A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit <a rel="external noopener" href="http://www.cs.otago.ac.nz/homepages/andrew/papers/2015-3.pdf">the original URL</a>. The file type is <code>application/pdf</code>.
Filters
Improving Throughput of a Pipeline Model Indexer
<span title="">2015</span>
<i title="ACM Press">
<a target="_blank" rel="noopener" href="https://fatcat.wiki/container/ym4qbiso25flxacjl7t5dh6k3i" style="color: black;">Proceedings of the 20th Australasian Document Computing Symposium on ZZZ - ADCS '15</a>
</i>
Preserved Fulltext
Information retrieval is also an inherently parallel process, indexing one document is independent of another document. ...
There are many competing models for the indexing process of an information retrieval system, one of which is a pipeline based model. ...
ACKNOWLEDGEMENTS The authors would like to thank the Queensland University of Technology for providing use of the machines to perform experimentation. ...
<span class="external-identifiers">
<a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1145/2838931.2838943">doi:10.1145/2838931.2838943</a>
<a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/adcs/CraneTE15.html">dblp:conf/adcs/CraneTE15</a>
<a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/46iefkqhsrakzhw53gp7wkcvdq">fatcat:46iefkqhsrakzhw53gp7wkcvdq</a>
</span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170418120813/http://www.cs.otago.ac.nz/homepages/andrew/papers/2015-3.pdf" 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/c9/ec/c9ec85a7f6c26f9a283e6dfaffd2ca0b89458bd6.180px.jpg" alt="fulltext thumbnail" loading="lazy">
</div>
</button>
</a>
<a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1145/2838931.2838943">
<button class="ui left aligned compact blue labeled icon button serp-button">
<i class="external alternate icon"></i>
acm.org
</button>
</a>
Data Fusion for Japanese Term and Character N-gram Search
<span title="">2015</span>
<i title="ACM Press">
<a target="_blank" rel="noopener" href="https://fatcat.wiki/container/ym4qbiso25flxacjl7t5dh6k3i" style="color: black;">Proceedings of the 20th Australasian Document Computing Symposium on ZZZ - ADCS '15</a>
</i>
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2016; you can also visit <a rel="external noopener" href="http://culpepper.io/publications/ycs15-adcs.pdf">the original URL</a>. The file type is <code>application/pdf</code>.
In this study, we explore data fusion techniques to answer the following question: if there are multiple ranked lists of documents from both word and n-gram indexes, can we improve overall effectiveness ...
Our experimental results demonstrate that the combination of the two different segmentation approaches has the potential to significantly outperform the best word-segmented search methods. ...
ADCS, December 08 -09, 2015, Parramatta, NSW, Australia c ⃝ 2015 Copyright held by the owner/author(s). Publication rights licensed to ACM. ...
<span class="external-identifiers">
<a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1145/2838931.2838939">doi:10.1145/2838931.2838939</a>
<a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/adcs/YasukawaCS15.html">dblp:conf/adcs/YasukawaCS15</a>
<a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/a3bdwzns2rh45brzojnzvoiysu">fatcat:a3bdwzns2rh45brzojnzvoiysu</a>
</span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20160620165459/http://culpepper.io/publications/ycs15-adcs.pdf" 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/9d/e8/9de88f341a82a838ff409101e536d8fce1ee5b04.180px.jpg" alt="fulltext thumbnail" loading="lazy">
</div>
</button>
</a>
<a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1145/2838931.2838939">
<button class="ui left aligned compact blue labeled icon button serp-button">
<i class="external alternate icon"></i>
acm.org
</button>
</a>
Text segmentation and Chinese site search
<span title="">2015</span>
<i title="ACM Press">
<a target="_blank" rel="noopener" href="https://fatcat.wiki/container/ym4qbiso25flxacjl7t5dh6k3i" style="color: black;">Proceedings of the 20th Australasian Document Computing Symposium on ZZZ - ADCS '15</a>
</i>
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2016; you can also visit <a rel="external noopener" href="http://david-hawking.net/pubs/cn-segmentation.pdf">the original URL</a>. The file type is <code>application/pdf</code>.
