arXiv subjects

Hao Cheng

Publications and source records attributed to Hao Cheng.

At least 235 records · Page 13Linked to original sources

arXiv2022

Human Parity on CommonsenseQA: Augmenting Self-Attention with External Attention

Most of today's AI systems focus on using self-attention mechanisms and transformer architectures on large amounts of diverse data to achieve impressive performance gains. In this paper, we propose to augment the transformer architecture with an external attention mechanism to bring external knowledge and context to bear. By integrating external information into the prediction process, we hope to reduce the need for ever-larger models and increase the democratization of AI systems. We find that the proposed external attention mechanism can significantly improve the performance of existing AI systems, allowing practitioners to easily customize foundation AI models to many diverse downstream applications. In particular, we focus on the task of Commonsense Reasoning, demonstrating that the proposed external attention mechanism can augment existing transformer models and significantly improve the model's reasoning capabilities. The proposed system, Knowledgeable External Attention for commonsense Reasoning (KEAR), reaches human parity on the open CommonsenseQA research benchmark with an accuracy of 89.4\% in comparison to the human accuracy of 88.9\%.

cs.CL↗

arXiv2022

Learning with Noisy Labels Revisited: A Study Using Real-World Human Annotations

Existing research on learning with noisy labels mainly focuses on synthetic label noise. Synthetic noise, though has clean structures which greatly enabled statistical analyses, often fails to model real-world noise patterns. The recent literature has observed several efforts to offer real-world noisy datasets, yet the existing efforts suffer from two caveats: (1) The lack of ground-truth verification makes it hard to theoretically study the property and treatment of real-world label noise; (2) These efforts are often of large scales, which may result in unfair comparisons of robust methods within reasonable and accessible computation power. To better understand real-world label noise, it is crucial to build controllable and moderate-sized real-world noisy datasets with both ground-truth and noisy labels. This work presents two new benchmark datasets CIFAR-10N, CIFAR-100N, equipping the training datasets of CIFAR-10, CIFAR-100 with human-annotated real-world noisy labels we collected from Amazon Mechanical Turk. We quantitatively and qualitatively show that real-world noisy labels follow an instance-dependent pattern rather than the classically assumed and adopted ones (e.g., class-dependent label noise). We then initiate an effort to benchmarking a subset of the existing solutions using CIFAR-10N and CIFAR-100N. We further proceed to study the memorization of correct and wrong predictions, which further illustrates the difference between human noise and class-dependent synthetic noise. We show indeed the real-world noise patterns impose new and outstanding challenges as compared to synthetic label noise. These observations require us to rethink the treatment of noisy labels, and we hope the availability of these two datasets would facilitate the development and evaluation of future learning with noisy label solutions. Datasets and leaderboards are available at http://noisylabels.com.

cs.LG↗

arXiv2022

Open Domain Question Answering with A Unified Knowledge Interface

The retriever-reader framework is popular for open-domain question answering (ODQA) due to its ability to use explicit knowledge. Although prior work has sought to increase the knowledge coverage by incorporating structured knowledge beyond text, accessing heterogeneous knowledge sources through a unified interface remains an open question. While data-to-text generation has the potential to serve as a universal interface for data and text, its feasibility for downstream tasks remains largely unknown. In this work, we bridge this gap and use the data-to-text method as a means for encoding structured knowledge for ODQA. Specifically, we propose a verbalizer-retriever-reader framework for ODQA over data and text where verbalized tables from Wikipedia and graphs from Wikidata are used as augmented knowledge sources. We show that our Unified Data and Text QA, UDT-QA, can effectively benefit from the expanded knowledge index, leading to large gains over text-only baselines. Notably, our approach sets the single-model state-of-the-art on Natural Questions. Furthermore, our analyses indicate that verbalized knowledge is preferred for answer reasoning for both adapted and hot-swap settings.

cs.CL↗

arXiv2022

A Survey of Knowledge-Intensive NLP with Pre-Trained Language Models

With the increasing of model capacity brought by pre-trained language models, there emerges boosting needs for more knowledgeable natural language processing (NLP) models with advanced functionalities including providing and making flexible use of encyclopedic and commonsense knowledge. The mere pre-trained language models, however, lack the capacity of handling such knowledge-intensive NLP tasks alone. To address this challenge, large numbers of pre-trained language models augmented with external knowledge sources are proposed and in rapid development. In this paper, we aim to summarize the current progress of pre-trained language model-based knowledge-enhanced models (PLMKEs) by dissecting their three vital elements: knowledge sources, knowledge-intensive NLP tasks, and knowledge fusion methods. Finally, we present the challenges of PLMKEs based on the discussion regarding the three elements and attempt to provide NLP practitioners with potential directions for further research.

