All Articles

Hot Papers 2021-01-01

1. Out of Order: How important is the sequential order of words in a sentence in Natural Language Understanding tasks?

Thang M. Pham, Trung Bui, Long Mai, Anh Nguyen

Do state-of-the-art natural language understanding models care about word order - one of the most important characteristics of a sequence? Not always! We found 75% to 90% of the correct predictions of BERT-based classifiers, trained on many GLUE tasks, remain constant after input words are randomly shuffled. Despite BERT embeddings are famously contextual, the contribution of each individual word to downstream tasks is almost unchanged even after the word’s context is shuffled. BERT-based models are able to exploit superficial cues (e.g. the sentiment of keywords in sentiment analysis; or the word-wise similarity between sequence-pair inputs in natural language inference) to make correct decisions when tokens are arranged in random orders. Encouraging classifiers to capture word order information improves the performance on most GLUE tasks, SQuAD 2.0 and out-of-samples. Our work suggests that many GLUE tasks are not challenging machines to understand the meaning of a sentence.

2. Reinforcement Learning for Control of Valves

Rajesh Siraskar

This paper compares reinforcement learning (RL) with PID (proportional-integral-derivative) strategy for control of nonlinear valves using a unified framework. RL is an autonomous learning mechanism that learns by interacting with its environment. It is gaining increasing attention in the world of control systems as a means of building optimal-controllers for challenging dynamic and nonlinear processes. Published RL research often uses open-source tools (Python and OpenAI Gym environments) which could be difficult to adapt and apply by practicing industrial engineers, we therefore used MathWorks tools. MATLAB’s recently launched (R2019a) Reinforcement Learning Toolbox was used to develop the valve controller; trained using the DDPG (Deep Deterministic Policy-Gradient) algorithm and Simulink to simulate the nonlinear valve and setup the experimental test-bench to evaluate the RL and PID controllers. Results indicate that the RL controller is extremely good at tracking the signal with speed and produces a lower error with respect to the reference signals. The PID, however, is better at disturbance rejection and hence provides a longer life for the valves. Experiential learnings gained from this research are corroborated against published research. It is known that successful machine learning involves tuning many hyperparameters and significant investment of time and efforts. We introduce Graded Learning" as a simplified, application oriented adaptation of the more formal and algorithmicCurriculum for Reinforcement Learning”. It is shown via experiments that it helps converge the learning task of complex non-linear real world systems.

3. Transformer Feed-Forward Layers Are Key-Value Memories

Mor Geva, Roei Schuster, Jonathan Berant, Omer Levy

  • retweets: 4221, favorites: 290 (01/04/2021 10:51:45)
  • links: abs | pdf
  • cs.CL

Feed-forward layers constitute two-thirds of a transformer model’s parameters, yet their role in the network remains under-explored. We show that feed-forward layers in transformer-based language models operate as key-value memories, where each key correlates with textual patterns in the training examples, and each value induces a distribution over the output vocabulary. Our experiments show that the learned patterns are human-interpretable, and that lower layers tend to capture shallow patterns, while upper layers learn more semantic ones. The values complement the keys’ input patterns by inducing output distributions that concentrate probability mass on tokens likely to appear immediately after each pattern, particularly in the upper layers. Finally, we demonstrate that the output of a feed-forward layer is a composition of its memories, which is subsequently refined throughout the model’s layers via residual connections to produce the final output distribution.

4. A Memory Efficient Baseline for Open Domain Question Answering

Gautier Izacard, Fabio Petroni, Lucas Hosseini, Nicola De Cao, Sebastian Riedel, Edouard Grave

  • retweets: 2401, favorites: 202 (01/04/2021 10:51:46)
  • links: abs | pdf
  • cs.CL

Recently, retrieval systems based on dense representations have led to important improvements in open-domain question answering, and related tasks. While very effective, this approach is also memory intensive, as the dense vectors for the whole knowledge source need to be kept in memory. In this paper, we study how the memory footprint of dense retriever-reader systems can be reduced. We consider three strategies to reduce the index size: dimension reduction, vector quantization and passage filtering. We evaluate our approach on two question answering benchmarks: TriviaQA and NaturalQuestions, showing that it is possible to get competitive systems using less than 6Gb of memory.

