我们旨在使用大量自动转录语音来改进口语建模（LM）。我们利用INA（法国国家视听学院）的收藏，并在350,000小时的电视节目中应用ASR后获得19GB的文本。由此，通过微调现有的LM（FLAUBERT）或通过从头开始训练LM来培训口语模型。新模型（Flaubert-Oral）与社区共享，并评估了3个下游任务：口语理解，电视节目的分类和语音句法解析。结果表明，与最初的Flaubert版本相比，Flaubert-Oral可能是有益的，表明尽管其固有的嘈杂性，但ASR生成的文本仍可用于构建口头语言模型。

最近的一些研究测试了变压器语言模型表示的使用来推断文本到语音综合（TTS）的韵律特征。尽管这些研究总体上探讨了韵律，但在这项工作中，我们专门研究了对对比的个人代词的预测。这是一项特别具有挑战性的任务，因为它通常需要语义，话语和/或务实的知识才能正确预测。我们收集包含对比焦点的话语语料库，并评估了BERT模型的准确性，该模型的准确性是在这些样品上预测量化的量化声学突出特征。我们还研究了过去的话语如何为该预测提供相关信息。此外，我们评估了以声音突出特征为条件的TTS模型中代词突出性的可控性。

Recently, very large pre-trained models achieve state-of-the-art results in various natural language processing (NLP) tasks, but their size makes it more challenging to apply them in resource-constrained environments. Compression techniques allow to drastically reduce the size of the models and therefore their inference time with negligible impact on top-tier metrics. However, the general performance averaged across multiple tasks and/or languages may hide a drastic performance drop on under-represented features, which could result in the amplification of biases encoded by the models. In this work, we assess the impact of compression methods on Multilingual Neural Machine Translation models (MNMT) for various language groups, gender, and semantic biases by extensive analysis of compressed models on different machine translation benchmarks, i.e. FLORES-101, MT-Gender, and DiBiMT. We show that the performance of under-represented languages drops significantly, while the average BLEU metric only slightly decreases. Interestingly, the removal of noisy memorization with compression leads to a significant improvement for some medium-resource languages. Finally, we demonstrate that compression amplifies intrinsic gender and semantic biases, even in high-resource languages. Code: https://github.com/alirezamshi/bias-compressedMT

最近，用于语音处理的自我监督模型最近作为语音处理管道中流行的基础块出现。这些模型在未标记的音频数据上进行了预训练，然后用于语音处理下游任务，例如自动语音识别（ASR）或语音翻译（ST）。由于这些模型现在都用于研究和工业系统，因此有必要理解某些特征在培训数据中的性别分布等特征所引起的影响。我们以法语为我们的调查语言，训练和比较性别特定的WAV2VEC 2.0模型与在其预训练数据中包含不同性别平衡的模型。通过将这些模型应用于两个语音到文本下游任务：ASR和ST进行比较。结果显示了下游集成的类型。在微调端到端ASR系统之前，我们使用性别特定的预训练观察到较低的总体性能。但是，当将自我监督模型用作特征提取器时，总体ASR和ST结果遵循更复杂的模式，在这种模式下，平衡的预训练模型不一定会带来最佳结果。最后，我们粗制的“公平”度量标准（男性测试集之间测量的相对性能差异）并未显示出从平衡到特定性别的预训练的Preaded Wav2Vec 2.0模型的强烈变化。

Graph Neural Networks (GNNs) have shown great potential in the field of graph representation learning. Standard GNNs define a local message-passing mechanism which propagates information over the whole graph domain by stacking multiple layers. This paradigm suffers from two major limitations, over-squashing and poor long-range dependencies, that can be solved using global attention but significantly increases the computational cost to quadratic complexity. In this work, we propose an alternative approach to overcome these structural limitations by leveraging the ViT/MLP-Mixer architectures introduced in computer vision. We introduce a new class of GNNs, called Graph MLP-Mixer, that holds three key properties. First, they capture long-range dependency and mitigate the issue of over-squashing as demonstrated on the Long Range Graph Benchmark (LRGB) and the TreeNeighbourMatch datasets. Second, they offer better speed and memory efficiency with a complexity linear to the number of nodes and edges, surpassing the related Graph Transformer and expressive GNN models. Third, they show high expressivity in terms of graph isomorphism as they can distinguish at least 3-WL non-isomorphic graphs. We test our architecture on 4 simulated datasets and 7 real-world benchmarks, and show highly competitive results on all of them.

