What has LeBenchmark Learnt about French Syntax?
The paper reports on a series of experiments aiming at probing LeBenchmark, a pretrained acoustic model trained on 7k hours of spoken French, for syntactic information. Pretrained acoustic models are increasingly used for downstream speech tasks such as automatic speech recognition, speech translation, spoken language understanding or speech parsing. They are trained on very low level information (the raw speech signal), and do not have explicit lexical knowledge. Despite that, they obtained reasonable results on tasks that requires higher level linguistic knowledge. As a result, an emerging question is whether these models encode syntactic information. We probe each representation layer of LeBenchmark for syntax, using the Orf\'eo treebank, and observe that it has learnt some syntactic information. Our results show that syntactic information is more easily extractable from the middle layers of the network, after which a very sharp decrease is observed.
Code (0)
등록된 구현이 없습니다.
Tasks
Automatic Speech Recognitionspeech-recognitionSpeech RecognitionSpoken Language UnderstandingSimilar Papers 제목 키워드 기반
Pantagruel: Unified Self-Supervised Encoders for French Text and Speech
We release Pantagruel models, a new family of self-supervised encoder models for French text and speech. Instead of predicting modality-tailored targets such as textual tokens or speech units, Pantagruel learns contextua…
Representation LearningLeBenchmark 2.0: a Standardized, Replicable and Enhanced Framework for Self-supervised Representations of French Speech
Self-supervised learning (SSL) is at the origin of unprecedented improvements in many different domains including computer vision and natural language processing. Speech processing drastically benefitted from SSL as most…
Self-Supervised LearningDo Syntactic Probes Probe Syntax? Experiments with Jabberwocky Probing
Analysing whether neural language models encode linguistic information has become popular in NLP. One method of doing so, which is frequently cited to support the claim that models like BERT encode syntax, is called prob…
LeBenchmark: A Reproducible Framework for Assessing Self-Supervised Representation Learning from Speech
Self-Supervised Learning (SSL) using huge unlabeled data has been successfully explored for image and natural language processing. Recent works also investigated SSL from speech. They were notably successful to improve p…
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Emotion RecognitionRepresentation Learning+5Deeper syntax for better semantic parsing
Syntax plays an important role in the task of predicting the semantic structure of a sentence. But syntactic phenomena such as alternations, control and raising tend to obfuscate the relation between syntax and semantics…
Semantic ParsingSemantic Role LabelingSentence