Walid Dahhane

Jessica López Espejel, Mahaman Sanoussi Yahaya Alassan, Walid Dahhane et al.

Pretrained transformer-based models have shown high performance in natural language generation task. However, a new wave of interest has surged: automatic programming language generation. This task consists of translating natural language instructions to a programming code. Despite the fact that well-known pretrained models on language generation have achieved good performance in learning programming languages, effort is still needed in automatic code generation. In this paper, we introduce JaCoText, a model based on Transformers neural network. It aims to generate java source code from natural language text. JaCoText leverages advantages of both natural language and code generation models. More specifically, we study some findings from the state of the art and use them to (1) initialize our model from powerful pretrained models, (2) explore additional pretraining on our java dataset, (3) carry out experiments combining the unimodal and bimodal data in the training, and (4) scale the input and output length during the fine-tuning of the model. Conducted experiments on CONCODE dataset show that JaCoText achieves new state-of-the-art results.

El Mehdi Chouham, Jessica López Espejel, Mahaman Sanoussi Yahaya Alassan et al.

The field of programming has a diversity of paradigms that are used according to the working framework. While current neural code generation methods are able to learn and generate code directly from text, we believe that this approach is not optimal for certain code tasks, particularly the generation of classes in an object-oriented project. Specifically, we use natural language processing techniques to extract structured information from requirements descriptions, in order to automate the generation of CRUD (Create, Read, Update, Delete) class code. To facilitate this process, we introduce a pipeline for extracting entity and relation information, as well as a representation called an "Entity Tree" to model this information. We also create a dataset to evaluate the effectiveness of our approach.

Mahaman Sanoussi Yahaya Alassan, Jessica López Espejel, Merieme Bouhandi et al.

Large Language Models (LLMs) have recently demonstrated remarkable performance in various Natural Language Processing (NLP) applications, such as sentiment analysis, content generation, and personalized recommendations. Despite their impressive capabilities, there remains a significant need for systematic studies concerning the practical application of LLMs in industrial settings, as well as the specific requirements and challenges related to their deployment in these contexts. This need is particularly critical for Machine Reading Comprehension (MCR), where factual, concise, and accurate responses are required. To date, most MCR rely on Small Language Models (SLMs) or Recurrent Neural Networks (RNNs) such as Long Short-Term Memory (LSTM). This trend is evident in the SQuAD2.0 rankings on the Papers with Code table. This article presents a comparative analysis between open-source LLMs and proprietary models on this task, aiming to identify light and open-source alternatives that offer comparable performance to proprietary models.

Jessica López Espejel, Mahaman Sanoussi Yahaya Alassan, Merieme Bouhandi et al.

Large Language Models (LLMs) have become a popular choice for many Natural Language Processing (NLP) tasks due to their versatility and ability to produce high-quality results. Specifically, they are increasingly used for automatic code generation to help developers tackle repetitive coding tasks. However, LLMs' substantial computational and memory requirements often make them inaccessible to users with limited resources. This paper focuses on very low-cost models which offer a more accessible alternative to resource-intensive LLMs. We notably: (1) propose a thorough semi-manual evaluation of their performance in generating Python code, (2) introduce a Chain-of-Thought (CoT) prompting strategy to improve model reasoning and code quality, and (3) propose a new dataset of 60 programming problems, with varied difficulty levels, designed to extend existing benchmarks like HumanEval and EvalPlus. Our findings show that some low-cost compatible models achieve competitive results compared to larger models like ChatGPT despite using significantly fewer resources. We will make our dataset and prompts publicly available to support further research.

El Hassane Ettifouri, Jessica López Espejel, Laura Minkova et al.

Most visual grounding solutions primarily focus on realistic images. However, applications involving synthetic images, such as Graphical User Interfaces (GUIs), remain limited. This restricts the development of autonomous computer vision-powered artificial intelligence (AI) agents for automatic application interaction. Enabling AI to effectively understand and interact with GUIs is crucial to advancing automation in software testing, accessibility, and human-computer interaction. In this work, we explore Instruction Visual Grounding (IVG), a multi-modal approach to object identification within a GUI. More precisely, given a natural language instruction and a GUI screen, IVG locates the coordinates of the element on the screen where the instruction should be executed. We propose two main methods: (1) IVGocr, which combines a Large Language Model (LLM), an object detection model, and an Optical Character Recognition (OCR) module; and (2) IVGdirect, which uses a multimodal architecture for end-to-end grounding. For each method, we introduce a dedicated dataset. In addition, we propose the Central Point Validation (CPV) metric, a relaxed variant of the classical Central Proximity Score (CPS) metric. Our final test dataset is publicly released to support future research.

Jessica López Espejel, El Hassane Ettifouri, Mahaman Sanoussi Yahaya Alassan et al.

Large Language Models (LLMs) have exhibited remarkable performance on various Natural Language Processing (NLP) tasks. However, there is a current hot debate regarding their reasoning capacity. In this paper, we examine the performance of GPT-3.5, GPT-4, and BARD models, by performing a thorough technical evaluation on different reasoning tasks across eleven distinct datasets. Our paper provides empirical evidence showcasing the superior performance of ChatGPT-4 in comparison to both ChatGPT-3.5 and BARD in zero-shot setting throughout almost all evaluated tasks. While the superiority of GPT-4 compared to GPT-3.5 might be explained by its larger size and NLP efficiency, this was not evident for BARD. We also demonstrate that the three models show limited proficiency in Inductive, Mathematical, and Multi-hop Reasoning Tasks. To bolster our findings, we present a detailed and comprehensive analysis of the results from these three models. Furthermore, we propose a set of engineered prompts that enhances the zero-shot setting performance of all three models.