[Topic-models] On author topic model

Mohamed Morchid mohamed.morchid at univ-avignon.fr
Mon Jul 24 02:34:42 EDT 2017

Dear friends,

We have also evaluated the efficiency and the effectiveness of the author-topic model during a theme identification task of spoken dialogues. You can find out more information in:

Tracking Dialog States using an Author-Topic based Representation <http://lia.univ-avignon.fr/chercheurs/morchid/articles/slt2016_dufour.pdf>
Richard Dufour, Mohamed Morchid et Titouan Parcollet
IEEE SLT 2016 <http://www.slt2016.org/>
13-16 Decembre 2016, San Diego, (Etats-Unis)

Author-Topic based Representation of Call-Center Conversations <http://lia.univ-avignon.fr/chercheurs/morchid/articles/slt2014_mohamed_morchid.pdf>
Mohamed Morchid, Richard Dufour, Mohamed Bouallegue et Georges Linarès
IEEE SLT 2014 <http://www.slt2014.org/>
7-10 Decembre 2014, South Lake Tahoe (Etats-Unis)

Spoken Language Understanding in a Latent Topic-based Subspace <http://lia.univ-avignon.fr/chercheurs/morchid/articles/interspeech2016_mohamed_morchid.pdf>
Mohamed Morchid, Mohamed Bouaziz, Waad Ben Kheder, Killian Janod, Pierre-Michel Bousquet, Richard Dufour et Georges Linarès
ISCA INTERSPEECH 2016 <http://www.interspeech2016.org/>
8-12 Septembre 2016, San Fransisco, (Etats-Unis)


Mohamed Morchid <http://lia.univ-avignon.fr/chercheurs/morchid>
Maître de Conférences / Associate Professor
Université d'Avignon et des Pays de Vaucluse
http://lia.univ-avignon.fr/chercheurs/morchid/ <http://lia.univ-avignon.fr/chercheurs/morchid/>

> Le 24 juil. 2017 à 00:11, Thibaut Thonet <thibaut.thonet at irit.fr> a écrit :
> Hi Eric,
> You can also have a look at the following papers:
> Yang, M., & Hsu, W. H. (2016). HDPauthor: A New Hybrid Author-Topic Model using Latent Dirichlet Allocation and Hierarchical Dirichlet Processes. In Proceedings of the 25th International Conference Companion on World Wide Web (pp. 619–624). http://doi.org/10.1145/2872518.2890561 <http://doi.org/10.1145/2872518.2890561>
> Xuan, J., Lu, J., Zhang, G., Xu, R. Y. Da, & Luo, X. (2015). Infinite Author Topic Model based on Mixed Gamma-Negative Binomial Process. In Proceedings of the 2015 IEEE International Conference on Data Mining (pp. 489–498). http://doi.org/10.1109/ICDM.2015.19 <http://doi.org/10.1109/ICDM.2015.19>
> They both propose non-parametric author-topic models with hierarchical priors, similar to what you described -- document-level topic distributions' prior is based on author-specific topic distributions.
> Best,
> Thibaut
> Le 21/07/2017 à 02:20, Eric Kang a écrit :
>> Hi everyone,
>> I have a question about the author-topic model. Is my understanding correct that the author-topic probabilities are "constant" across different documents? So if the same author writes multiple documents, the implied document-topic proportions would be the same between those documents?
>> I thought perhaps another model might be to suppose that author-topic probabilities are a multinomial random variable (with a Dirichlet prior) that is sampled per document. In other words, each author is associated with author-specific Dirichlet distribution over topics, and for a particular document, a topic mixture is sampled from that Dirichlet distribution. And the inference problem would be to determine the topic-word probabilities, and the Dirichlet parameters for each author. 
>> Does this make sense? Is there existing work of this kind in the literature? Would this be interesting? Useful? Tractable?
>> Any suggestions or guidance would be really appreciated. 
>> Thank you,
>> Eric
>> _______________________________________________
>> Topic-models mailing list
>> Topic-models at lists.cs.princeton.edu <mailto:Topic-models at lists.cs.princeton.edu>
>> https://lists.cs.princeton.edu/mailman/listinfo/topic-models <https://lists.cs.princeton.edu/mailman/listinfo/topic-models>
> _______________________________________________
> Topic-models mailing list
> Topic-models at lists.cs.princeton.edu
> https://lists.cs.princeton.edu/mailman/listinfo/topic-models

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.cs.princeton.edu/pipermail/topic-models/attachments/20170724/4dab03aa/attachment-0001.html>

More information about the Topic-models mailing list