This paper describes the participation of ELiRF-UPV team at task 4 SemEval2017. Our approach is based on use convolutional and recurrent neural networks combination general specific word embeddings with polarity lexicons. We participated in all proposed subtasks both for English Arabic languages using same system small variations.

This paper describes the participation of ELiRF-UPV team at tasks 1 and 3 Semeval-2018. We present a deep learning based system that assembles Convolutional Neural Networks Long Short-Term Memory neural networks. has been used with slight modifications for two addressed both English Spanish. Finally, results obtained in competition are reported discussed.

We introduce a simple method to build Lexicalized Hidden Markov Models (L-HMMs) for improving the precision of part-of-speech tagging. This technique enriches contextual Language Model taking into account set selected words empirically obtained. The evaluation was conducted with different lexicalization criteria on Penn Treebank corpus using TnT tagger. obtained about 6% reduction tagging error, an unseen data test, without reducing efficiency system. have also studied how use linguistic...

In this paper we present an integrated system for tagging and chunking texts from a certain language. The approach is based on stochastic finite-state models that are learnt automatically. This includes biagram or automata using grammatical inference techniques. As the involved in our automatically, very flexible portable system.In order to show viability of results bigram Wall Street Journal corpus. We have achieved accuracy rate 96.8%, precision NP chunks 94.6% with recall 93.6%.

This paper describes our proposal for Sentiment Analysis in Twitter the Spanish language. The main characteristics of system are use word embedding specifically trained from tweets and self-attention mechanisms that allow to consider sequences without using convolutional nor recurrent layers. These based on encoders Transformer model. results obtained Task 1 TASS 2019 workshop, all variants proposed, support correctness adequacy proposal.

This paper describes our participation at tasks 10 (sub-task B, Message Polarity Classification) and 11 task (Sentiment Analysis of Figurative Language in Twitter) Semeval2015.We describe the Support Vector Machine system we used this competition.We also present relevant feature set that take into account models.Finally, show results obtained competition some conclusions.

This paper describes the participation of ELiRF-UPV team at task 7 (subtask 2: homographic pun detection and subtask 3: interpretation) SemEval2017. Our approach is based on use word embeddings to find related words in a sentence version Lesk algorithm establish relationships between synsets. The results obtained are line with those by other participants they encourage us continue working this problem.

This paper describes the participation of ELiRF-UPV team at task 11, Machine Comprehension using Commonsense Knowledge, SemEval-2018. Our approach is based on use word embeddings, NumberBatch Embeddings, and a Deep Learning architecture to find best answer for multiple-choice questions narrative text. The results obtained are in line with those by other participants they encourage us continue working this problem.