5. Improving Zero-Shot Translation by Disentangling Positional Information

Danni Liu, Jan Niehues, James Cross, Francisco Guzmán, Xian Li

  • retweets: 1640, favorites: 296 (01/04/2021 10:51:46)
  • links: abs | pdf
  • cs.CL

Multilingual neural machine translation has shown the capability of directly translating between language pairs unseen in training, i.e. zero-shot translation. Despite being conceptually attractive, it often suffers from low output quality. The difficulty of generalizing to new translation directions suggests the model representations are highly specific to those language pairs seen in training. We demonstrate that a main factor causing the language-specific representations is the positional correspondence to input tokens. We show that this can be easily alleviated by removing residual connections in an encoder layer. With this modification, we gain up to 18.5 BLEU points on zero-shot translation while retaining quality on supervised directions. The improvements are particularly prominent between related languages, where our proposed model outperforms pivot-based translation. Moreover, our approach allows easy integration of new languages, which substantially expands translation coverage. By thorough inspections of the hidden layer outputs, we show that our approach indeed leads to more language-independent representations.

6. Fully Non-autoregressive Neural Machine Translation: Tricks of the Trade

Jiatao Gu, Xiang Kong

  • retweets: 1368, favorites: 229 (01/04/2021 10:51:46)
  • links: abs | pdf
  • cs.CL

Fully non-autoregressive neural machine translation (NAT) is proposed to simultaneously predict tokens with single forward of neural networks, which significantly reduces the inference latency at the expense of quality drop compared to the Transformer baseline. In this work, we target on closing the performance gap while maintaining the latency advantage. We first inspect the fundamental issues of fully NAT models, and adopt dependency reduction in the learning space of output tokens as the basic guidance. Then, we revisit methods in four different aspects that have been proven effective for improving NAT models, and carefully combine these techniques with necessary modifications. Our extensive experiments on three translation benchmarks show that the proposed system achieves the new state-of-the-art results for fully NAT models, and obtains comparable performance with the autoregressive and iterative NAT systems. For instance, one of the proposed models achieves 27.49 BLEU points on WMT14 En-De with approximately 16.5X speed up at inference time.

7. Neural Body: Implicit Neural Representations with Structured Latent Codes for Novel View Synthesis of Dynamic Humans

Sida Peng, Yuanqing Zhang, Yinghao Xu, Qianqian Wang, Qing Shuai, Hujun Bao, Xiaowei Zhou

  • retweets: 1156, favorites: 173 (01/04/2021 10:51:46)
  • links: abs | pdf
  • cs.CV

This paper addresses the challenge of novel view synthesis for a human performer from a very sparse set of camera views. Some recent works have shown that learning implicit neural representations of 3D scenes achieves remarkable view synthesis quality given dense input views. However, the representation learning will be ill-posed if the views are highly sparse. To solve this ill-posed problem, our key idea is to integrate observations over video frames. To this end, we propose Neural Body, a new human body representation which assumes that the learned neural representations at different frames share the same set of latent codes anchored to a deformable mesh, so that the observations across frames can be naturally integrated. The deformable mesh also provides geometric guidance for the network to learn 3D representations more efficiently. Experiments on a newly collected multi-view dataset show that our approach outperforms prior works by a large margin in terms of the view synthesis quality. We also demonstrate the capability of our approach to reconstruct a moving person from a monocular video on the People-Snapshot dataset. The code and dataset will be available at https://zju3dv.github.io/neuralbody/.

8. Is Pessimism Provably Efficient for Offline RL?

Ying Jin, Zhuoran Yang, Zhaoran Wang

We study offline reinforcement learning (RL), which aims to learn an optimal policy based on a dataset collected a priori. Due to the lack of further interactions with the environment, offline RL suffers from the insufficient coverage of the dataset, which eludes most existing theoretical analysis. In this paper, we propose a pessimistic variant of the value iteration algorithm (PEVI), which incorporates an uncertainty quantifier as the penalty function. Such a penalty function simply flips the sign of the bonus function for promoting exploration in online RL, which makes it easily implementable and compatible with general function approximators. Without assuming the sufficient coverage of the dataset, we establish a data-dependent upper bound on the suboptimality of PEVI for general Markov decision processes (MDPs). When specialized to linear MDPs, it matches the information-theoretic lower bound up to multiplicative factors of the dimension and horizon. In other words, pessimism is not only provably efficient but also minimax optimal. In particular, given the dataset, the learned policy serves as the best effort'' among all policies, as no other policies can do better. Our theoretical analysis identifies the critical role of pessimism in eliminating a notion of spurious correlation, which emerges from theirrelevant” trajectories that are less covered by the dataset and not informative for the optimal policy.

