Content deleted Content added
Neonrights (talk | contribs) m →Models |
Neonrights (talk | contribs) Added external links to common datasets |
||
Line 7:
== Models ==
===
Barzilay and Lee<ref name=Barzilay>{{cite conference|last1=Barzilay|first1=Regina|last2=Lee|first2=Lillian|title=Learning to Paraphrase: An Unsupervised Approach Using Multiple-Sequence Alignment|book-title=Proceedings of HLT-NAACL 2003|date=May-June 2003|url=http://www.cs.cornell.edu/home/llee/papers/statpar.home.html}}</ref> proposed a method to generate paraphrases through the usage of monolingual [[parallel text|parallel corpora]], namely news articles covering the same event on the same day. Training consists of using "[[multiple sequence alignment|multi-sequence alignment]] to generate sentence-level paraphrases... from [an] unannotated corpus data", as such it can be considered an instance of [[unsupervised learning]]. The main goals of the training algorithm are thus
Line 21:
<ref name=Socher>{{Citation|last1=Socher|first1=Richard|last2=Huang|first2=Eric|last3=Pennington|first3=Jeffrey|last4=Ng|first4=Andrew|last5=Manning|first5=Christopher|title=Dynamic Pooling and Unfolding Recursive Autoencoders for Paraphrase Detection|booktitle=Advances in Neural Information Processing Systems 24|year=2011|url=http://www.socher.org/index.php/Main/DynamicPoolingAndUnfoldingRecursiveAutoencodersForParaphraseDetection}}</ref>
=== Skip-
<ref name=Kiros>{{Citation|last1=Kiros|first1=Ryan|last2=Zhu|first2=Yukun|last3=Salakhutdinov|first3=Ruslan|last4=Zemel|first4=Richard|last5=Torralba|first5=Antonio|last6=Urtasun|first6=Raquel|last7=Fidler|first7=Sanja|title=Skip-Thought Vectors|year=2015|url=https://arxiv.org/abs/1506.06726}}</ref>
== Evaluation
==
* [https://www.microsoft.com/en-us/download/details.aspx?id=52398] - Microsoft Research Paraphrase Corpus
* [http://paraphrase.org/#/] - Paraphrase Database (PPDB)
== References ==
| |||