cs.CL↗

arXiv2022

Keypoints-Based Deep Feature Fusion for Cooperative Vehicle Detection of Autonomous Driving

Sharing collective perception messages (CPM) between vehicles is investigated to decrease occlusions so as to improve the perception accuracy and safety of autonomous driving. However, highly accurate data sharing and low communication overhead is a big challenge for collective perception, especially when real-time communication is required among connected and automated vehicles. In this paper, we propose an efficient and effective keypoints-based deep feature fusion framework built on the 3D object detector PV-RCNN, called Fusion PV-RCNN (FPV-RCNN for short), for collective perception. We introduce a high-performance bounding box proposal matching module and a keypoints selection strategy to compress the CPM size and solve the multi-vehicle data fusion problem. Besides, we also propose an effective localization error correction module based on the maximum consensus principle to increase the robustness of the data fusion. Compared to a bird's-eye view (BEV) keypoints feature fusion, FPV-RCNN achieves improved detection accuracy by about 9% at a high evaluation criterion (IoU 0.7) on the synthetic dataset COMAP dedicated to collective perception. In addition, its performance is comparable to two raw data fusion baselines that have no data loss in sharing. Moreover, our method also significantly decreases the CPM size to less than 0.3 KB, and is thus about 50 times smaller than the BEV feature map sharing used in previous works. Even with further decreased CPM feature channels, i.e., from 128 to 32, the detection performance does not show apparent drops. The code of our method is available at https://github.com/YuanYunshuang/FPV_RCNN.

cs.CV↗

arXiv2022

Leopard: Towards High Throughput-Preserving BFT for Large-scale Systems

With the emergence of large-scale decentralized applications, a scalable and efficient Byzantine Fault Tolerant (BFT) protocol of hundreds of replicas is desirable. Although the throughput of existing leader-based BFT protocols has reached a high level of $10^5$ requests per second for a small scale of replicas, it drops significantly when the number of replicas increases, which leads to a lack of practicality. This paper focuses on the scalability of BFT protocols and identifies a major bottleneck to leader-based BFT protocols due to the excessive workload of the leader at large scales. A new metric of scaling factor is defined to capture whether a BFT protocol will get stuck when it scales out, which can be used to measure the performance of efficiency and scalability of BFT protocols. We propose "Leopard", the first leader-based BFT protocol that scales to multiple hundreds of replicas, and more importantly, preserves a high efficiency. We remove the bottleneck by introducing a technique of achieving a constant scaling factor, which takes full advantage of the idle resource and adaptively balances the workload of the leader among all replicas. We implement Leopard and evaluate its performance compared to HotStuff, the state-of-the-art BFT protocol. We run extensive experiments on the two systems with up to 600 replicas. The results show that Leopard achieves significant performance improvements both on throughput and scalability. In particular, the throughput of Leopard remains at a high level of $10^5$ when the system scales out to 600 replicas. It achieves a $5\times$ throughput over HotStuff when the scale is 300 (which is already the largest scale we can see the progress of the latter in our experiments), and the gap becomes wider as the number of replicas further increases.

cs.DC↗

arXiv2021

Fine-Tuning Large Neural Language Models for Biomedical Natural Language Processing

Motivation: A perennial challenge for biomedical researchers and clinical practitioners is to stay abreast with the rapid growth of publications and medical notes. Natural language processing (NLP) has emerged as a promising direction for taming information overload. In particular, large neural language models facilitate transfer learning by pretraining on unlabeled text, as exemplified by the successes of BERT models in various NLP applications. However, fine-tuning such models for an end task remains challenging, especially with small labeled datasets, which are common in biomedical NLP. Results: We conduct a systematic study on fine-tuning stability in biomedical NLP. We show that finetuning performance may be sensitive to pretraining settings, especially in low-resource domains. Large models have potential to attain better performance, but increasing model size also exacerbates finetuning instability. We thus conduct a comprehensive exploration of techniques for addressing fine-tuning instability. We show that these techniques can substantially improve fine-tuning performance for lowresource biomedical NLP applications. Specifically, freezing lower layers is helpful for standard BERT-BASE models, while layerwise decay is more effective for BERT-LARGE and ELECTRA models. For low-resource text similarity tasks such as BIOSSES, reinitializing the top layer is the optimal strategy. Overall, domainspecific vocabulary and pretraining facilitate more robust models for fine-tuning. Based on these findings, we establish new state of the art on a wide range of biomedical NLP applications. Availability and implementation: To facilitate progress in biomedical NLP, we release our state-of-the-art pretrained and fine-tuned models: https://aka.ms/BLURB.

