Empower Distantly Supervised Relation Extraction with Collaborative Adversarial Training

With recent advances in distantly supervised (DS) relation extraction (RE), considerable attention is attracted to leverage multi-instance learning (MIL) to distill high-quality supervision from the noisy DS. Here, we go beyond label noise and identify the key bottleneck of DS-MIL to be its low data utilization: as high-quality supervision being refined by MIL, MIL abandons a large amount of training instances, which leads to a low data utilization and hinders model training from having abundant supervision. In this paper, we propose collaborative adversarial training to improve the data utilization, which coordinates virtual adversarial training (VAT) and adversarial training (AT) at different levels. Specifically, since VAT is label-free, we employ the instance-level VAT to recycle instances abandoned by MIL. Besides, we deploy AT at the bag-level to unleash the full potential of the high-quality supervision got by MIL. Our proposed method brings consistent improvements (~ 5 absolute AUC score) to the previous state of the art, which verifies the importance of the data utilization issue and the effectiveness of our method.

Multi-head or Single-head? An Empirical Comparison for Transformer Training

Multi-head attention plays a crucial role in the recent success of Transformer models, which leads to consistent performance improvements over conventional attention in various applications. The popular belief is that this effectiveness stems from the ability of jointly attending multiple positions. In this paper, we first demonstrate that jointly attending multiple positions is not a unique feature of multi-head attention, as multi-layer single-head attention also attends multiple positions and is more effective. Then, we suggest the main advantage of the multi-head attention is the training stability, since it has less number of layers than the single-head attention, when attending the same number of positions. For example, 24-layer 16-head Transformer (BERT-large) and 384-layer single-head Transformer has the same total attention head number and roughly the same model size, while the multi-head one is significantly shallower. Meanwhile, we show that, with recent advances in deep learning, we can successfully stabilize the training of the 384-layer Transformer. As the training difficulty is no longer a bottleneck, substantially deeper single-head Transformer achieves consistent performance improvements without tuning hyper-parameters.

Data Profiling for Adversarial Training: On the Ruin of Problematic Data

There are multiple intriguing problems hovering in adversarial training, including robustness-accuracy trade-off, robust overfitting, and robustness overestimation. These problems pose great challenges to both reliable evaluation and practical deployment. Here, we show that these problems share one common cause -- low quality samples in the dataset. We first identify an intrinsic property of the data called emph{problematic score} and then design controlled experiments to investigate its connections with these problems. Specifically, we find that when problematic data is removed, robust overfitting and robustness overestimation can be largely alleviated; and robustness-accuracy trade-off becomes less significant. These observations not only verify our intuition about data quality but also open new opportunities to advance adversarial training. Interestingly, simply removing problematic data from adversarial training, while making the training set smaller, yields better robustness for leading adversarial training strategies.

On the Transformer Growth for Progressive BERT Training

Due to the excessive cost of large-scale language model pre-training, considerable efforts have been made to train BERT progressively -- start from an inferior but low-cost model and gradually grow the model to increase the computational complexity. Our objective is to advance the understanding of Transformer growth and discover principles that guide progressive training. First, we find that similar to network architecture search, Transformer growth also favors compound scaling. Specifically, while existing methods only conduct network growth in a single dimension, we observe that it is beneficial to use compound growth operators and balance multiple dimensions (e.g., depth, width, and input length of the model). Moreover, we explore alternative growth operators in each dimension via controlled comparison to give operator selection practical guidance. In light of our analyses, the proposed method speeds up BERT pre-training by 73.6% and 82.2% for the base and large models respectively, while achieving comparable performances

Overfitting or Underfitting? Understand Robustness Drop in Adversarial Training

Our goal is to understand why the robustness drops after conducting adversarial training for too long. Although this phenomenon is commonly explained as overfitting, our analysis suggest that its primary cause is perturbation underfitting. We observe that after training for too long, FGSM-generated perturbations deteriorate into random noise. Intuitively, since no parameter updates are made to strengthen the perturbation generator, once this process collapses, it could be trapped in such local optima. Also, sophisticating this process could mostly avoid the robustness drop, which supports that this phenomenon is caused by underfitting instead of overfitting. In the light of our analyses, we propose APART, an adaptive adversarial training framework, which parameterizes perturbation generation and progressively strengthens them. Shielding perturbations from underfitting unleashes the potential of our framework. In our experiments, APART provides comparable or even better robustness than PGD-10, with only about 1/4 of its computational cost.

Very Deep Transformers for Neural Machine Translation

We explore the application of very deep Transformer models for Neural Machine Translation (NMT). Using a simple yet effective initialization technique that stabilizes training, we show that it is feasible to build standard Transformer-based models with up to 60 encoder layers and 12 decoder layers. These deep models outperform their baseline 6-layer counterparts by as much as 2.5 BLEU, and achieve new state-of-the-art benchmark results on WMT14 English-French (43.8 BLEU and 46.4 BLEU with back-translation) and WMT14 English-German (30.1 BLEU).The code and trained models will be publicly available at: https://github.com/namisan/exdeep-nmt.

