A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit <a rel="external noopener" href="https://jair.org/index.php/jair/article/download/11191/26400">the original URL</a>. The file type is <code>application/pdf</code>.
<i title="AI Access Foundation">
<a target="_blank" rel="noopener" href="https://fatcat.wiki/container/4ax4efcwajcgvidb6hcg6mwx4a" style="color: black;">The Journal of Artificial Intelligence Research</a>
Extracting information about entities remains an important research area. This paper addresses the problem of corpus-level entity typing, i.e., inferring from a large corpus that an entity is a member of a class, such as "food" or "artist". The application of entity typing we are interested in is knowledge base completion, specifically, to learn which classes an entity is a member of. We propose FIGMENT to tackle this problem. FIGMENT is embedding-based and combines (i) a global model that<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1613/jair.5601">doi:10.1613/jair.5601</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ktuwhpaysjajdfhim6yothitbu">fatcat:ktuwhpaysjajdfhim6yothitbu</a> </span>
more »... tes scores based on global information of an entity and (ii) a context model that first evaluates the individual occurrences of an entity and then aggregates the scores. Each of the two proposed models has specific properties. For the global model, learning high-quality entity representations is crucial because it is the only source used for the predictions. Therefore, we introduce representations using the name and contexts of entities on the three levels of entity, word, and character. We show that each level provides complementary information and a multi-level representation performs best. For the context model, we need to use distant supervision since there are no context-level labels available for entities. Distantly supervised labels are noisy and this harms the performance of models. Therefore, we introduce and apply new algorithms for noise mitigation using multi-instance learning. We show the effectiveness of our models on a large entity typing dataset built from Freebase.
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20190427054535/https://jair.org/index.php/jair/article/download/11191/26400" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/78/48/78483382dfe2c3bdeed7b63c753531255b1e461a.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1613/jair.5601"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> Publisher / doi.org </button> </a>