cs.CL↗

arXiv2021

CLUES: Few-Shot Learning Evaluation in Natural Language Understanding

Most recent progress in natural language understanding (NLU) has been driven, in part, by benchmarks such as GLUE, SuperGLUE, SQuAD, etc. In fact, many NLU models have now matched or exceeded "human-level" performance on many tasks in these benchmarks. Most of these benchmarks, however, give models access to relatively large amounts of labeled data for training. As such, the models are provided far more data than required by humans to achieve strong performance. That has motivated a line of work that focuses on improving few-shot learning performance of NLU models. However, there is a lack of standardized evaluation benchmarks for few-shot NLU resulting in different experimental settings in different papers. To help accelerate this line of work, we introduce CLUES (Constrained Language Understanding Evaluation Standard), a benchmark for evaluating the few-shot learning capabilities of NLU models. We demonstrate that while recent models reach human performance when they have access to large amounts of labeled data, there is a huge gap in performance in the few-shot setting for most tasks. We also demonstrate differences between alternative model families and adaptation techniques in the few shot setting. Finally, we discuss several principles and choices in designing the experimental settings for evaluating the true few-shot learning performance and suggest a unified standardized approach to few-shot learning evaluation. We aim to encourage research on NLU models that can generalize to new tasks with a small number of examples. Code and data for CLUES are available at https://github.com/microsoft/CLUES.

cs.CL↗

arXiv2021

RMNet: Equivalently Removing Residual Connection from Networks

Although residual connection enables training very deep neural networks, it is not friendly for online inference due to its multi-branch topology. This encourages many researchers to work on designing DNNs without residual connections at inference. For example, RepVGG re-parameterizes multi-branch topology to a VGG-like (single-branch) model when deploying, showing great performance when the network is relatively shallow. However, RepVGG can not transform ResNet to VGG equivalently because re-parameterizing methods can only be applied to linear blocks and the non-linear layers (ReLU) have to be put outside of the residual connection which results in limited representation ability, especially for deeper networks. In this paper, we aim to remedy this problem and propose to remove the residual connection in a vanilla ResNet equivalently by a reserving and merging (RM) operation on ResBlock. Specifically, the RM operation allows input feature maps to pass through the block while reserving their information and merges all the information at the end of each block, which can remove residual connections without changing the original output. As a plug-in method, RM Operation basically has three advantages: 1) its implementation makes it naturally friendly for high ratio network pruning. 2) it helps break the depth limitation of RepVGG. 3) it leads to better accuracy-speed trade-off network (RMNet) compared to ResNet and RepVGG. We believe the ideology of RM Operation can inspire many insights on model design for the community in the future. Code is available at: https://github.com/fxmeng/RMNet.

cs.CV↗

arXiv2021

Disentangled Feature Representation for Few-shot Image Classification

Learning the generalizable feature representation is critical for few-shot image classification. While recent works exploited task-specific feature embedding using meta-tasks for few-shot learning, they are limited in many challenging tasks as being distracted by the excursive features such as the background, domain and style of the image samples. In this work, we propose a novel Disentangled Feature Representation framework, dubbed DFR, for few-shot learning applications. DFR can adaptively decouple the discriminative features that are modeled by the classification branch, from the class-irrelevant component of the variation branch. In general, most of the popular deep few-shot learning methods can be plugged in as the classification branch, thus DFR can boost their performance on various few-shot tasks. Furthermore, we propose a novel FS-DomainNet dataset based on DomainNet, for benchmarking the few-shot domain generalization tasks. We conducted extensive experiments to evaluate the proposed DFR on general and fine-grained few-shot classification, as well as few-shot domain generalization, using the corresponding four benchmarks, i.e., mini-ImageNet, tiered-ImageNet, CUB, as well as the proposed FS-DomainNet. Thanks to the effective feature disentangling, the DFR-based few-shot classifiers achieved the state-of-the-art results on all datasets.

cs.CV↗

arXiv2021

Measurements of $^{160}$Dy($p,γ$) at energies relevant for astrophysical $γ$ process

