Orthogonality constraints encourage matrices to be orthogonal for numerical stability. These plug-and-play constraints, which can be conveniently incorporated into model training, have been studied for popular architectures in natural language processing, such as convolutional neural networks and recurrent neural networks. However, a dedicated study on such constraints for transformers has been absent. To fill this gap, this paper studies orthogonality constraints for transformers, showing the effectiveness with empirical evidence from ten machine translation tasks and two dialogue generation tasks. For example, on the large-scale WMT’16 En→De benchmark, simply plugging-and-playing orthogonality constraints on the original transformer model (Vaswani et al., 2017) increases the BLEU from 28.4 to 29.6, coming close to the 29.7 BLEU achieved by the very competitive dynamic convolution (Wu et al., 2019).

This paper demonstrates a fatal vulnerability in natural language inference (NLI) and text classification systems. More concretely, we present a ‘backdoor poisoning’ attack on NLP models. Our poisoning attack utilizes conditional adversarially regularized autoencoder (CARA) to generate poisoned training samples by poison injection in latent space. Just by adding 1% poisoned data, our experiments show that a victim BERT finetuned classifier’s predictions can be steered to the poison target class with success rates of >80% when the input hypothesis is injected with the poison signature, demonstrating that NLI and text classification systems face a huge security risk.

Deep learning has become the dominant approach to NLP problems, especially when applied on large scale corpora. Recent progress on unsupervised pre-training techniques such as BERT, ELMo, GPT-2, and language modeling in general, when applied on large corpora, is shown to be effective in improving a wide variety of downstream tasks. These techniques push the limits of available hardware, requiring specialized frameworks optimized for GPU, ASIC, and distributed cloud-based training.A few complexities pose challenges to scale these models and algorithms effectively. Compared to other areas where deep learning is applied, these NLP models contain a variety of moving parts: text normalization and tokenization, word representation at subword-level and word-level, variable-length models such as RNN and attention, and sequential decoder based on beam search, among others.In this hands-on tutorial, we take a closer look at the challenges from these complexities and see how with proper tooling with Apache MXNet and GluonNLP, we can overcome these challenges and achieve state-of-the-art results for real-world problems. GluonNLP is a powerful new toolkit that combines MXNet’s speed, the flexibility of Gluon, and an extensive new library automating the most laborious aspects of deep learning for NLP.

Many state-of-the-art neural models for NLP are heavily parameterized and thus memory inefficient. This paper proposes a series of lightweight and memory efficient neural architectures for a potpourri of natural language processing (NLP) tasks. To this end, our models exploit computation using Quaternion algebra and hypercomplex spaces, enabling not only expressive inter-component interactions but also significantly (75%) reduced parameter size due to lesser degrees of freedom in the Hamilton product. We propose Quaternion variants of models, giving rise to new architectures such as the Quaternion attention Model and Quaternion Transformer. Extensive experiments on a battery of NLP tasks demonstrates the utility of proposed Quaternion-inspired models, enabling up to 75% reduction in parameter size without significant loss in performance.

This paper tackles the problem of reading comprehension over long narratives where documents easily span over thousands of tokens. We propose a curriculum learning (CL) based Pointer-Generator framework for reading/sampling over large documents, enabling diverse training of the neural model based on the notion of alternating contextual difficulty. This can be interpreted as a form of domain randomization and/or generative pretraining during training. To this end, the usage of the Pointer-Generator softens the requirement of having the answer within the context, enabling us to construct diverse training samples for learning. Additionally, we propose a new Introspective Alignment Layer (IAL), which reasons over decomposed alignments using block-based self-attention. We evaluate our proposed method on the NarrativeQA reading comprehension benchmark, achieving state-of-the-art performance, improving existing baselines by 51% relative improvement on BLEU-4 and 17% relative improvement on Rouge-L. Extensive ablations confirm the effectiveness of our proposed IAL and CL components.

Recent literature has shown a wide variety of benefits to mapping traditional one-hot representations of words and phrases to lower-dimensional real-valued vectors known as word embeddings. Traditionally, most word embedding algorithms treat each word as the finest meaningful semantic granularity and perform embedding by learning distinct embedding vectors for each word. Contrary to this line of thought, technical domains such as scientific and medical literature compose words from subword structures such as prefixes, suffixes, and root-words as well as compound words. Treating individual words as the finest-granularity unit discards meaningful shared semantic structure between words sharing substructures. This not only leads to poor embeddings for text corpora that have long-tail distributions, but also heuristic methods for handling out-of-vocabulary words. In this paper we propose SubwordMine, an entropy-based subword mining algorithm that is fast, unsupervised, and fully data-driven. We show that this allows for great cross-domain performance in identifying semantically meaningful subwords. We then investigate utilizing the mined subwords within the FastText embedding model and compare performance of the learned representations in a downstream language modeling task.