Entity linking aims to link ambiguous mentions to their corresponding entities in a knowledge base, which is significant and fundamental for various downstream applications, e.g., knowledge base completion, question answering, and information extraction. While great efforts have been devoted to this task, most of these studies follow the assumption that large-scale labeled data is available. However, when the labeled data is insufficient for specific domains due to labor-intensive annotation work, the performance of existing algorithms will suffer an intolerable decline. In this paper, we endeavor to solve the problem of few-shot entity linking, which only requires a minimal amount of in-domain labeled data and is more practical in real situations. Specifically, we firstly propose a novel weak supervision strategy to generate non-trivial synthetic entity-mention pairs based on mention rewriting. Since the quality of the synthetic data has a critical impact on effective model training, we further design a meta-learning mechanism to assign different weights to each synthetic entity-mention pair automatically. Through this way, we can profoundly exploit rich and precious semantic information to derive a well-trained entity linking model under the few-shot setting. The experiments on real-world datasets show that the proposed method can extensively improve the state-of-the-art few-shot entity linking model and achieve impressive performance when only a small amount of labeled data is available. Moreover, we also demonstrate the outstanding ability of the model's transferability.

AWS and Udacity are collaborating to educate developers of all skill levels on machine learning concepts. We invite learners globally 18 years of age or older who are interested in expanding their machine learning skills and expertise to enroll in the AWS Machine Learning Engineer Scholarship Program. The goal for this program is to up-level machine learning skills to all, and to cultivate the next generation of ML leaders across the world, with a focus on underrepresented groups. Through its We Power Tech Program, AWS collaborates with professional organizations that are leading initiatives to increase the diversity and talent in technical roles, including organizations like Girls In Tech and the National Society of Black Engineers. The scholarship is open to all for registration starting June 21, 2022.

Today we are witnessing a collision of three areas – data, computing and education – which has far-reaching consequences and raises fundamental questions about the very nature of education: what to teach and how to teach. The use of artificial intelligence allows you to redistribute the resources of the teacher. In the traditional model of education, there is a serious problem of uneven distribution of teachers, which also leads to uneven and unequal education. By investing in AI education, teachers around the world can turn their own resources into curriculum. Everywhere in the world, children use the same educational resources.

The good news however is that since Artificial Intelligence technology is a simulation, it can be controlled and modified to even be better than human beings. Astro Teller, the famous British computer scientist once said – "Building intelligent machines can teach us about our minds – about who we are – and those lessons will make our world a better place. To win that knowledge, though, our species will have to trade in another piece of its vanity." Take for example, the case of sexbots. They are often made to be/look better than the average man/woman, by amplifying certain aspects about them.

We study the problem of online learning in adversarial bandit problems under a partial observability model called off-policy feedback. In this sequential decision making problem, the learner cannot directly observe its rewards, but instead sees the ones obtained by another unknown policy run in parallel (behavior policy). Instead of a standard exploration-exploitation dilemma, the learner has to face another challenge in this setting: due to limited observations outside of their control, the learner may not be able to estimate the value of each policy equally well. To address this issue, we propose a set of algorithms that guarantee regret bounds that scale with a natural notion of mismatch between any comparator policy and the behavior policy, achieving improved performance against comparators that are well-covered by the observations. We also provide an extension to the setting of adversarial linear contextual bandits, and verify the theoretical guarantees via a set of experiments. Our key algorithmic idea is adapting the notion of pessimistic reward estimators that has been recently popular in the context of off-policy reinforcement learning.

Admittedly, Graph Convolution Network (GCN) has achieved excellent results on graph datasets such as social networks, citation networks, etc. However, softmax used as the decision layer in these frameworks is generally optimized with thousands of iterations via gradient descent. Furthermore, due to ignoring the inner distribution of the graph nodes, the decision layer might lead to an unsatisfactory performance in semi-supervised learning with less label support. To address the referred issues, we propose a novel graph deep model with a non-gradient decision layer for graph mining. Firstly, manifold learning is unified with label local-structure preservation to capture the topological information of the nodes. Moreover, owing to the non-gradient property, closed-form solutions is achieved to be employed as the decision layer for GCN. Particularly, a joint optimization method is designed for this graph model, which extremely accelerates the convergence of the model. Finally, extensive experiments show that the proposed model has achieved state-of-the-art performance compared to the current models.