Rare information on photodisintegration reactions of nuclei with mass numbers $A \approx 160$ at astrophysical conditions impedes our understanding of the origin of $p$-nuclei. Experimental determination of the key ($p,γ$) cross sections has been playing an important role to verify nuclear reaction models and to provide rates of relevant ($γ,p$) reactions in $γ$-process. In this paper we report the first cross section measurements of $^{160}$Dy($p,γ$)$^{161}$Ho and $^{161}$Dy($p,n$)$^{161}$Ho in the beam energy range of 3.4 - 7.0 MeV, partially covering the Gamow window. Such determinations are possible by using two targets with various isotopic fractions. The cross section data can put a strong constraint on the nuclear level densities and gamma strength functions for $A \approx$ 160 in the Hauser-Feshbach statistical model. Furthermore, we find the best parameters for TALYS that reproduce the A $\thicksim$ 160 data available, $^{160}$Dy($p,γ$)$^{161}$Ho and $^{162}$Er($p,γ$)$^{163}$Tm, and recommend the constrained $^{161}$Ho($γ,p$)$^{160}$Dy reaction rates over a wide temperature range for $γ$-process network calculations. Although the determined $^{161}$Ho($γ$, p) stellar reaction rates at the temperature of 1 to 2 GK can differ by up to one order of magnitude from the NON-SMOKER predictions, it has a minor effect on the yields of $^{160}$Dy and accordingly the $p$-nuclei, $^{156,158}$Dy. A sensitivity study confirms that the cross section of $^{160}$Dy($p$, $γ$)$^{161}$Ho is measured precisely enough to predict yields of $p$-nuclei in the $γ$-process.

nucl-ex↗

arXiv2021

Autonomous Vehicles Drive into Shared Spaces: eHMI Design Concept Focusing on Vulnerable Road Users

In comparison to conventional traffic designs, shared spaces promote a more pleasant urban environment with slower motorized movement, smoother traffic, and less congestion. In the foreseeable future, shared spaces will be populated with a mixture of autonomous vehicles (AVs) and vulnerable road users (VRUs) like pedestrians and cyclists. However, a driver-less AV lacks a way to communicate with the VRUs when they have to reach an agreement of a negotiation, which brings new challenges to the safety and smoothness of the traffic. To find a feasible solution to integrating AVs seamlessly into shared-space traffic, we first identified the possible issues that the shared-space designs have not considered for the role of AVs. Then an online questionnaire was used to ask participants about how they would like a driver of the manually driving vehicle to communicate with VRUs in a shared space. We found that when the driver wanted to give some suggestions to the VRUs in a negotiation, participants thought that the communications via the driver's body behaviors were necessary. Besides, when the driver conveyed information about her/his intentions and cautions to the VRUs, participants selected different communication methods with respect to their transport modes (as a driver, pedestrian, or cyclist). These results suggest that novel eHMIs might be useful for AV-VRU communication when the original drivers are not present. Hence, a potential eHMI design concept was proposed for different VRUs to meet their various expectations. In the end, we further discussed the effects of the eHMIs on improving the sociality in shared spaces and the autonomous driving systems.

cs.HC↗

arXiv2021

NeurIPS 2020 EfficientQA Competition: Systems, Analyses and Lessons Learned

We review the EfficientQA competition from NeurIPS 2020. The competition focused on open-domain question answering (QA), where systems take natural language questions as input and return natural language answers. The aim of the competition was to build systems that can predict correct answers while also satisfying strict on-disk memory budgets. These memory budgets were designed to encourage contestants to explore the trade-off between storing retrieval corpora or the parameters of learned models. In this report, we describe the motivation and organization of the competition, review the best submissions, and analyze system predictions to inform a discussion of evaluation for open-domain QA.

cs.CL↗

arXiv2021

Domain-Specific Pretraining for Vertical Search: Case Study on Biomedical Literature

Information overload is a prevalent challenge in many high-value domains. A prominent case in point is the explosion of the biomedical literature on COVID-19, which swelled to hundreds of thousands of papers in a matter of months. In general, biomedical literature expands by two papers every minute, totalling over a million new papers every year. Search in the biomedical realm, and many other vertical domains is challenging due to the scarcity of direct supervision from click logs. Self-supervised learning has emerged as a promising direction to overcome the annotation bottleneck. We propose a general approach for vertical search based on domain-specific pretraining and present a case study for the biomedical domain. Despite being substantially simpler and not using any relevance labels for training or development, our method performs comparably or better than the best systems in the official TREC-COVID evaluation, a COVID-related biomedical search competition. Using distributed computing in modern cloud infrastructure, our system can scale to tens of millions of articles on PubMed and has been deployed as Microsoft Biomedical Search, a new search experience for biomedical literature: https://aka.ms/biomedsearch.

