webkit-auto; text-indent: 0px; text-transform: none; white-space: normal; widows: 2; word-spacing: 0px; -webkit-border-horizontal-spacing: 0px; -webkit-border-vertical-spacing: 0px; -webkit-text-decorations-in-effect: none; -webkit-text-size-adjust: auto; -webkit-text-stroke-width: 0px; font-size: medium; ">
<div style="margin-top: 0px; margin-right: 0px; margin-bottom: 0px; margin-left: 0px; ">
<span style="font-family: Helvetica; font-size: medium; "><br>
</span></div>
<div style="margin-top: 0px; margin-right: 0px; margin-bottom: 0px; margin-left: 0px; ">
<span style="font-family: Helvetica; font-size: medium; ">--------------</span></div>
<div style="margin-top: 0px; margin-right: 0px; margin-bottom: 0px; margin-left: 0px; ">
<span style="font-family: Helvetica; font-size: medium; "><br>
</span></div>
<div style="margin-top: 0px; margin-right: 0px; margin-bottom: 0px; margin-left: 0px; ">
<span style="font-family: Helvetica; font-size: medium; "><br>
</span></div>
<div style="margin-top: 0px; margin-right: 0px; margin-bottom: 0px; margin-left: 0px; ">
<span style="font-family: Helvetica; font-size: medium; ">Discovering Robust Embeddings in (Dis)Similarity Space for High-Dimensional Lingustic Features</span></div>
<div style="word-wrap: break-word; -webkit-nbsp-mode: space; -webkit-line-break: after-white-space; ">
<div>
<div>
<div style="word-wrap: break-word; -webkit-nbsp-mode: space; -webkit-line-break: after-white-space; ">
<div>
<div style="word-wrap: break-word; -webkit-nbsp-mode: space; -webkit-line-break: after-white-space; ">
<div>
<div>
<div style="word-wrap: break-word; -webkit-nbsp-mode: space; -webkit-line-break: after-white-space; ">
<div>
<div style="word-wrap: break-word; -webkit-nbsp-mode: space; -webkit-line-break: after-white-space; ">
<span class="Apple-style-span" style="orphans: 2; text-align: -webkit-auto; text-indent: 0px; widows: 2; -webkit-text-decorations-in-effect: none; ">
<div style="word-wrap: break-word; -webkit-nbsp-mode: space; -webkit-line-break: after-white-space; ">
<div>
<div><br>
</div>
<div>Tingting Mu, Makoto Miwa, Jun'ichi Tsujii and Sophia Ananiadou</div>
<div><br>
</div>
<div>Computational Intelligence 2012</div>
<div><br>
</div>
<div><a href="http://onlinelibrary.wiley.com/doi/10.1111/j.1467-8640.2012.00452.x/abstract">http://onlinelibrary.wiley.com/doi/10.1111/j.1467-8640.2012.00452.x/abstract</a></div>
<div><br>
</div>
<div><br>
</div>
<div>Abstract</div>
<div>========</div>
<div><br>
</div>
<div>
<div>Recent research has shown the effectiveness of rich feature representation for tasks in natural language</div>
<div>processing (NLP). However, exceedingly large number of features do not always improve classification performance.</div>
<div>They may contain redundant information, lead to noisy feature presentations, and also render the learning algorithms</div>
<div>intractable. In this paper, we propose a supervised embedding framework that modifies the relative positions between</div>
<div>instances to increase the compatibility between the input features and the output labels and meanwhile preserves the</div>
<div>local distribution of the original data in the embedded space. The proposed framework attempts to support flexible</div>
<div>balance between the preservation of intrinsic geometry and the enhancement of class separability for both interclass</div>
<div>and intraclass instances. It takes into account characteristics of linguistic features by using an inner product-based</div>
<div>optimization template. (Dis)similarity features, also known as empirical kernel mapping, is employed to enable</div>
<div>computationally tractable processing of extremely high-dimensional input, and also to handle nonlinearities in</div>
<div>embedding generation when necessary. Evaluated on two NLP tasks with six data sets, the proposed framework</div>
<div>provides better classification performance than the support vector machine without using any dimensionality</div>
<div>reduction technique. It also generates embeddings with better class discriminability as compared to many existing</div>
<div>embedding algorithms.</div>
</div>
</div>
</div>
</span></div>
</div>
</div>
</div>
</div>
</div>
</div>
</div>
</div>
</div>
</div>
</span></div>
</div>
<br>
