Nous évaluons leurs avantages et inconvénients, en explorant leur précision respective sur des tâches de classification, ainsi que leur impact sur la génération coopérative et leur coût de calcul, dans le cadre d’une stratégie de décodage état de l’art, basée sur une recherche arborescente de Monte-Carlo (MCTS).
The proliferation of misinformation on social media platforms (SMPs) poses a significant danger to public health, social cohesion and ultimately democracy.
Such information is publicly released in a variety of non-structured and multi-modal documentation.
Research in Image Generation has recently made significant progress, particularly boosted by the introduction of Vision-Language models which are able to produce high-quality visual content based on textual inputs.
Text Summarization is a popular task and an active area of research for the Natural Language Processing community.
Language models generate texts by successively predicting probability distributions for next tokens given past ones.
Generative Adversarial Networks (GANs) have known a tremendous success for many continuous generation tasks, especially in the field of image generation.
Motivated by human reading strategies, this paper presents Skim-Attention, a new attention mechanism that takes advantage of the structure of the document and its layout.
Due to the discrete nature of words, language GANs require to be optimized from rewards provided by discriminator networks, via reinforcement learning methods.
In the context of Sentence Simplification, this is particularly challenging: the task requires by nature to replace complex words with simpler ones that shares the same meaning.
QuestEval is a reference-less metric used in text-to-text tasks, that compares the generated summaries directly to the source text, by automatically asking and answering questions.
Summarization evaluation remains an open research problem: current metrics such as ROUGE are known to be limited and to correlate poorly with human judgments.
Coupled with the availability of large scale datasets, deep learning architectures have enabled rapid progress on the Question Answering task.
In the context of chit-chat dialogues it has been shown that endowing systems with a persona profile is important to produce more coherent and meaningful conversations.
Motivated by the lack of data for non-English languages, in particular for the evaluation of downstream tasks such as Question Answering, we present a participatory effort to collect a native French Question Answering Dataset.
Ranked #4 on Question Answering on FQuAD (using extra training data)
Training regimes based on Maximum Likelihood Estimation (MLE) suffer from known limitations, often leading to poorly generated text sequences.
Pre-trained language models have recently contributed to significant advances in NLP tasks.
We introduce a novel approach for sequence decoding, Discriminative Adversarial Search (DAS), which has the desirable properties of alleviating the effects of exposure bias without requiring external metrics.
Abstractive summarization approaches based on Reinforcement Learning (RL) have recently been proposed to overcome classical likelihood maximization.
Neural architectures based on self-attention, such as Transformers, recently attracted interest from the research community, and obtained significant improvements over the state of the art in several tasks.
Several lexica for sentiment analysis have been developed and made available in the NLP community.
In this paper, we describe a methodology to infer Bullish or Bearish sentiment towards companies/brands.
This is mainly because it is hard to collect data about "city life".
Computers and Society Social and Information Networks Physics and Society
Studying free-standing conversational groups (FCGs) in unstructured social settings (e. g., cocktail party ) is gratifying due to the wealth of information available at the group (mining social networks) and individual (recognizing native behavioral and personality traits) levels.
This article provides a comprehensive investigation on the relations between virality of news articles and the emotions they are found to evoke.
While many lexica annotated with words polarity are available for sentiment analysis, very few tackle the harder task of emotion analysis and are usually quite limited in coverage.