Related papers: What has LeBenchmark Learnt about French Syntax?

This paper analyses the contribution of language metrics and, potentially, of linguistic structures, to classify French learners of English according to levels of the Common European Framework of Reference for Languages (CEFRL). The purpose…

Designing machine intelligence to converse with a human user necessarily requires an understanding of how humans participate in conversation, and thus conversation modeling is an important task in natural language processing. New…

Interleaved texts, where posts belonging to different threads occur in a sequence, commonly occur in online chat posts, so that it can be time-consuming to quickly obtain an overview of the discussions. Existing systems first disentangle…

The objective of pre-trained language models is to learn contextual representations of textual data. Pre-trained language models have become mainstream in natural language processing and code modeling. Using probes, a technique to study the…

This paper explores morpho-syntactic ambiguities for French to develop a strategy for part-of-speech disambiguation that a) reflects the complexity of French as an inflected language, b) optimizes the estimation of probabilities, c) allows…

Sentence and word embeddings encode structural and semantic information in a distributed manner. Part of the information encoded -- particularly lexical information -- can be seen as continuous, whereas other -- like structural information…

In this work we tackle the problem of sentence boundary detection applied to French as a binary classification task ("sentence boundary" or "not sentence boundary"). We combine convolutional neural networks with subword-level information…

Much recent work suggests that incorporating syntax information from dependency trees can improve task-specific transformer models. However, the effect of incorporating dependency tree information into pre-trained transformer models (e.g.,…

While recent automatic speech recognition systems achieve remarkable performance when large amounts of adequate, high quality annotated speech data is used for training, the same systems often only achieve an unsatisfactory result for tasks…

Automatic speech transcription and speaker recognition are usually treated as separate tasks even though they are interdependent. In this study, we investigate training a single network to perform both tasks jointly. We train the network in…

In recent studies, it has shown that speaker patterns can be learned from very short speech segments (e.g., 0.3 seconds) by a carefully designed convolutional & time-delay deep neural network (CT-DNN) model. By enforcing the model to…

Results from a recent neuroimaging study on spoken sentence comprehension have been interpreted as evidence for cortical entrainment to hierarchical syntactic structure. We present a simple computational model that predicts the power…

Accurate syntactic representations are essential for robust generalization in natural language. Recent work has found that pre-training can teach language models to rely on hierarchical syntactic features - as opposed to incorrect linear…

End-to-end models have achieved impressive results on the task of automatic speech recognition (ASR). For low-resource ASR tasks, however, labeled data can hardly satisfy the demand of end-to-end models. Self-supervised acoustic…

Large speech models-derived features have recently shown increased performance over signal-based features across multiple downstream tasks, even when the networks are not finetuned towards the target task. In this paper we show the results…

For conversational large-vocabulary continuous speech recognition (LVCSR) tasks, up to about two thousand hours of audio is commonly used to train state of the art models. Collection of labeled conversational audio however, is prohibitively…

The French TreeBank developed at the University Paris 7 is the main source of morphosyntactic and syntactic annotations for French. However, it does not include explicit information related to named entities, which are among the most useful…

Latent tree learning models learn to parse a sentence without syntactic supervision, and use that parse to build the sentence representation. Existing work on such models has shown that, while they perform well on tasks like sentence…

Pre-trained language models like BERT achieve superior performances in various NLP tasks without explicit consideration of syntactic information. Meanwhile, syntactic information has been proved to be crucial for the success of NLP…

Inductive transfer learning has taken the entire NLP field by storm, with models such as BERT and BART setting new state of the art on countless NLU tasks. However, most of the available models and research have been conducted for English.…