ﻻ يوجد ملخص باللغة العربية
In Automatic Speech Recognition it is still challenging to learn useful intermediate representations when using high-level (or abstract) target units such as words. For that reason, character or phoneme based systems tend to outperform word-based systems when just few hundreds of hours of training data are being used. In this paper, we first show how hierarchical multi-task training can encourage the formation of useful intermediate representations. We achieve this by performing Connectionist Temporal Classification at different levels of the network with targets of different granularity. Our model thus performs predictions in multiple scales for the same input. On the standard 300h Switchboard training setup, our hierarchical multi-task architecture exhibits improvements over single-task architectures with the same number of parameters. Our model obtains 14.0% Word Error Rate on the Eval2000 Switchboard subset without any decoder or language model, outperforming the current state-of-the-art on acoustic-to-word models.
Recently, there has been an increasing interest in end-to-end speech recognition that directly transcribes speech to text without any predefined alignments. One approach is the attention-based encoder-decoder framework that learns a mapping between v
We present methods for multi-task learning that take advantage of natural groupings of related tasks. Task groups may be defined along known properties of the tasks, such as task domain or language. Such task groups represent supervised information a
This paper explores the task of answer-aware questions generation. Based on the attention-based pointer generator model, we propose to incorporate an auxiliary task of language modeling to help question generation in a hierarchical multi-task learnin
Sentiment analysis is directly affected by compositional phenomena in language that act on the prior polarity of the words and phrases found in the text. Negation is the most prevalent of these phenomena and in order to correctly predict sentiment, a
Recently, there have been significant advances in neural methods for tackling knowledge-intensive tasks such as open domain question answering (QA). These advances are fueled by combining large pre-trained language models with learnable retrieval of