9. Studying Strategically: Learning to Mask for Closed-book QA

Qinyuan Ye, Belinda Z. Li, Sinong Wang, Benjamin Bolte, Hao Ma, Xiang Ren, Wen-tau Yih, Madian Khabsa

  • retweets: 930, favorites: 157 (01/04/2021 10:51:47)
  • links: abs | pdf
  • cs.CL | cs.AI

Closed-book question-answering (QA) is a challenging task that requires a model to directly answer questions without access to external knowledge. It has been shown that directly fine-tuning pre-trained language models with (question, answer) examples yields surprisingly competitive performance, which is further improved upon through adding an intermediate pre-training stage between general pre-training and fine-tuning. Prior work used a heuristic during this intermediate stage, whereby named entities and dates are masked, and the model is trained to recover these tokens. In this paper, we aim to learn the optimal masking strategy for the intermediate pretraining stage. We first train our masking policy to extract spans that are likely to be tested, using supervision from the downstream task itself, then deploy the learned policy during intermediate pre-training. Thus, our policy packs task-relevant knowledge into the parameters of a language model. Our approach is particularly effective on TriviaQA, outperforming strong heuristics when used to pre-train BART.

10. NeuralMagicEye: Learning to See and Understand the Scene Behind an Autostereogram

Zhengxia Zou, Tianyang Shi, Yi Yuan, Zhenwei Shi

  • retweets: 882, favorites: 181 (01/04/2021 10:51:47)
  • links: abs | pdf
  • cs.CV

An autostereogram, a.k.a. magic eye image, is a single-image stereogram that can create visual illusions of 3D scenes from 2D textures. This paper studies an interesting question that whether a deep CNN can be trained to recover the depth behind an autostereogram and understand its content. The key to the autostereogram magic lies in the stereopsis - to solve such a problem, a model has to learn to discover and estimate disparity from the quasi-periodic textures. We show that deep CNNs embedded with disparity convolution, a novel convolutional layer proposed in this paper that simulates stereopsis and encodes disparity, can nicely solve such a problem after being sufficiently trained on a large 3D object dataset in a self-supervised fashion. We refer to our method as NeuralMagicEye”. Experiments show that our method can accurately recover the depth behind autostereograms with rich details and gradient smoothness. Experiments also show the completely different working mechanisms for autostereogram perception between neural networks and human eyes. We hope this research can help people with visual impairments and those who have trouble viewing autostereograms. Our code is available at \url{https://jiupinjia.github.io/neuralmagiceye/}.

11. Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers

Sixiao Zheng, Jiachen Lu, Hengshuang Zhao, Xiatian Zhu, Zekun Luo, Yabiao Wang, Yanwei Fu, Jianfeng Feng, Tao Xiang, Philip H.S. Torr, Li Zhang

  • retweets: 650, favorites: 98 (01/04/2021 10:51:48)
  • links: abs | pdf
  • cs.CV

Most recent semantic segmentation methods adopt a fully-convolutional network (FCN) with an encoder-decoder architecture. The encoder progressively reduces the spatial resolution and learns more abstract/semantic visual concepts with larger receptive fields. Since context modeling is critical for segmentation, the latest efforts have been focused on increasing the receptive field, through either dilated/atrous convolutions or inserting attention modules. However, the encoder-decoder based FCN architecture remains unchanged. In this paper, we aim to provide an alternative perspective by treating semantic segmentation as a sequence-to-sequence prediction task. Specifically, we deploy a pure transformer (ie, without convolution and resolution reduction) to encode an image as a sequence of patches. With the global context modeled in every layer of the transformer, this encoder can be combined with a simple decoder to provide a powerful segmentation model, termed SEgmentation TRansformer (SETR). Extensive experiments show that SETR achieves new state of the art on ADE20K (50.28% mIoU), Pascal Context (55.83% mIoU) and competitive results on Cityscapes. Particularly, we achieve the first (44.42% mIoU) position in the highly competitive ADE20K test server leaderboard.

