This paper describes the participation of the Genaios team in the monolingual track of Subtask A at SemEval-2024 Task 8. Our best system, LLMixtic, is a Transformer Encoder that mixes token-level probabilistic features extracted from four LLaMA-2 models. We obtained the best results in the official ranking (96.88% accuracy), showing a false positive ratio of 4.38% and a false negative ratio of 1.97% on the test set. We further study LLMixtic through ablation, probabilistic, and attention analyses, finding that (i) performance improves as more LLMs and probabilistic features are included, (ii) LLMixtic puts most attention on the features of the last tokens, (iii) it fails on samples where human text probabilities become consistently higher than for generated text, and (iv) LLMixtic’s false negatives exhibit a bias towards text with newlines.

In a text, entities mentioned earlier can be referred to in later discourse by a more general description. For example, Celine Dion and Justin Bieber can be referred to by Canadian singers or celebrities. In this work, we study this phenomenon in the context of summarization, where entities from a source text are generalized in the summary. We call such instances source-summary entity aggregations. We categorize these aggregations into two types and analyze them in the Cnn/Dailymail corpus, showing that they are reasonably frequent. We then examine how well three state-of-the-art summarization systems can generate such aggregations within summaries. We also develop techniques to encourage them to generate more aggregations. Our results show that there is significant room for improvement in producing semantically correct aggregations.

This paper describes the approach developed by the ELiRF-UPV team at SemEval 2019 Task 3: Contextual Emotion Detection in Text. We have developed a Snapshot Ensemble of 1D Hierarchical Convolutional Neural Networks to extract features from 3-turn conversations in order to perform contextual emotion detection in text. This Snapshot Ensemble is obtained by averaging the models selected by a Genetic Algorithm that optimizes the evaluation measure. The proposed ensemble obtains better results than a single model and it obtains competitive and promising results on Contextual Emotion Detection in Text.

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

This paper describes the participation of ELiRF-UPV team at task 10, Capturing Discriminative Attributes, of SemEval-2018. Our best approach consists of using ConceptNet, Wikipedia and NumberBatch embeddings in order to stablish relationships between concepts and attributes. Furthermore, this system achieves competitive results in the official evaluation.

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

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

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