<div><span class="Apple-style-span" style="border-collapse: separate; font-family: Helvetica; font-style: normal; font-variant: normal; font-weight: normal; letter-spacing: normal; line-height: normal; orphans: 2; text-align: -webkit-auto; text-indent: 0px; text-transform: none; white-space: normal; widows: 2; word-spacing: 0px; -webkit-border-horizontal-spacing: 0px; -webkit-border-vertical-spacing: 0px; -webkit-text-decorations-in-effect: none; -webkit-text-size-adjust: auto; -webkit-text-stroke-width: 0px; font-size: medium; "><span class="Apple-style-span" style="border-collapse: separate; font-family: Helvetica; font-style: normal; font-variant: normal; font-weight: normal; letter-spacing: normal; line-height: normal; orphans: 2; text-align: -webkit-auto; text-indent: 0px; text-transform: none; white-space: normal; widows: 2; word-spacing: 0px; -webkit-border-horizontal-spacing: 0px; -webkit-border-vertical-spacing: 0px; -webkit-text-decorations-in-effect: none; -webkit-text-size-adjust: auto; -webkit-text-stroke-width: 0px; font-size: medium; "><span class="Apple-style-span" style="border-collapse: separate; font-family: Helvetica; font-style: normal; font-variant: normal; font-weight: normal; letter-spacing: normal; line-height: normal; orphans: 2; text-align: -webkit-auto; text-indent: 0px; text-transform: none; white-space: normal; widows: 2; word-spacing: 0px; -webkit-border-horizontal-spacing: 0px; -webkit-border-vertical-spacing: 0px; -webkit-text-decorations-in-effect: none; -webkit-text-size-adjust: auto; -webkit-text-stroke-width: 0px; font-size: medium; ">
<div style="word-wrap: break-word; -webkit-nbsp-mode: space; -webkit-line-break: after-white-space; ">
<span class="Apple-style-span" style="border-collapse: separate; font-family: Helvetica; font-style: normal; font-variant: normal; font-weight: normal; letter-spacing: normal; line-height: normal; orphans: 2; text-align: -webkit-auto; text-indent: 0px; text-transform: none; white-space: normal; widows: 2; word-spacing: 0px; -webkit-border-horizontal-spacing: 0px; -webkit-border-vertical-spacing: 0px; -webkit-text-decorations-in-effect: none; -webkit-text-size-adjust: auto; -webkit-text-stroke-width: 0px; font-size: medium; ">
<div style="word-wrap: break-word; -webkit-nbsp-mode: space; -webkit-line-break: after-white-space; ">
<div><br class="Apple-interchange-newline">
--------</div>
<div><br>
</div>
<div>Paul Thompson<br>
Research Associate<br>
School of Computer Science<br>
National Centre for Text Mining<br>
Manchester Institute of Biotechnology<br>
University of Manchester<br>
131 Princess Street<br>
Manchester<br>
M1 7DN<br>
UK<br>
Tel: 0161 306 3091<br>
<a href="http://personalpages.manchester.ac.uk/staff/Paul.Thompson/">http://personalpages.manchester.ac.uk/staff/Paul.Thompson/</a></div>
<div><br>
</div>
</div>
</span></div>
</span></span></span></div>
</div>
</div>
<div><span class="Apple-style-span" style="border-collapse: separate; color: rgb(0, 0, 0); font-family: Helvetica; font-style: normal; font-variant: normal; font-weight: normal; letter-spacing: normal; line-height: normal; orphans: 2; text-align: -webkit-auto; text-indent: 0px; text-transform: none; white-space: normal; widows: 2; word-spacing: 0px; -webkit-border-horizontal-spacing: 0px; -webkit-border-vertical-spacing: 0px; -webkit-text-decorations-in-effect: none; -webkit-text-size-adjust: auto; -webkit-text-stroke-width: 0px; font-size: medium; "><span class="Apple-style-span" style="border-collapse: separate; color: rgb(0, 0, 0); font-family: Helvetica; font-style: normal; font-variant: normal; font-weight: normal; letter-spacing: normal; line-height: normal; orphans: 2; text-align: -webkit-auto; text-indent: 0px; text-transform: none; white-space: normal; widows: 2; word-spacing: 0px; -webkit-border-horizontal-spacing: 0px; -webkit-border-vertical-spacing: 0px; -webkit-text-decorations-in-effect: none; -webkit-text-size-adjust: auto; -webkit-text-stroke-width: 0px; font-size: medium; "><span class="Apple-style-span" style="border-collapse: separate; color: rgb(0, 0, 0); font-family: Helvetica; font-style: normal; font-variant: normal; font-weight: normal; letter-spacing: normal; line-height: normal; orphans: 2; text-align: -webkit-auto; text-indent: 0px; text-transform: none; white-space: normal; widows: 2; word-spacing: 0px; -webkit-border-horizontal-spacing: 0px; -webkit-border-vertical-spacing: 0px; -webkit-text-decorations-in-effect: none; -webkit-text-size-adjust: auto; -webkit-text-stroke-width: 0px; font-size: medium; ">
<div style="word-wrap: break-word; -webkit-nbsp-mode: space; -webkit-line-break: after-white-space; ">
<span class="Apple-style-span" style="border-collapse: separate; color: rgb(0, 0, 0); font-family: Helvetica; font-style: normal; font-variant: normal; font-weight: normal; letter-spacing: normal; line-height: normal; orphans: 2; text-align: -webkit-auto; text-indent: 0px; text-transform: none; white-space: normal; widows: 2; word-spacing: 0px; -webkit-border-horizontal-spacing: 0px; -webkit-border-vertical-spacing: 0px; -webkit-text-decorations-in-effect: none; -webkit-text-size-adjust: auto; -webkit-text-stroke-width: 0px; font-size: medium; ">
<div style="word-wrap: break-word; -webkit-nbsp-mode: space; -webkit-line-break: after-white-space; ">
<br>
<div><br>
</div>
</div>
</span><br class="Apple-interchange-newline">
</div>
</span><br class="Apple-interchange-newline">
</span><br class="Apple-interchange-newline">
</span></div>
<br>
</body>
</html>