12. FastIF: Scalable Influence Functions for Efficient Model Interpretation and Debugging

Han Guo, Nazneen Fatema Rajani, Peter Hase, Mohit Bansal, Caiming Xiong

Influence functions approximate the ‘influences’ of training data-points for test predictions and have a wide variety of applications. Despite the popularity, their computational cost does not scale well with model and training data size. We present FastIF, a set of simple modifications to influence functions that significantly improves their run-time. We use k-Nearest Neighbors (kNN) to narrow the search space down to a subset of good candidate data points, identify the configurations that best balance the speed-quality trade-off in estimating the inverse Hessian-vector product, and introduce a fast parallel variant. Our proposed method achieves about 80x speedup while being highly correlated with the original influence values. With the availability of the fast influence functions, we demonstrate their usefulness in four applications. First, we examine whether influential data-points can ‘explain’ test time behavior using the framework of simulatability. Second, we visualize the influence interactions between training and test data-points. Third, we show that we can correct model errors by additional fine-tuning on certain influential data-points, improving the accuracy of a trained MNLI model by 2.6% on the HANS challenge set using a small number of gradient updates. Finally, we experiment with a data-augmentation setup where we use influence functions to search for new data-points unseen during training to improve model performance. Overall, our fast influence functions can be efficiently applied to large models and datasets, and our experiments demonstrate the potential of influence functions in model interpretation and correcting model errors. Code is available at https://github.com/salesforce/fast-influence-functions

13. OSTeC: One-Shot Texture Completion

Baris Gecer, Jiankang Deng, Stefanos Zafeiriou

  • retweets: 484, favorites: 124 (01/04/2021 10:51:48)
  • links: abs | pdf
  • cs.CV

The last few years have witnessed the great success of non-linear generative models in synthesizing high-quality photorealistic face images. Many recent 3D facial texture reconstruction and pose manipulation from a single image approaches still rely on large and clean face datasets to train image-to-image Generative Adversarial Networks (GANs). Yet the collection of such a large scale high-resolution 3D texture dataset is still very costly and difficult to maintain age/ethnicity balance. Moreover, regression-based approaches suffer from generalization to the in-the-wild conditions and are unable to fine-tune to a target-image. In this work, we propose an unsupervised approach for one-shot 3D facial texture completion that does not require large-scale texture datasets, but rather harnesses the knowledge stored in 2D face generators. The proposed approach rotates an input image in 3D and fill-in the unseen regions by reconstructing the rotated image in a 2D face generator, based on the visible parts. Finally, we stitch the most visible textures at different angles in the UV image-plane. Further, we frontalize the target image by projecting the completed texture into the generator. The qualitative and quantitative experiments demonstrate that the completed UV textures and frontalized images are of high quality, resembles the original identity, can be used to train a texture GAN model for 3DMM fitting and improve pose-invariant face recognition.

14. TransTrack: Multiple-Object Tracking with Transformer

Peize Sun, Yi Jiang, Rufeng Zhang, Enze Xie, Jinkun Cao, Xinting Hu, Tao Kong, Zehuan Yuan, Changhu Wang, Ping Luo

  • retweets: 372, favorites: 232 (01/04/2021 10:51:48)
  • links: abs | pdf
  • cs.CV

Multiple-object tracking(MOT) is mostly dominated by complex and multi-step tracking-by-detection algorithm, which performs object detection, feature extraction and temporal association, separately. Query-key mechanism in single-object tracking(SOT), which tracks the object of the current frame by object feature of the previous frame, has great potential to set up a simple joint-detection-and-tracking MOT paradigm. Nonetheless, the query-key method is seldom studied due to its inability to detect new-coming objects. In this work, we propose TransTrack, a baseline for MOT with Transformer. It takes advantage of query-key mechanism and introduces a set of learned object queries into the pipeline to enable detecting new-coming objects. TransTrack has three main advantages: (1) It is an online joint-detection-and-tracking pipeline based on query-key mechanism. Complex and multi-step components in the previous methods are simplified. (2) It is a brand new architecture based on Transformer. The learned object query detects objects in the current frame. The object feature query from the previous frame associates those current objects with the previous ones. (3) For the first time, we demonstrate a much simple and effective method based on query-key mechanism and Transformer architecture could achieve competitive 65.8% MOTA on the MOT17 challenge dataset. We hope TransTrack can provide a new perspective for multiple-object tracking. The code is available at: \url{https://github.com/PeizeSun/TransTrack}.

