@InProceedings{hazem-boussaha-hernandez:2017:RANLP,
  author    = {Hazem, Amir  and  Boussaha, Basma El Amel  and  Hernandez, Nicolas},
  title     = {MappSent: a Textual Mapping Approach for Question-to-Question Similarity},
  booktitle = {Proceedings of the International Conference Recent Advances in Natural Language Processing, RANLP 2017},
  month     = {September},
  year      = {2017},
  address   = {Varna, Bulgaria},
  publisher = {INCOMA Ltd.},
  pages     = {291--300},
  abstract  = {Since the advent of word embedding methods, the representation of longer pieces
	of texts such as sentences and paragraphs is gaining more and more interest,
	especially for textual similarity tasks. \citet{Mikolov2013} have demonstrated
	that words and phrases exhibit linear structures that allow to meaningfully
	combine words by an element-wise addition of their vector representations.   
	Recently, \citet{arora2017} have shown that removing the projections of the
	weighted average sum of word embedding vectors on their first principal
	components, outperforms sophisticated supervised methods including RNN's and
	LSTM's. Inspired by \citet{Mikolov2013,arora2017} findings and by a bilingual
	word mapping technique presented in \citet{artetxe2016learning}, we introduce
	MappSent, a novel approach for textual similarity. Based on a linear sentence
	embedding representation, its principle is to build a matrix that maps
	sentences in a joint-subspace where similar sets of sentences are pushed
	closer. We evaluate our approach on  the SemEval 2016/2017 question-to-question
	similarity task and show that overall MappSent                                     
	achieves
	competitive
	results
	and outperforms in most cases state-of-art methods.},
  url       = {https://doi.org/10.26615/978-954-452-049-6_040}
}