The task of Chinese Spelling Check (CSC) is aiming to detect and correct spelling errors that can be found in the text. While manually annotating a high-quality dataset is expensive and time-consuming, thus the scale of the training dataset is usually very small (e.g., SIGHAN15 only contains 2339 samples for training), therefore supervised-learning based models usually suffer the data sparsity limitation and over-fitting issue, especially in the era of big language models. In this paper, we are dedicated to investigating the \textbf{unsupervised} paradigm to address the CSC problem and we propose a framework named \textbf{uChecker} to conduct unsupervised spelling error detection and correction. Masked pretrained language models such as BERT are introduced as the backbone model considering their powerful language diagnosis capability. Benefiting from the various and flexible MASKing operations, we propose a Confusionset-guided masking strategy to fine-train the masked language model to further improve the performance of unsupervised detection and correction. Experimental results on standard datasets demonstrate the effectiveness of our proposed model uChecker in terms of character-level and sentence-level Accuracy, Precision, Recall, and F1-Measure on tasks of spelling error detection and correction respectively.

Research on Automatic Story Generation (ASG) relies heavily on human and automatic evaluation. However, there is no consensus on which human evaluation criteria to use, and no analysis of how well automatic criteria correlate with them. In this paper, we propose to re-evaluate ASG evaluation. We introduce a set of 6 orthogonal and comprehensive human criteria, carefully motivated by the social sciences literature. We also present HANNA, an annotated dataset of 1,056 stories produced by 10 different ASG systems. HANNA allows us to quantitatively evaluate the correlations of 72 automatic metrics with human criteria. Our analysis highlights the weaknesses of current metrics for ASG and allows us to formulate practical recommendations for ASG evaluation.

Graph neural network (GNN) pre-training methods have been proposed to enhance the power of GNNs. Specifically, a GNN is first pre-trained on a large-scale unlabeled graph and then fine-tuned on a separate small labeled graph for downstream applications, such as node classification. One popular pre-training method is to mask out a proportion of the edges, and a GNN is trained to recover them. However, such a generative method suffers from graph mismatch. That is, the masked graph inputted to the GNN deviates from the original graph. To alleviate this issue, we propose DiP-GNN (Discriminative Pre-training of Graph Neural Networks). Specifically, we train a generator to recover identities of the masked edges, and simultaneously, we train a discriminator to distinguish the generated edges from the original graph's edges. In our framework, the graph seen by the discriminator better matches the original graph because the generator can recover a proportion of the masked edges. Extensive experiments on large-scale homogeneous and heterogeneous graphs demonstrate the effectiveness of the proposed framework.

Two of the most fundamental challenges in Natural Language Understanding (NLU) at present are: (a) how to establish whether deep learning-based models score highly on NLU benchmarks for the 'right' reasons; and (b) to understand what those reasons would even be. We investigate the behavior of reading comprehension models with respect to two linguistic 'skills': coreference resolution and comparison. We propose a definition for the reasoning steps expected from a system that would be 'reading slowly', and compare that with the behavior of five models of the BERT family of various sizes, observed through saliency scores and counterfactual explanations. We find that for comparison (but not coreference) the systems based on larger encoders are more likely to rely on the 'right' information, but even they struggle with generalization, suggesting that they still learn specific lexical patterns rather than the general principles of comparison.

We introduce the task of entity-centric query refinement. Given an input query whose answer is a (potentially large) collection of entities, the task output is a small set of query refinements meant to assist the user in efficient domain exploration and entity discovery. We propose a method to create a training dataset for this task. For a given input query, we use an existing knowledge base taxonomy as a source of candidate query refinements, and choose a final set of refinements from among these candidates using a search procedure designed to partition the set of entities answering the input query. We demonstrate that our approach identifies refinement sets which human annotators judge to be interesting, comprehensive, and non-redundant. In addition, we find that a text generation model trained on our newly-constructed dataset is able to offer refinements for novel queries not covered by an existing taxonomy. Our code and data are available at https://github.