15. Linguistic calibration through metacognition: aligning dialogue agent responses with expected correctness

Sabrina J. Mielke, Arthur Szlam, Y-Lan Boureau, Emily Dinan

Open-domain dialogue agents have vastly improved, but still confidently hallucinate knowledge or express doubt when asked straightforward questions. In this work, we analyze whether state-of-the-art chit-chat models can express metacognition capabilities through their responses: does a verbalized expression of doubt (or confidence) match the likelihood that the model’s answer is incorrect (or correct)? We find that these models are poorly calibrated in this sense, yet we show that the representations within the models can be used to accurately predict likelihood of correctness. By incorporating these correctness predictions into the training of a controllable generation model, we obtain a dialogue agent with greatly improved linguistic calibration.

16. Combinatorial Pure Exploration with Full-bandit Feedback and Beyond: Solving Combinatorial Optimization under Uncertainty with Limited Observation

Yuko Kuroki, Junya Honda, Masashi Sugiyama

Combinatorial optimization is one of the fundamental research fields that has been extensively studied in theoretical computer science and operations research. When developing an algorithm for combinatorial optimization, it is commonly assumed that parameters such as edge weights are exactly known as inputs. However, this assumption may not be fulfilled since input parameters are often uncertain or initially unknown in many applications such as recommender systems, crowdsourcing, communication networks, and online advertisement. To resolve such uncertainty, the problem of combinatorial pure exploration of multi-armed bandits (CPE) and its variants have recieved increasing attention. Earlier work on CPE has studied the semi-bandit feedback or assumed that the outcome from each individual edge is always accessible at all rounds. However, due to practical constraints such as a budget ceiling or privacy concern, such strong feedback is not always available in recent applications. In this article, we review recently proposed techniques for combinatorial pure exploration problems with limited feedback.

17. CLEAR: Contrastive Learning for Sentence Representation

Zhuofeng Wu, Sinong Wang, Jiatao Gu, Madian Khabsa, Fei Sun, Hao Ma

  • retweets: 380, favorites: 119 (01/04/2021 10:51:49)
  • links: abs | pdf
  • cs.CL

Pre-trained language models have proven their unique powers in capturing implicit language features. However, most pre-training approaches focus on the word-level training objective, while sentence-level objectives are rarely studied. In this paper, we propose Contrastive LEArning for sentence Representation (CLEAR), which employs multiple sentence-level augmentation strategies in order to learn a noise-invariant sentence representation. These augmentations include word and span deletion, reordering, and substitution. Furthermore, we investigate the key reasons that make contrastive learning effective through numerous experiments. We observe that different sentence augmentations during pre-training lead to different performance improvements on various downstream tasks. Our approach is shown to outperform multiple existing methods on both SentEval and GLUE benchmarks.

18. BinaryBERT: Pushing the Limit of BERT Quantization

Haoli Bai, Wei Zhang, Lu Hou, Lifeng Shang, Jing Jin, Xin Jiang, Qun Liu, Michael Lyu, Irwin King

  • retweets: 210, favorites: 82 (01/04/2021 10:51:49)
  • links: abs | pdf
  • cs.CL

The rapid development of large pre-trained language models has greatly increased the demand for model compression techniques, among which quantization is a popular solution. In this paper, we propose BinaryBERT, which pushes BERT quantization to the limit with weight binarization. We find that a binary BERT is hard to be trained directly than a ternary counterpart due to its complex and irregular loss landscapes. Therefore, we propose ternary weight splitting, which initializes the binary model by equivalent splitting from a half-sized ternary network. The binary model thus inherits the good performance of the ternary model, and can be further enhanced by fine-tuning the new architecture after splitting. Empirical results show that BinaryBERT has negligible performance drop compared to the full-precision BERT-base while being 24×24\times smaller, achieving the state-of-the-art results on GLUE and SQuAD benchmarks.

19. Beyond Offline Mapping: Learning Cross Lingual Word Embeddings through Context Anchoring

Aitor Ormazabal, Mikel Artetxe, Aitor Soroa, Gorka Labaka, Eneko Agirre

Recent research on cross-lingual word embeddings has been dominated by unsupervised mapping approaches that align monolingual embeddings. Such methods critically rely on those embeddings having a similar structure, but it was recently shown that the separate training in different languages causes departures from this assumption. In this paper, we propose an alternative approach that does not have this limitation, while requiring a weak seed dictionary (e.g., a list of identical words) as the only form of supervision. Rather than aligning two fixed embedding spaces, our method works by fixing the target language embeddings, and learning a new set of embeddings for the source language that are aligned with them. To that end, we use an extension of skip-gram that leverages translated context words as anchor points, and incorporates self-learning and iterative restarts to reduce the dependency on the initial dictionary. Our approach outperforms conventional mapping methods on bilingual lexicon induction, and obtains competitive results in the downstream XNLI task.

