diff --git a/bilder/pngfuel-friends.png b/bilder/pngfuel-friends.png new file mode 100644 index 0000000000000000000000000000000000000000..563466b31527ab765bac22cd92dd7a84d012da15 Binary files /dev/null and b/bilder/pngfuel-friends.png differ diff --git a/references.bib b/references.bib index ffcbcb7ed3d5ce1b93d09c05ba1d9785fadc2c5b..99cd50580b0ee4a621da3fd358622c2232336e8e 100755 --- a/references.bib +++ b/references.bib @@ -45,4 +45,45 @@ numpages = {6}, location = {Las Cruces, New Mexico}, series = {ACL ’94} +} +@inproceedings{pennington2014glove, + title = {{G}love: Global Vectors for Word Representation}, + author = {Pennington, Jeffrey and Socher, Richard and Manning, Christopher}, + booktitle = {Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing ({EMNLP})}, + month = {10}, + year = {2014}, + address = {Doha, Qatar}, + publisher = {Association for Computational Linguistics}, + url = {https://doi.org/10.3115/v1/D14-1162}, + doi = {10.3115/v1/D14-1162}, + pages = "1532--1543" +} +@article{Peters:2018ELMo, + author = {Matthew E. Peters and Mark Neumann and Mohit Iyyer and Matt Gardner and Christopher Clark and Kenton Lee}, + title = {Deep contextualized word representations}, + journal = {CoRR}, + year = {2018}, + url = {http://arxiv.org/abs/1802.05365}, + archivePrefix = {arXiv}, + eprint = {1802.05365} +} +@article{devlin2018bert, + author = {Jacob Devlin and Ming{-}Wei Chang and Kenton Lee and Kristina Toutanova}, + title = {{BERT:} Pre-training of Deep Bidirectional Transformers for Language Understanding}, + journal = {CoRR}, + year = {2018}, + url = {http://arxiv.org/abs/1810.04805}, + archivePrefix = {arXiv}, + eprint = {1810.04805} +} +@inproceedings{Armand:2017FastText, + title = {Bag of Tricks for Efficient Text Classification}, + author = {Joulin, Armand and Grave, Edouard and Bojanowski, Piotr and Mikolov, Tomas}, + booktitle = {Proceedings of the 15th Conference of the {E}uropean Chapter of the Association for Computational Linguistics}, + month = {04}, + year = {2017}, + address = {Valencia, Spain}, + publisher = {Association for Computational Linguistics}, + url = {https://doi.org/10.18653/v1/E17-2068}, + pages = {427--431} } \ No newline at end of file diff --git a/slides/methods.tex b/slides/methods.tex index db6338a7198175fcbff54fa41701216b27eb25d5..8d30c13b46e0b6eab2f6bfede9ecaaa93d0e9778 100644 --- a/slides/methods.tex +++ b/slides/methods.tex @@ -51,23 +51,27 @@ \begin{itemize} \item For ranking the arguments, we measured the semantic similarity between the premises and conclusions - \item Each argument was embedded word-wise in an averaged vector space - \item The resulting similarity was calculated by using $cos(c, p)$ - \item In the course of this experiment, we used three different embeddings - \begin{itemize} - \item BERT\footnote{J. Devlin, M. Chang, K. Lee, and K. Toutanova, “BERT: pre-training of deep bidirectional transformers -for language understanding,”} - \item ELMo\footnote{M. E. Peters, M. Neumann, M. Iyyer, M. Gardner, C. Clark, K. Lee, and L. Zettlemoyer, “Deep -contextualized word representations,”} - \item GloVe\footnote{J. Pennington, R. Socher, and C. Manning, “Glove: Global vectors for word representation,”} - \end{itemize} + \item Argument were embedded word-wise in an averaged vector space + \item The resulting similarity was calculated by using $Cos(c, p)$ \end{itemize} + \begin{block}{Embeddings used} + BERT by \cite{devlin2018bert} + + ELMo by \cite{Peters:2018ELMo} + + GloVe by \cite{pennington2014glove} + \end{block} \end{frame} \begin{frame} \frametitle{Sentiment} - \begin{itemize} - \item As another approach we used to measure the positivity of the argument - \item Therefore, we used a sentiment neural network based on FastText\footnote{A. Joulin, E. Grave, P. Bojanowski, and T. Mikolov, “Bag of tricks for efficient text classification,”}, which was - trained on film ratings of IMDb - \end{itemize} + \begin{columns} + \column{0.6\textwidth} + \begin{itemize} + \item As another approach we used to measure the positivity of the argument + \item We used a neural network based on FastText by \cite{Armand:2017FastText} + \item The neural network was trained to indicate the sentiment of IMDb film ratings + \end{itemize} + \column{0.4\textwidth} + \includegraphics[scale=0.1]{bilder/pngfuel-friends.png} + \end{columns} \end{frame} \ No newline at end of file