The leading approaches in language modeling are all obsessed with TV shows of my youth - namely Transformers and Sesame Street. Transformers this, Transformers that, and over here a bonfire worth of GPU-TPU-neuromorphic wafer scale silicon. We opt for the lazy path of old and proven techniques with a fancy crypto inspired acronym: the Single Headed Attention RNN (SHA-RNN). The author's lone goal is to show that the entire field might have evolved a different direction if we had instead been obsessed with a slightly different acronym and slightly different result. We take a previously strong language model based only on boring LSTMs and get it to within a stone's throw of a stone's throw of state-of-the-art byte level language model results on enwik8. This work has undergone no intensive hyperparameter optimization and lived entirely on a commodity desktop machine that made the author's small studio apartment far too warm in the midst of a San Franciscan summer. The final results are achievable in plus or minus 24 hours on a single GPU as the author is impatient. The attention mechanism is also readily extended to large contexts with minimal computation. Take that Sesame Street.
Two of the most important aspects of machine learning models are feature extraction and feature engineering. Those features are what supply relevant information to the machine learning models. If the features are few or irrelevant, your model may have a hard time making any useful predictions. If there are too many features, your model will be slow and likely overfit. Humans don't necessarily know what feature representation are best for a given task.
Transformer networks have lead to important progress in language modeling and machine translation. These models include two consecutive modules, a feed-forward layer and a self-attention layer. The latter allows the network to capture long term dependencies and are often regarded as the key ingredient in the success of Transformers. Building upon this intuition, we propose a new model that solely consists of attention layers. More precisely, we augment the self-attention layers with persistent memory vectors that play a similar role as the feed-forward layer. Thanks to these vectors, we can remove the feed-forward layer without degrading the performance of a transformer. Our evaluation shows the benefits brought by our model on standard character and word level language modeling benchmarks.
The year 2018 has been an inflection point for machine learning models handling text (or more accurately, Natural Language Processing or NLP for short). Our conceptual understanding of how best to represent words and sentences in a way that best captures underlying meanings and relationships is rapidly evolving. Moreover, the NLP community has been putting forward incredibly powerful components that you can freely download and use in your own models and pipelines (It's been referred to as NLP's ImageNet moment, referencing how years ago similar developments accelerated the development of machine learning in Computer Vision tasks). But I couldn't think of anything else..) One of the latest milestones in this development is the release of BERT, an event described as marking the beginning of a new era in NLP. BERT is a model that broke several records for how well models can handle language-based tasks.
Neural Machine Translation (NMT) has achieved remarkable progress with the quick evolvement of model structures. In this paper, we propose the concept of layer-wise coordination for NMT, which explicitly coordinates the learning of hidden representations of the encoder and decoder together layer by layer, gradually from low level to high level. Specifically, we design a layer-wise attention and mixed attention mechanism, and further share the parameters of each layer between the encoder and decoder to regularize and coordinate the learning. Experiments show that combined with the state-of-the-art Transformer model, layer-wise coordination achieves improvements on three IWSLT and two WMT translation tasks. More specifically, our method achieves 34.43 and 29.01 BLEU score on WMT16 English-Romanian and WMT14 English-German tasks, outperforming the Transformer baseline.