Recent Progress on Electrical Excitation and Manipulation of Spin-Waves in Spin Hall Nano-Oscillators

Spin waves (SWs), the collective precessional motion of spins in a magnetic system, have been proposed as a promising alternative system with low-power consumption for encoding information. Spin Hall nano-oscillator (SHNO), a new-type spintronic nano-device, can electrically excite and control spin waves in both nanoscale magnetic metals and insulators with low damping by the spin current due to spin Hall effect. Here, we will review recent progress about spin-wave excitation and experimental parameters dependent spectrum in SHNOs. The nanogap SHNOs based on in-plane magnetization Py/Pt exhibits a nonlinear self-localized bullet soliton localized at the center of the gap between the electrodes and a secondary high-frequency mode which coexists with the primary bullet mode at higher currents. While in the nanogap SHNOs with strong perpendicular magnetic anisotropy (PMA), besides both nonlinear bullet soliton and propagating spin-wave mode are achieved and controlled by varying the external magnetic field and current, the magnetic bubble skyrmion mode also can be excited at a low in-plane magnetic field. These SW modes show thermal-induced mode hopping behavior at high temperature due to the coupling between modes mediated by thermal-magnon-mediated scattering. Moreover, thanks to PMA-induced effective field, a single coherent mode also can be achieved without applying an external magnetic field. The strong nonlinear effect of spin-waves makes SHNOs easy to achieve synchronization with external microwave signals or mutual synchronization between multiple oscillators with improving the coherence and power of oscillation modes significantly. Spin-waves in SHNOs with an external free magnetic layer have a wide range of applications from as a nanoscale signal source of low-power consumption magnonic devices to spin-based neuromorphic computing systems in the field of artificial intelligence.

Partially-Typed NER Datasets Integration: Connecting Practice to Theory

While typical named entity recognition (NER) models require the training set to be annotated with all target types, each available datasets may only cover a part of them. Instead of relying on fully-typed NER datasets, many efforts have been made to leverage multiple partially-typed ones for training and allow the resulting model to cover a full type set. However, there is neither guarantee on the quality of integrated datasets, nor guidance on the design of training algorithms. Here, we conduct a systematic analysis and comparison between partially-typed NER datasets and fully-typed ones, in both theoretical and empirical manner. Firstly, we derive a bound to establish that models trained with partially-typed annotations can reach a similar performance with the ones trained with fully-typed annotations, which also provides guidance on the algorithm design. Moreover, we conduct controlled experiments, which shows partially-typed datasets leads to similar performance with the model trained with the same amount of fully-typed annotations

Understanding the Difficulty of Training Transformers

Transformers have proved effective in many NLP tasks. However, their training requires non-trivial efforts regarding designing cutting-edge optimizers and learning rate schedulers carefully (e.g., conventional SGD fails to train Transformers effectively). Our objective here is to understand $textit{what complicates Transformer training}$ from both empirical and theoretical perspectives. Our analysis reveals that unbalanced gradients are not the root cause of the instability of training. Instead, we identify an amplification effect that influences training substantially -- for each layer in a multi-layer Transformer model, heavy dependency on its residual branch makes training unstable, since it amplifies small parameter perturbations (e.g., parameter updates) and results in significant disturbances in the model output. Yet we observe that a light dependency limits the model potential and leads to inferior trained models. Inspired by our analysis, we propose Admin ($textbf{Ad}$aptive $textbf{m}$odel $textbf{in}$itialization) to stabilize stabilize the early stages training and unleash its full potential in the late stage. Extensive experiments show that Admin is more stable, converges faster, and leads to better performance. Implementations are released at: https://github.com/LiyuanLucasLiu/Transforemr-Clinic.

Raw-to-End Name Entity Recognition in Social Media

Taking word sequences as the input, typical named entity recognition (NER) models neglect errors from pre-processing (e.g., tokenization). However, these errors can influence the model performance greatly, especially for noisy texts like tweets. Here, we introduce Neural-Char-CRF, a raw-to-end framework that is more robust to pre-processing errors. It takes raw character sequences as inputs and makes end-to-end predictions. Word embedding and contextualized representation models are further tailored to capture textual signals for each character instead of each word. Our model neither requires the conversion from character sequences to word sequences, nor assumes tokenizer can correctly detect all word boundaries. Moreover, we observe our model performance remains unchanged after replacing tokenization with string matching, which demonstrates its potential to be tokenization-free. Extensive experimental results on two public datasets demonstrate the superiority of our proposed method over the state of the art. The implementations and datasets are made available at: https://github.com/LiyuanLucasLiu/Raw-to-End.