Basic syntax from speech: Spontaneous concatenation in unsupervised deep neural networks

• URL: http://arxiv.org/abs/2305.01626v3
• Date: Wed, 20 Nov 2024 18:30:49 GMT
• Title: Basic syntax from speech: Spontaneous concatenation in unsupervised deep neural networks
• Authors: Gašper Beguš, Thomas Lu, Zili Wang,
• Abstract summary: We focus on one of the most ubiquitous and elementary suboperation of syntax -- concatenation. We introduce spontaneous concatenation: a phenomenon where convolutional neural networks (CNNs) trained on acoustic recordings of individual words start generating outputs. We also propose a potential neural mechanism called disinhibition that outlines a possible neural pathway towards concatenation and compositionality.
• Score: 8.683116789109462
• License:
• Abstract: Computational models of syntax are predominantly text-based. Here we propose that the most basic first step in the evolution of syntax can be modeled directly from raw speech in a fully unsupervised way. We focus on one of the most ubiquitous and elementary suboperation of syntax -- concatenation. We introduce spontaneous concatenation: a phenomenon where convolutional neural networks (CNNs) trained on acoustic recordings of individual words start generating outputs with two or even three words concatenated without ever accessing data with multiple words in the input. We replicate this finding in several independently trained models with different hyperparameters and training data. Additionally, networks trained on two words learn to embed words into novel unobserved word combinations. We also show that the concatenated outputs contain precursors to compositionality. To our knowledge, this is a previously unreported property of CNNs trained in the ciwGAN/fiwGAN setting on raw speech and has implications both for our understanding of how these architectures learn as well as for modeling syntax and its evolution in the brain from raw acoustic inputs. We also propose a potential neural mechanism called disinhibition that outlines a possible neural pathway towards concatenation and compositionality and suggests our modeling is useful for generating testable prediction for biological and artificial neural processing of speech.

Related papers

• Probabilistic Transformer: A Probabilistic Dependency Model for Contextual Word Representation [52.270712965271656]
  We propose a new model of contextual word representation, not from a neural perspective, but from a purely syntactic and probabilistic perspective. We find that the graph of our model resembles transformers, with correspondences between dependencies and self-attention. Experiments show that our model performs competitively to transformers on small to medium sized datasets.
  arXiv  Detail & Related papers  (2023-11-26T06:56:02Z)
• Multimodal Neurons in Pretrained Text-Only Transformers [52.20828443544296]
  We identify "multimodal neurons" that convert visual representations into corresponding text. We show that multimodal neurons operate on specific visual concepts across inputs, and have a systematic causal effect on image captioning.
  arXiv  Detail & Related papers  (2023-08-03T05:27:12Z)
• Why can neural language models solve next-word prediction? A mathematical perspective [53.807657273043446]
  We study a class of formal languages that can be used to model real-world examples of English sentences. Our proof highlights the different roles of the embedding layer and the fully connected component within the neural language model.
  arXiv  Detail & Related papers  (2023-06-20T10:41:23Z)
• BrainBERT: Self-supervised representation learning for intracranial recordings [18.52962864519609]
  We create a reusable Transformer, BrainBERT, for intracranial recordings bringing modern representation learning approaches to neuroscience. Much like in NLP and speech recognition, this Transformer enables classifying complex concepts, with higher accuracy and with much less data. In the future, far more concepts will be decodable from neural recordings by using representation learning, potentially unlocking the brain like language models unlocked language.
  arXiv  Detail & Related papers  (2023-02-28T07:40:37Z)
• Word class representations spontaneously emerge in a deep neural network trained on next word prediction [7.240611820374677]
  How do humans learn language, and can the first language be learned at all? These fundamental questions are still hotly debated. In particular, we train an artificial deep neural network on predicting the next word. We find that the internal representations of nine-word input sequences cluster according to the word class of the tenth word to be predicted as output.
  arXiv  Detail & Related papers  (2023-02-15T11:02:50Z)
• Deep Learning Models to Study Sentence Comprehension in the Human Brain [0.1503974529275767]
  Recent artificial neural networks that process natural language achieve unprecedented performance in tasks requiring sentence-level understanding. We review works that compare these artificial language models with human brain activity and we assess the extent to which this approach has improved our understanding of the neural processes involved in natural language comprehension.
  arXiv  Detail & Related papers  (2023-01-16T10:31:25Z)
• Decoding speech perception from non-invasive brain recordings [48.46819575538446]
  We introduce a model trained with contrastive-learning to decode self-supervised representations of perceived speech from non-invasive recordings. Our model can identify, from 3 seconds of MEG signals, the corresponding speech segment with up to 41% accuracy out of more than 1,000 distinct possibilities.
  arXiv  Detail & Related papers  (2022-08-25T10:01:43Z)
• Wav2Seq: Pre-training Speech-to-Text Encoder-Decoder Models Using Pseudo Languages [58.43299730989809]
  We introduce Wav2Seq, the first self-supervised approach to pre-train both parts of encoder-decoder models for speech data. We induce a pseudo language as a compact discrete representation, and formulate a self-supervised pseudo speech recognition task. This process stands on its own, or can be applied as low-cost second-stage pre-training.
  arXiv  Detail & Related papers  (2022-05-02T17:59:02Z)
• Modeling speech recognition and synthesis simultaneously: Encoding and decoding lexical and sublexical semantic information into speech with no direct access to speech data [0.0]
  We introduce, to our knowledge, the most challenging objective in unsupervised lexical learning: an unsupervised network that must learn to assign unique representations for lexical items. Strong evidence in favor of lexical learning emerges. The architecture that combines the production and perception principles is thus able to learn to decode unique information from raw acoustic data in an unsupervised manner without ever accessing real training data.
  arXiv  Detail & Related papers  (2022-03-22T06:04:34Z)
• Dependency-based Mixture Language Models [53.152011258252315]
  We introduce the Dependency-based Mixture Language Models. In detail, we first train neural language models with a novel dependency modeling objective. We then formulate the next-token probability by mixing the previous dependency modeling probability distributions with self-attention.
  arXiv  Detail & Related papers  (2022-03-19T06:28:30Z)
• CiwGAN and fiwGAN: Encoding information in acoustic data to model lexical learning with Generative Adversarial Networks [0.0]
  Lexical learning is modeled as emergent from an architecture that forces a deep neural network to output data. Networks trained on lexical items from TIMIT learn to encode unique information corresponding to lexical items in the form of categorical variables in their latent space. We show that phonetic and phonological representations learned by the network can be productively recombined and directly paralleled to productivity in human speech.
  arXiv  Detail & Related papers  (2020-06-04T15:33:55Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.