We develop a large language model (LLM) based automatic speech recognition (ASR) system that can be contextualized by providing keywords as prior information in text prompts. We adopt decoder-only architecture and use our in-house LLM, PLaMo-100B, pre-trained from scratch using datasets dominated by Japanese and English texts as the decoder. We adopt a pre-trained Whisper encoder as an audio encoder, and the audio embeddings from the audio encoder are projected to the text embedding space by an adapter layer and concatenated with text embeddings converted from text prompts to form inputs to the decoder. By providing keywords as prior information in the text prompts, we can contextualize our LLM-based ASR system without modifying the model architecture to transcribe ambiguous words in the input audio accurately. Experimental results demonstrate that providing keywords to the decoder can significantly improve the recognition performance of rare and ambiguous words.

Building a commercial machine learning application is a challenging task. Therefore, following promising directions would save you a lot of time. In the previous article, I mentioned scales that drive machine learning progress. Building the proper model needs the right dataset. In this article, I will discuss dataset selection and how to make your dataset for machine learning models.

Using prompts to utilize language models to perform various downstream tasks, also known as prompt-based learning or prompt-learning, has lately gained significant success in comparison to the pre-train and fine-tune paradigm. Nonetheless, virtually all prompt-based methods are token-level, meaning they all utilize GPT's left-to-right language model or BERT's masked language model to perform cloze-style tasks. In this paper, we attempt to accomplish several NLP tasks in the zero-shot scenario using a BERT original pre-training task abandoned by RoBERTa and other models--Next Sentence Prediction (NSP). Unlike token-level techniques, our sentence-level prompt-based method NSP-BERT does not need to fix the length of the prompt or the position to be predicted, allowing it to handle tasks such as entity linking with ease. Based on the characteristics of NSP-BERT, we offer several quick building templates for various downstream tasks. We suggest a two-stage prompt method for word sense disambiguation tasks in particular. Our strategies for mapping the labels significantly enhance the model's performance on sentence pair tasks. On the FewCLUE benchmark, our NSP-BERT outperforms other zero-shot methods on most of these tasks and comes close to the few-shot methods.

AI, Machine Learning, and Deep Learning are rapidly evolving and transforming many industries. Andrew Y. Ng is one of the leading minds in the field - he is a co-Founder of Coursera, former head of Baidu AI Group, and a former head of Google Brain. He is writing a book, "Machine Learning Yearning" (you can get a free draft copy), to teach you how to structure Machine Learning projects. This book is focused not on teaching you ML algorithms, but on how to make ML algorithms work. Some technical AI classes will give you a hammer; this book teaches you how to use the hammer.

Welcome to the third chapter of ML lessons from Ng's experience! Yes, this one is the continuation of the series entirely based on a recent course by Andrew Ng on Coursera. Although this post can be an independent learning, reading the previous two articles will only help understand this one better. Here are the links to the first and second articles in the series. When trying to solve a new machine learning problem (one which does not have too many online resources available already), Andrew Ng advises to build you first system real quick and then iterate on it.

You have worked for weeks on building your machine learning system and the performance is not something you are satisfied with. You think of multiple ways to improve your algorithm's performance, viz, collect more data, add more hidden units, add more layers, change the network architecture, change the basic algorithm etc. But which one of these will give the best improvement on your system? You can either try them all, invest a lot of time and find out what works for you. You can use the following tips from Ng's experience.

One of the challenges with building machine learning systems is that there are so many things you could try, so many things you could change. Including, for example, so many hyperparameters you could tune. The art of knowing what parameter to tune to get what effect, is called orthogonalisation. In supervised learning, one needs to perform well on the following four tasks and for each of them, there should be a set of knobs which can be tuned for that task to perform well. Suppose, your algo isn't doing well on training set, you want one knob, or maybe one specific set of knobs that you can use, to make sure you can tune your algorithm to make it fit well on the training set.

Internet of @ThingsExpo, taking place June 6-8, 2017 at Javits Center, New York City, is co-located with 20th International @CloudExpo and will feature technical sessions from a rock star conference faculty and the leading industry players in the world. The Internet of Things (IoT) is the most profound change in personal and enterprise IT since the creation of the Worldwide Web more than 20 years ago. All major researchers estimate there will be tens of billions devices - computers, smartphones, tablets, and sensors - connected to the Internet by 2020. This number will continue to grow at a rapid pace for the next several decades. With major technology companies and startups seriously embracing IoT strategies, now is the perfect time to attend @ThingsExpo 2017 in New York and Silicon Valley.