Publicaciones

This paper conducts an evaluation of several traditional Language Models for the task of Natural Language Generation, focusing on the surface realisation stage. Specifically, we analyse and compare the n-gram language models and the factored language models through the evaluation of automatically generated sentences. In this manner, factored language models have shown to be better, improving the coherence of the generated sentences compared with the ones generated with n-grams.

The structure and selection of content in Automatic Language Generation is commonly referred to as Macroplanning. It provides an intermediate artefact that conveys such information, called document plan. This paper studies the appropriateness of Positional Language Models for building that plan, since they provide mechanisms to outline relevant elements and their distribution along the text. A series of experiments were conducted over a corpus of children tales in English, with the purpose of studying the behaviour and optimal adjustment of the method and its parameters.

La Generación de Lenguaje Natural es la disciplina que permite conferir cierta forma textual a un conjunto de datos, persiguiendo un determinado objetivo comunicativo. El actual escenario tecnológico reclama sistemas de generación flexibles, adaptables a diferentes casos de uso, por lo que la incorporación dinámica del contexto debe formar parte del sistema mismo. La propuesta que aquí se expone busca introducir información semántica y pragmática en la parte del proceso que selecciona y estructura los mensajes esperados en la salida.

The writing style used in social media usually contains informal elements that can lower the performance of Natural Language Processing applications. For this reason, text normalisation techniques have drawn a lot of attention recently when dealing with informal content. However, not all the texts present the same level of informality and may not require additional pre-processing steps.