Over the past decade, neural networks have been successful at making predictions from biological sequences, especially in the context of regulatory genomics. As in other fields of deep learning, tools have been devised to extract features such as sequence motifs that can explain the predictions made by a trained network. Here we intend to go beyond explainable machine learning and introduce SEISM, a selective inference procedure to test the association between these extracted features and the predicted phenotype. In particular, we discuss how training a one-layer convolutional network is formally equivalent to selecting motifs maximizing some association score. We adapt existing sampling-based selective inference procedures by quantizing this selection over an infinite set to a large but finite grid. Finally, we show that sampling under a specific choice of parameters is sufficient to characterize the composite null hypothesis typically used for selective inference-a result that goes well beyond our particular framework. We illustrate the behavior of our method in terms of calibration, power and speed and discuss its power/speed trade-off with a simpler data-split strategy. SEISM paves the way to an easier analysis of neural networks used in regulatory genomics, and to more powerful methods for genome wide association studies (GWAS).

Information on the grass growth over a year is essential for some models simulating the use of this resource to feed animals on pasture or at barn with hay or grass silage. Unfortunately, this information is rarely available. The challenge is to reconstruct grass growth from two sources of information: usual daily climate data (rainfall, radiation, etc.) and cumulative growth over the year. We have to be able to capture the effect of seasonal climatic events which are known to distort the growth curve within the year. In this paper, we formulate this challenge as a problem of disaggregating the cumulative growth into a time series. To address this problem, our method applies time series forecasting using climate information and grass growth from previous time steps. Several alternatives of the method are proposed and compared experimentally using a database generated from a grassland process-based model. The results show that our method can accurately reconstruct the time series, independently of the use of the cumulative growth information.

As of 2022, greenhouse gases (GHG) emissions reporting and auditing are not yet compulsory for all companies and methodologies of measurement and estimation are not unified. We propose a machine learning-based model to estimate scope 1 and scope 2 GHG emissions of companies not reporting them yet. Our model, specifically designed to be transparent and completely adapted to this use case, is able to estimate emissions for a large universe of companies. It shows good out-of-sample global performances as well as good out-of-sample granular performances when evaluating it by sectors, by countries or by revenues buckets. We also compare our results to those of other providers and find our estimates to be more accurate. Thanks to the proposed explainability tools using Shapley values, our model is fully interpretable, the user being able to understand which factors split explain the GHG emissions for each particular company.

Robots are traditionally bounded by a fixed embodiment during their operational lifetime, which limits their ability to adapt to their surroundings. Co-optimizing control and morphology of a robot, however, is often inefficient due to the complex interplay between the controller and morphology. In this paper, we propose a learning-based control method that can inherently take morphology into consideration such that once the control policy is trained in the simulator, it can be easily deployed to robots with different embodiments in the real world. In particular, we present the Embodiment-aware Transformer (EAT), an architecture that casts this control problem as conditional sequence modeling. EAT outputs the optimal actions by leveraging a causally masked Transformer. By conditioning an autoregressive model on the desired robot embodiment, past states, and actions, our EAT model can generate future actions that best fit the current robot embodiment. Experimental results show that EAT can outperform all other alternatives in embodiment-varying tasks, and succeed in an example of real-world evolution tasks: stepping down a stair through updating the morphology alone. We hope that EAT will inspire a new push toward real-world evolution across many domains, where algorithms like EAT can blaze a trail by bridging the field of evolutionary robotics and big data sequence modeling.

Dependency hell is a well-known pain point in the development of large software projects and machine learning (ML) code bases are not immune from it. In fact, ML applications suffer from an additional form, namely, "data source dependency hell". This term refers to the central role played by data and its unique quirks that often lead to unexpected failures of ML models which cannot be explained by code changes. In this paper, we present an automated dependency mapping framework that allows MLOps engineers to monitor the whole dependency map of their models in a fast paced engineering environment and thus mitigate ahead of time the consequences of any data source changes (e.g., re-train model, ignore data, set default data etc.). Our system is based on a unified and generic approach, employing techniques from static analysis, from which data sources can be identified reliably for any type of dependency on a wide range of source languages and artefacts. The dependency mapping framework is exposed as a REST web API where the only input is the path to the Git repository hosting the code base. Currently used by MLOps engineers at Microsoft, we expect such dependency map APIs to be adopted more widely by MLOps engineers in the future.