With the booming growth of advanced digital technologies, it has become possible for users as well as distributors of energy to obtain detailed and timely information about the electricity consumption of households. These technologies can also be used to forecast the household's electricity consumption (a.k.a. the load). In this paper, we investigate the use of Variational Mode Decomposition and deep learning techniques to improve the accuracy of the load forecasting problem. Although this problem has been studied in the literature, selecting an appropriate decomposition level and a deep learning technique providing better forecasting performance have garnered comparatively less attention. This study bridges this gap by studying the effect of six decomposition levels and five distinct deep learning networks. The raw load profiles are first decomposed into intrinsic mode functions using the Variational Mode Decomposition in order to mitigate their non-stationary aspect. Then, day, hour, and past electricity consumption data are fed as a three-dimensional input sequence to a four-level Wavelet Decomposition Network model. Finally, the forecast sequences related to the different intrinsic mode functions are combined to form the aggregate forecast sequence. The proposed method was assessed using load profiles of five Moroccan households from the Moroccan buildings' electricity consumption dataset (MORED) and was benchmarked against state-of-the-art time-series models and a baseline persistence model.

Document-level information extraction (IE) tasks have recently begun to be revisited in earnest using the end-to-end neural network techniques that have been successful on their sentence-level IE counterparts. Evaluation of the approaches, however, has been limited in a number of dimensions. In particular, the precision/recall/F1 scores typically reported provide few insights on the range of errors the models make. We build on the work of Kummerfeld and Klein (2013) to propose a transformation-based framework for automating error analysis in document-level event and (N-ary) relation extraction. We employ our framework to compare two state-of-the-art document-level template-filling approaches on datasets from three domains; and then, to gauge progress in IE since its inception 30 years ago, vs. four systems from the MUC-4 (1992) evaluation.

Neural Ordinary Differential Equations (Neural ODEs) are the continuous analog of Residual Neural Networks (ResNets). We investigate whether the discrete dynamics defined by a ResNet are close to the continuous one of a Neural ODE. We first quantify the distance between the ResNet's hidden state trajectory and the solution of its corresponding Neural ODE. Our bound is tight and, on the negative side, does not go to 0 with depth N if the residual functions are not smooth with depth. On the positive side, we show that this smoothness is preserved by gradient descent for a ResNet with linear residual functions and small enough initial loss. It ensures an implicit regularization towards a limit Neural ODE at rate 1 over N, uniformly with depth and optimization time. As a byproduct of our analysis, we consider the use of a memory-free discrete adjoint method to train a ResNet by recovering the activations on the fly through a backward pass of the network, and show that this method theoretically succeeds at large depth if the residual functions are Lipschitz with the input. We then show that Heun's method, a second order ODE integration scheme, allows for better gradient estimation with the adjoint method when the residual functions are smooth with depth. We experimentally validate that our adjoint method succeeds at large depth, and that Heun method needs fewer layers to succeed. We finally use the adjoint method successfully for fine-tuning very deep ResNets without memory consumption in the residual layers.

At ICRA 2022, Benjamin Rosman delivered a keynote presentation on an organization he co-founded called "Deep learning Indaba". Deep Learning Indaba is based in South Africa and their mission is to strengthen Artificial Intelligence and Machine Learning communities across Africa. They host yearly meetups in varying countries on the continent, as well as promote grass roots communities in each of the countries to run their own local events. An indaba is a Zulu word for a gathering or meeting. Such meetings are held throughout southern Africa, and serve several functions: to listen and share news of members of the community, to discuss common interests and issues facing the community, and to give advice and coach others.

Tehran, Iran – The United Kingdom's defence ministry has backed a Ukrainian claim that Ukraine's forces likely shot down an Iranian-made drone that was used by Russia in its offensive against its neighbouring country. In its latest military intelligence update on Wednesday, the ministry said it was "highly likely" that Russia has deployed unmanned aerial vehicles (UAV) made by Iran in the nearly seven-month war in Ukraine. "Russia is almost certainly increasingly sourcing weaponry from other heavily sanctioned states like Iran and North Korea as its own stocks dwindle," it said. The statement came a day after the Ukrainian military published several images and said it had likely shot down a drone near Kupiansk in Kharkiv that appeared to be an Iranian Shahed-136 model. The Iranian government has yet to comment on the claims, but its officials have previously denied supplying Russia with drones to be used in Ukraine, saying Iran would not assist either side in the war as it backed its resolution through dialogue. There are no known official specifications for the Shahed-136, but it is a so-called "suicide drone" that is capable of carrying a warhead over long distances.