20. Learning from the Worst: Dynamically Generated Datasets to Improve Online Hate Detection

Bertie Vidgen, Tristan Thrush, Zeerak Waseem, Douwe Kiela

  • retweets: 128, favorites: 33 (01/04/2021 10:51:49)
  • links: abs | pdf
  • cs.CL | cs.LG

We present a first-of-its-kind large synthetic training dataset for online hate classification, created from scratch with trained annotators over multiple rounds of dynamic data collection. We provide a 40,623 example dataset with annotations for fine-grained labels, including a large number of challenging contrastive perturbation examples. Unusually for an abusive content dataset, it comprises 54% hateful and 46% not hateful entries. We show that model performance and robustness can be greatly improved using the dynamic data collection paradigm. The model error rate decreased across rounds, from 72.1% in the first round to 35.8% in the last round, showing that models became increasingly harder to trick — even though content become progressively more adversarial as annotators became more experienced. Hate speech detection is an important and subtle problem that is still very challenging for existing AI methods. We hope that the models, dataset and dynamic system that we present here will help improve current approaches, having a positive social impact.

21. Audio-Visual Floorplan Reconstruction

Senthil Purushwalkam, Sebastian Vicenc Amengual Gari, Vamsi Krishna Ithapu, Carl Schissler, Philip Robinson, Abhinav Gupta, Kristen Grauman

  • retweets: 81, favorites: 36 (01/04/2021 10:51:50)
  • links: abs | pdf
  • cs.CV

Given only a few glimpses of an environment, how much can we infer about its entire floorplan? Existing methods can map only what is visible or immediately apparent from context, and thus require substantial movements through a space to fully map it. We explore how both audio and visual sensing together can provide rapid floorplan reconstruction from limited viewpoints. Audio not only helps sense geometry outside the camera’s field of view, but it also reveals the existence of distant freespace (e.g., a dog barking in another room) and suggests the presence of rooms not visible to the camera (e.g., a dishwasher humming in what must be the kitchen to the left). We introduce AV-Map, a novel multi-modal encoder-decoder framework that reasons jointly about audio and vision to reconstruct a floorplan from a short input video sequence. We train our model to predict both the interior structure of the environment and the associated rooms’ semantic labels. Our results on 85 large real-world environments show the impact: with just a few glimpses spanning 26% of an area, we can estimate the whole area with 66% accuracy — substantially better than the state of the art approach for extrapolating visual maps.

22. kōan: A Corrected CBOW Implementation

Ozan İrsoy, Adrian Benton, Karl Stratos

It is a common belief in the NLP community that continuous bag-of-words (CBOW) word embeddings tend to underperform skip-gram (SG) embeddings. We find that this belief is founded less on theoretical differences in their training objectives but more on faulty CBOW implementations in standard software libraries such as the official implementation word2vec.c and Gensim. We show that our correct implementation of CBOW yields word embeddings that are fully competitive with SG on various intrinsic and extrinsic tasks while being more than three times as fast to train. We release our implementation, k=oan, at https://github.com/bloomberg/koan.

23. Adaptive Extreme Edge Computing for Wearable Devices

Erika Covi, Elisa Donati, Hadi Heidari, David Kappel, Xiangpeng Liang, Melika Payvand, Wei Wang

  • retweets: 56, favorites: 46 (01/04/2021 10:51:50)
  • links: abs | pdf
  • cs.ET

Wearable devices are a fast-growing technology with impact on personal healthcare for both society and economy. Due to the widespread of sensors in pervasive and distributed networks, power consumption, processing speed, and system adaptation are vital in future smart wearable devices. The visioning and forecasting of how to bring computation to the edge in smart sensors have already begun, with an aspiration to provide adaptive extreme edge computing. Here, we provide a holistic view of hardware and theoretical solutions towards smart wearable devices that can provide guidance to research in this pervasive computing era. We propose various solutions for biologically plausible models for continual learning in neuromorphic computing technologies for wearable sensors. To envision this concept, we provide a systematic outline in which prospective low power and low latency scenarios of wearable sensors in neuromorphic platforms are expected. We successively describe vital potential landscapes of neuromorphic processors exploiting complementary metal-oxide semiconductors (CMOS) and emerging memory technologies (e.g. memristive devices). Furthermore, we evaluate the requirements for edge computing within wearable devices in terms of footprint, power consumption, latency, and data size. We additionally investigate the challenges beyond neuromorphic computing hardware, algorithms and devices that could impede enhancement of adaptive edge computing in smart wearable devices.