We introduce a new distributed policy gradient algorithm and show that it outperforms existing reward-aware training procedures such as REINFORCE, minimum risk training (MRT) and proximal policy optimization (PPO) in terms of training stability and generalization performance when optimizing machine translation models. Our algorithm, which we call MAD (on account of using the mean absolute deviation in the importance weighting calculation), has distributed data generators sampling multiple candidates per source sentence on worker nodes, while a central learner updates the policy. MAD depends crucially on two variance reduction strategies: (1) a conditional reward normalization method that ensures each source sentence has both positive and negative reward translation examples and (2) a new robust importance weighting scheme that acts as a conditional entropy regularizer. Experiments on a variety of translation tasks show that policies learned using the MAD algorithm perform very well when using both greedy decoding and beam search, and that the learned policies are sensitive to the specific reward used during training.

Adaptive learning aims to stimulate and meet the needs of individual learners, which requires sophisticated system-level coordination of diverse tasks, including modeling learning resources, estimating student states, and making personalized recommendations. Existing deep learning methods have achieved great success over statistical models; however, they still lack generalization for diverse tasks and suffer from insufficient capacity since they are composed of highly-coupled task-specific architectures and rely on small-scale, coarse-grained recommendation scenarios. To realize the idea of general adaptive systems proposed in pedagogical theory, with the emerging pre-training techniques in NLP, we try to conduct a practical exploration on applying pre-training to adaptive learning, to propose a unified framework based on data observation and learning style analysis, properly leveraging heterogeneous learning elements. Through a series of downstream tasks of Learning Recommendation, Learning Resource Evaluation, Knowledge Tracing, and Dropout Prediction, we find that course structures, text, and knowledge are helpful for modeling and inherently coherent to student non-sequential learning behaviors and that indirectly relevant information included in the pre-training foundation can be shared across downstream tasks to facilitate effectiveness. We finally build a simplified systematic application of adaptive learning and reflect on the insights brought back to pedagogy. The source code and dataset will be released.

Pretrained language models (PTLMs) are typically learned over a large, static corpus and further fine-tuned for various downstream tasks. However, when deployed in the real world, a PTLM-based model must deal with data distributions that deviate from what the PTLM was initially trained on. In this paper, we study a lifelong language model pretraining challenge where a PTLM is continually updated so as to adapt to emerging data. Over a domain-incremental research paper stream and a chronologically-ordered tweet stream, we incrementally pretrain a PTLM with different continual learning algorithms, and keep track of the downstream task performance (after fine-tuning). We evaluate PTLM's ability to adapt to new corpora while retaining learned knowledge in earlier corpora. Our experiments show distillation-based approaches to be most effective in retaining downstream performance in earlier domains. The algorithms also improve knowledge transfer, allowing models to achieve better downstream performance over the latest data, and improve temporal generalization when distribution gaps exist between training and evaluation because of time. We believe our problem formulation, methods, and analysis will inspire future studies towards continual pretraining of language models.

The most difficult task in machine learning is to interpret trained shallow neural networks. Deep neural networks (DNNs) provide impressive results on a larger number of tasks, but it is generally still unclear how decisions are made by such a trained deep neural network. Providing feature importance is the most important and popular interpretation technique used in shallow and deep neural networks. In this paper, we develop an algorithm extending the idea of Garson Algorithm to explain Deep Belief Network based Auto-encoder (DBNA). It is used to determine the contribution of each input feature in the DBN. It can be used for any kind of neural network with many hidden layers. The effectiveness of this method is tested on both classification and regression datasets taken from literature. Important features identified by this method are compared against those obtained by Wald chi square (\c{hi}2). For 2 out of 4 classification datasets and 2 out of 5 regression datasets, our proposed methodology resulted in the identification of better-quality features leading to statistically more significant results vis-\`a-vis Wald \c{hi}2.