The democratization of deep learning in TASS 2017

2018 
espanolTASS 2017 ha vuelto a suponer un avance en el estado del arte de analisis de opiniones en espanol, debido a la exposicion de sistemas mayoritariamente fundamentados en metodos de Deep Learning. Ademas, en esta edicion se ha presentado un nueva coleccion de tuits en espanol manualmente etiquetados a nivel de documento y que se llama InterTASS. El analisis de los resultados con InterTASS demuestra que en el futuro el esfuerzo investigador se tiene que centrar en la distincion del nivel de intensidad de opinion neutro y la ausencia de opinion. Asimismo, se presento el proyecto de ampliar el nuevo corpus con tuits escritos en el espanol que se habla en Espana y en algunos paises de America. EnglishTASS 2017 has brought advances in the state-of-the-art in Sentiment Analysis in Spanish, because most of the systems submitted in 2017 were grounded on Deep Learning methods. Moreover, a new corpus of tweets written in Spanish was released, which is called InterTASS. The corpus is composed of tweets manually annotated at document level. The analysis of the results with InterTASS shows that the main challenge is the classification of tweets with a neutral opinion and those ones that do not express any opinion. Likewise, the organization exposed the project of extending InterTASS with tweets written in different versions of Spanish.
    • Correction
    • Source
    • Cite
    • Save
    • Machine Reading By IdeaReader
    0
    References
    4
    Citations
    NaN
    KQI
    []