24. Reservoir Transformer

Sheng Shen, Alexei Baevski, Ari S. Morcos, Kurt Keutzer, Michael Auli, Douwe Kiela

  • retweets: 36, favorites: 59 (01/04/2021 10:51:50)
  • links: abs | pdf
  • cs.CL

We demonstrate that transformers obtain impressive performance even when some of the layers are randomly initialized and never updated. Inspired by old and well-established ideas in machine learning, we explore a variety of non-linear “reservoir” layers interspersed with regular transformer layers, and show improvements in wall-clock compute time until convergence, as well as overall performance, on various machine translation and (masked) language modelling tasks.

25. BANG: Bridging Autoregressive and Non-autoregressive Generation with Large Scale Pretraining

Weizhen Qi, Yeyun Gong, Jian Jiao, Yu Yan, Dayiheng Liu, Weizhu Chen, Kewen Tang, Houqiang Li, Jiusheng Chen, Ruofei Zhang, Ming Zhou, Nan Duan

  • retweets: 56, favorites: 39 (01/04/2021 10:51:50)
  • links: abs | pdf
  • cs.CL

In this paper, we propose BANG, a new pretraining model to Bridge the gap between Autoregressive (AR) and Non-autoregressive (NAR) Generation. AR and NAR generation can be uniformly regarded as what extend of previous tokens can be attended to, and BANG bridges AR and NAR generation through designing a novel model structure for large-scale pre-training. A pretrained BANG model can simultaneously support AR, NAR, and semi-NAR generation to meet different requirements. Experiments on question generation (SQuAD 1.1), summarization (XSum), and dialogue (PersonaChat) show that BANG improves NAR and semi-NAR performance significantly as well as attaining comparable performance with strong AR pretrained models. Compared with the semi-NAR strong baselines, BANG achieves absolute improvements of 14.01 and 5.24 in overall scores of SQuAD and XSum, respectively. In addition, BANG achieves absolute improvements of 10.73, 6.39, and 5.90 in overall scores of SQuAD, XSUM, and PersonaChat compared with the NAR strong baselines, respectively. Our code will be made publicly available in the near future\footnote{https://github.com/microsoft/BANG}.

26. HateCheck: Functional Tests for Hate Speech Detection Models

Paul Röttger, Bertram Vidgen, Dong Nguyen, Zeerak Waseem, Helen Margetts, Janet Pierrehumbert

  • retweets: 56, favorites: 21 (01/04/2021 10:51:50)
  • links: abs | pdf
  • cs.CL

Detecting online hate is a difficult task that even state-of-the-art models struggle with. In previous research, hate speech detection models are typically evaluated by measuring their performance on held-out test data using metrics such as accuracy and F1 score. However, this approach makes it difficult to identify specific model weak points. It also risks overestimating generalisable model quality due to increasingly well-evidenced systematic gaps and biases in hate speech datasets. To enable more targeted diagnostic insights, we introduce HateCheck, a first suite of functional tests for hate speech detection models. We specify 29 model functionalities, the selection of which we motivate by reviewing previous research and through a series of interviews with civil society stakeholders. We craft test cases for each functionality and validate data quality through a structured annotation process. To illustrate HateCheck’s utility, we test near-state-of-the-art transformer detection models as well as a popular commercial model, revealing critical model weaknesses.

