Hierarchical-Task Reservoir for Online Semantic Analysis From Continuous Speech

Luca Pedrelli, Xavier Hinaut
IEEE Trans. Neural Netw. Learning Syst.. 2021-01-01; : 1-10
DOI: 10.1109/TNNLS.2021.3095140

Read on PubMed

1. IEEE Trans Neural Netw Learn Syst. 2021 Sep 27;PP. doi:
10.1109/TNNLS.2021.3095140. [Epub ahead of print]

Hierarchical-Task Reservoir for Online Semantic Analysis From Continuous Speech.

Pedrelli L, Hinaut X.

In this article, we propose a novel architecture called hierarchical-task
reservoir (HTR) suitable for real-time applications for which different levels of
abstraction are available. We apply it to semantic role labeling (SRL) based on
continuous speech recognition. Taking inspiration from the brain, this
demonstrates the hierarchies of representations from perceptive to integrative
areas, and we consider a hierarchy of four subtasks with increasing levels of
abstraction (phone, word, part-of-speech (POS), and semantic role tags). These
tasks are progressively learned by the layers of the HTR architecture.
Interestingly, quantitative and qualitative results show that the
hierarchical-task approach provides an advantage to improve the prediction. In
particular, the qualitative results show that a shallow or a hierarchical
reservoir, considered as baselines, does not produce estimations as good as the
HTR model would. Moreover, we show that it is possible to further improve the
accuracy of the model by designing skip connections and by considering word
embedding (WE) in the internal representations. Overall, the HTR outperformed the
other state-of-the-art reservoir-based approaches and it resulted in extremely
efficient with respect to typical recurrent neural networks (RNNs) in deep
learning (DL) [e.g., long short term memory (LSTMs)]. The HTR architecture is
proposed as a step toward the modeling of online and hierarchical processes at
work in the brain during language comprehension.

DOI: 10.1109/TNNLS.2021.3095140
PMID: 34570710

Know more about