We compare representatives of the two approaches using a 465,000 page crawl and test queries applicable to the university context. 503 pairs of result sets were judged by 56 Chinese students. ...
Automatic segmentation and overlapping bigrams are the most common methods for overcoming the lack of explicit word boundaries in Chinese text. ...
ADCS December 08-09, 2015, Parramatta, NSW, Australia c ACM 978-1-4503-4040-3/15/12 . . . $15.00. http://dx.doi.org/10.1145/2838931.2838940. ...
<span class="external-identifiers">
<a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1145/2838931.2838940">doi:10.1145/2838931.2838940</a>
<a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/adcs/ZhouHT15.html">dblp:conf/adcs/ZhouHT15</a>
<a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/hqpuca6oqzbp3hcolmqx75qaoy">fatcat:hqpuca6oqzbp3hcolmqx75qaoy</a>
</span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20160828134106/http://david-hawking.net/pubs/cn-segmentation.pdf" 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/54/62/5462220bc4bb61ff27e5630e1a6fc647a9563853.180px.jpg" alt="fulltext thumbnail" loading="lazy">
</div>
</button>
</a>
<a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1145/2838931.2838940">
<button class="ui left aligned compact blue labeled icon button serp-button">
<i class="external alternate icon"></i>
acm.org
</button>
</a>
TSDAE: Using Transformer-based Sequential Denoising Auto-Encoder for Unsupervised Sentence Embedding Learning
[article]
<span title="2021-09-10">2021</span>
<i >
arXiv
</i>
<span class="release-stage" >pre-print</span>
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit <a rel="external noopener" href="https://arxiv.org/pdf/2104.06979v3.pdf">the original URL</a>. The file type is <code>application/pdf</code>.
Other Versions
<span title="2021-04-14">2021</span>
<span class="release-stage" >pre-print</span>
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2104.06979v1">arXiv:2104.06979v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/3klmrq6xcjabvfe7yt4p57pnza">fatcat:3klmrq6xcjabvfe7yt4p57pnza</a> </span>
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2104.06979v1">arXiv:2104.06979v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/3klmrq6xcjabvfe7yt4p57pnza">fatcat:3klmrq6xcjabvfe7yt4p57pnza</a> </span>
<span title="2021-08-30">2021</span>
<span class="release-stage" >pre-print</span>
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2104.06979v2">arXiv:2104.06979v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/mrowcqqnvvefrkezlwifuycrzm">fatcat:mrowcqqnvvefrkezlwifuycrzm</a> </span>
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2104.06979v2">arXiv:2104.06979v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/mrowcqqnvvefrkezlwifuycrzm">fatcat:mrowcqqnvvefrkezlwifuycrzm</a> </span>
It can achieve up to 93.1% of the performance of in-domain supervised approaches. ...
A crucial shortcoming of previous studies is the narrow evaluation: Most work mainly evaluates on the single task of Semantic Textual Similarity (STS), which does not require any domain knowledge. ...
Acknowledgments This work has been supported by the German Research Foundation (DFG) as part of the UKP-SQuARE project (grant GU 798/29-1), by the Eu- ...
<span class="external-identifiers">
<a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2104.06979v3">arXiv:2104.06979v3</a>
<a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/aw32qx352vbkdje43kpfwkcu6y">fatcat:aw32qx352vbkdje43kpfwkcu6y</a>
</span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210916053546/https://arxiv.org/pdf/2104.06979v3.pdf" 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/b6/64/b6647280615f667dd7418bfb9b13d828a22c1cfe.180px.jpg" alt="fulltext thumbnail" loading="lazy">
</div>
</button>
</a>
<a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2104.06979v3" title="arxiv.org access">
<button class="ui compact blue labeled icon button serp-button">
<i class="file alternate outline icon"></i>
arxiv.org
</button>
</a>