cs.IR↗

arXiv2021

Domain-Specific Language Model Pretraining for Biomedical Natural Language Processing

Pretraining large neural language models, such as BERT, has led to impressive gains on many natural language processing (NLP) tasks. However, most pretraining efforts focus on general domain corpora, such as newswire and Web. A prevailing assumption is that even domain-specific pretraining can benefit by starting from general-domain language models. In this paper, we challenge this assumption by showing that for domains with abundant unlabeled text, such as biomedicine, pretraining language models from scratch results in substantial gains over continual pretraining of general-domain language models. To facilitate this investigation, we compile a comprehensive biomedical NLP benchmark from publicly-available datasets. Our experiments show that domain-specific pretraining serves as a solid foundation for a wide range of biomedical NLP tasks, leading to new state-of-the-art results across the board. Further, in conducting a thorough evaluation of modeling choices, both for pretraining and task-specific fine-tuning, we discover that some common practices are unnecessary with BERT models, such as using complex tagging schemes in named entity recognition (NER). To help accelerate research in biomedical NLP, we have released our state-of-the-art pretrained and task-specific models for the community, and created a leaderboard featuring our BLURB benchmark (short for Biomedical Language Understanding & Reasoning Benchmark) at https://aka.ms/BLURB.

cs.CL↗

arXiv2021

Dialogue State Tracking with a Language Model using Schema-Driven Prompting

Task-oriented conversational systems often use dialogue state tracking to represent the user's intentions, which involves filling in values of pre-defined slots. Many approaches have been proposed, often using task-specific architectures with special-purpose classifiers. Recently, good results have been obtained using more general architectures based on pretrained language models. Here, we introduce a new variation of the language modeling approach that uses schema-driven prompting to provide task-aware history encoding that is used for both categorical and non-categorical slots. We further improve performance by augmenting the prompting with schema descriptions, a naturally occurring source of in-domain knowledge. Our purely generative system achieves state-of-the-art performance on MultiWOZ 2.2 and achieves competitive performance on two other benchmarks: MultiWOZ 2.1 and M2M. The data and code will be available at https://github.com/chiahsuan156/DST-as-Prompting.

cs.CL↗

arXiv2021

An Empirical Study and Analysis on Open-Set Semi-Supervised Learning

Pseudo-labeling (PL) and Data Augmentation-based Consistency Training (DACT) are two approaches widely used in Semi-Supervised Learning (SSL) methods. These methods exhibit great power in many machine learning tasks by utilizing unlabeled data for efficient training. But in a more realistic setting (termed as open-set SSL), where unlabeled dataset contains out-of-distribution (OOD) samples, the traditional SSL methods suffer severe performance degradation. Recent approaches mitigate the negative influence of OOD samples by filtering them out from the unlabeled data. However, it is not clear whether directly removing the OOD samples is the best choice. Furthermore, why PL and DACT could perform differently in open-set SSL remains a mystery. In this paper, we thoroughly analyze various SSL methods (PL and DACT) on open-set SSL and discuss pros and cons of these two approaches separately. Based on our analysis, we propose Style Disturbance to improve traditional SSL methods on open-set SSL and experimentally show our approach can achieve state-of-the-art results on various datasets by utilizing OOD samples properly. We believe our study can bring new insights for SSL research.

cs.CV↗

arXiv2021

Ab initio study of anisotropic mechanical and electronic properties of strained carbon-nitride nanosheet with interlayer bonding

Due to the noticeable structural similarity and being neighborhood in periodic table of group-IV and -V elemental monolayers, whether the combination of group-IV and -V elements could have stable nanosheet structures with optimistic properties has attracted great research interest. In this work, we performed first-principles simulations to investigate the elastic, vibrational and electronic properties of the carbon nitride (CN) nanosheet in the puckered honeycomb structure with covalent interlayer bonding. It has been demonstrated that the structural stability of CN nanosheet is essentially maintained by the strong interlayer \so\ bonding between adjacent carbon atoms in the opposite atomic layers. A negative Poisson's ratio in the out-of-plane direction under biaxial deformation, and the extreme in-plane stiffness of CN nanosheet, only slightly inferior to the monolayer graphene, are revealed. Moreover, the highly anisotropic mechanical and electronic response of CN nanosheet to tensile strain have been explored.

cond-mat.mtrl-sci↗