27. Conditional Generation of Temporally-ordered Event Sequences

Shih-Ting Lin, Nathanael Chambers, Greg Durrett

  • retweets: 30, favorites: 45 (01/04/2021 10:51:50)
  • links: abs | pdf
  • cs.CL

Models encapsulating narrative schema knowledge have proven to be useful for a range of event-related tasks, but these models typically do not engage with temporal relationships between events. We present a a BART-based conditional generation model capable of capturing event cooccurrence as well as temporality of event sequences. This single model can address both temporal ordering, sorting a given sequence of events into the order they occurred, and event infilling, predicting new events which fit into a temporally-ordered sequence of existing ones. Our model is trained as a denoising autoencoder: we take temporally-ordered event sequences, shuffle them, delete some events, and then attempting to recover the original event sequence. In this fashion, the model learns to make inferences given incomplete knowledge about the events in an underlying scenario. On the temporal ordering task, we show that our model is able to unscramble event sequences from existing datasets without access to explicitly labeled temporal training data, outperforming both a BERT-based pairwise model and a BERT-based pointer network. On event infilling, human evaluation shows that our model is able to generate events that fit better temporally into the input events when compared to GPT-2 story completion models.

28. Simulation and Control of Deformable Autonomous Airships in Turbulent Wind

Eric Price, Yu Tang Liu, Michael J. Black, Aamir Ahmad

Abstract. Fixed wing and multirotor UAVs are common in the field of robotics. Solutions for simulation and control of these vehicles are ubiquitous. This is not the case for airships, a simulation of which needs to address unique properties, i) dynamic deformation in response to aerodynamic and control forces, ii) high susceptibility to wind and turbulence at low airspeed, iii) high variability in airship designs regarding placement, direction and vectoring of thrusters and control surfaces. We present a flexible framework for modeling, simulation and control of airships, based on the Robot operating system (ROS), simulation environment (Gazebo) and commercial off the shelf (COTS) electronics, both of which are open source. Based on simulated wind and deformation, we predict substantial effects on controllability, verified in real world flight experiments. All our code is shared as open source, for the benefit of the community and to facilitate lighter-than-air vehicle (LTAV) research. https://github.com/robot-perception-group/airship_simulation

29. Intrinsic Bias Metrics Do Not Correlate with Application Bias

Seraphina Goldfarb-Tarrant, Rebecca Marchant, Ricardo Muñoz Sanchez, Mugdha Pandya, Adam Lopez

  • retweets: 36, favorites: 22 (01/04/2021 10:51:51)
  • links: abs | pdf
  • cs.CL

Natural Language Processing (NLP) systems learn harmful societal biases that cause them to extend and proliferate inequality widely, as they are deployed in more and more situations. To address and combat this, the NLP community has come to rely on a variety of metrics to identify and quantify bias in black-box models, which are used to monitor model behaviour and to guide efforts at debiasing. Some of these metrics are intrinsic, and are measured in word embedding spaces, and some are extrinsic, which measure the bias present downstream in the tasks that the word embeddings are plugged into. This research examines whether intrinsic metrics (which are easy to measure) correlate well to extrinsic metrics (which reflect real world bias). We measure both intrinsic and extrinsic bias across hundreds of trained models covering different tasks and experimental conditions and find that there is no reliable correlation between these metrics that holds in more than extremely specific settings. We advise that efforts to debias embedding spaces be always also paired with measurement of downstream model bias, and suggest that that community direct more effort into making downstream measurement simpler and easier.

30. MiniLMv2: Multi-Head Self-Attention Relation Distillation for Compressing Pretrained Transformers

Wenhui Wang, Hangbo Bao, Shaohan Huang, Li Dong, Furu Wei

  • retweets: 16, favorites: 34 (01/04/2021 10:51:51)
  • links: abs | pdf
  • cs.CL

We generalize deep self-attention distillation in MiniLM (Wang et al., 2020) by only using self-attention relation distillation for task-agnostic compression of pretrained Transformers. In particular, we define multi-head self-attention relations as scaled dot-product between the pairs of query, key, and value vectors within each self-attention module. Then we employ the above relational knowledge to train the student model. Besides its simplicity and unified principle, more favorably, there is no restriction in terms of the number of student’s attention heads, while most previous work has to guarantee the same head number between teacher and student. Moreover, the fine-grained self-attention relations tend to fully exploit the interaction knowledge learned by Transformer. In addition, we thoroughly examine the layer selection strategy for teacher models, rather than just relying on the last layer as in MiniLM. Experimental results demonstrate that our models distilled from base-size and large-size teachers (BERT, and RoBERTa) outperform the state of the art.

Published 4 Jan 2021

ML Lead at Beatrust. (https://beatrust.com)Tatsuya Shirakawa on Twitter