Commonsense Validation and Explanation has been a difficult task for machines since the dawn of computing. Although very trivial to humans it poses a high complexity for machines due to the necessity of inference over a pre-existing knowledge base. In order to try and solve this problem the SemEval 2020 Task 4 - ”Commonsense Validation and Explanation (ComVE)” aims to evaluate systems capable of multiple stages of ComVE. The challenge includes 3 tasks (A, B and C), each with it’s own requirements. Our team participated only in task A which required selecting the statement that made the least sense. We choose to use a bidirectional transformer in order to solve the challenge, this paper presents the details of our method, runs and result.

Nowadays, social media credibility is a pressing issue for each of us who are living in an altered online landscape. The speed of news diffusion is striking. Given the popularity of social networks, more and more users began posting pictures, information, and news about personal life. At the same time, they started to use all this information to get informed about what their friends do or what is happening in the world, many of them arousing much suspicion. The problem we are currently experiencing is that we do not currently have an automatic method of figuring out in real-time which news or which users are credible and which are not, what is false or what is true on the Internet. The goal of this is to analyze Twitter in real-time using neural networks in order to provide us key elements about both the credibility of tweets and users who posted them. Thus, we make a real-time heatmap using information gathered from users to create overall images of the areas from which this fake news comes.

In this paper, we present a system description for implementing a sentiment analysis agent capable of interpreting the state of an interlocutor engaged in short three message conversations. We present the results and observations of our work and which parts could be further improved in the future.

This paper presents Wild Devs’ participation in the SemEval-2017 Task 2 “Multi-lingual and Cross-lingual Semantic Word Similarity”, which tries to automatically measure the semantic similarity between two words. The system was build using neural networks, having as input a collection of word pairs, whereas the output consists of a list of scores, from 0 to 4, corresponding to the degree of similarity between the word pairs.

This paper presents the participation of #WarTeam in Task 6 of SemEval2017 with a system classifying humor by comparing and ranking tweets. The training data consists of annotated tweets from the @midnight TV show. #WarTeam’s system uses a neural network (TensorFlow) having inputs from a Naïve Bayes humor classifier and a sentiment analyzer.

Discovering relations among Named Entities (NEs) from large corpora is both a challenging, as well as useful task in the domain of Natural Language Processing, with applications in Information Retrieval (IR), Summarization (SUM), Question Answering (QA) and Textual Entailment (TE). The work we present resulted from the attempt to solve practical issues we were confronted with while building systems for the tasks of Textual Entailment Recognition and Question Answering, respectively. The approach consists in applying grammar induced extraction patterns on a large corpus - Wikipedia - for the extraction of relations between a given Named Entity and other Named Entities. The results obtained are high in precision, determining a reliable and useful application of the built resource.