The notion of word embedding plays a fundamental role in natural language processing (NLP). However, pre-training word embedding for very large-scale vocabulary is computationally challenging for most existing methods. In this work, we show that with merely a small fraction of contexts (Q-contexts)which are typical in the whole corpus (and their mutual information with words), one can construct high-quality word embedding with negligible errors. Mutual information between contexts and words can be encoded canonically as a sampling state, thus, Q-contexts can be fast constructed. Furthermore, we present an efficient and effective WEQ method, which is capable of extracting word embedding directly from these typical contexts. In practical scenarios, our algorithm runs 11$\sim$13 times faster than well-established methods. By comparing with well-known methods such as matrix factorization, word2vec, GloVeand fasttext, we demonstrate that our method achieves comparable performance on a variety of downstream NLP tasks, and in the meanwhile maintains run-time and resource advantages over all these baselines.

Most of the recent works on probing representations have focused on BERT, with the presumption that the findings might be similar to the other models. In this work, we extend the probing studies to two other models in the family, namely ELECTRA and XLNet, showing that variations in the pre-training objectives or architectural choices can result in different behaviors in encoding linguistic information in the representations. Most notably, we observe that ELECTRA tends to encode linguistic knowledge in the deeper layers, whereas XLNet instead concentrates that in the earlier layers. Also, the former model undergoes a slight change during fine-tuning, whereas the latter experiences significant adjustments. Moreover, we show that drawing conclusions based on the weight mixing evaluation strategy -- which is widely used in the context of layer-wise probing -- can be misleading given the norm disparity of the representations across different layers. Instead, we adopt an alternative information-theoretic probing with minimum description length, which has recently been proven to provide more reliable and informative results.

Artificial intelligence (AI) will smoothen the government operations and also accelerate the pace of developments of all the governments as AI's role increases and becomes more mainstream, say public and private executives. "It's going to be interesting how artificial intelligence will react on smoothing the governments challenges through adopting the behaviours and with creative model. The ultimate goal of AI is to increase the value of the work, cut the cost, and save time. Therefore, it will accelerate the pace of the developments in all governments," said Dr. Ebrahim Al Alkeem Al Zaabi, director of cybersecurity and artificial intelligence at Government of Abu Dhabi. A study by Oliver Wyman, a global management consulting firm, has estimated that the efficiencies generated by AI technology can support Middle Eastern government budgets by up to $7 billion (Dh25.7 billion) annually.

Geoscape Australia, a government-owned geospatial data company, has announced it has partnered with an Israeli artificial intelligence start-up to use machine vision and deep learning technology to enhance its 3D digital maps of Australia. The CEO of Geoscape Australia said that the partnership will advance what is known about every address across the country. Applying the Israeli AI start-up's patented AI technology to the highest quality aerial imagery will significantly evolve the current digital model of Australia. The company says more accurate digital models of Australia's urban environment will enable the data-driven foundation of Digital Twin applications that better reflect the real world. The up-to-date data will also improve the assessment of risk for insurers, allow architects to visualise new developments in the context of their surroundings, help noise modellers better understand what will be impacted by noise, and power modelling of energy use patterns in commercial and residential buildings.

Intrinsic evaluations of OIE systems are carried out either manually -- with human evaluators judging the correctness of extractions -- or automatically, on standardized benchmarks. The latter, while much more cost-effective, is less reliable, primarily because of the incompleteness of the existing OIE benchmarks: the ground truth extractions do not include all acceptable variants of the same fact, leading to unreliable assessment of models' performance. Moreover, the existing OIE benchmarks are available for English only. In this work, we introduce BenchIE: a benchmark and evaluation framework for comprehensive evaluation of OIE systems for English, Chinese and German. In contrast to existing OIE benchmarks, BenchIE takes into account informational equivalence of extractions: our gold standard consists of fact synsets, clusters in which we exhaustively list all surface forms of the same fact. We benchmark several state-of-the-art OIE systems using BenchIE and demonstrate that these systems are significantly less effective than indicated by existing OIE benchmarks. We make BenchIE (data and evaluation code) publicly available.

Commonsense is defined as the knowledge that is shared by everyone. However, certain types of commonsense knowledge are correlated with culture and geographic locations and they are only shared locally. For example, the scenarios of wedding ceremonies vary across regions due to different customs influenced by historical and religious factors. Such regional characteristics, however, are generally omitted in prior work. In this paper, we construct a Geo-Diverse Visual Commonsense Reasoning dataset (GD-VCR) to test vision-and-language models' ability to understand cultural and geo-location-specific commonsense. In particular, we study two state-of-the-art Vision-and-Language models, VisualBERT and ViLBERT trained on VCR, a standard multimodal commonsense benchmark with images primarily from Western regions. We then evaluate how well the trained models can generalize to answering the questions in GD-VCR. We find that the performance of both models for non-Western regions including East Asia, South Asia, and Africa is significantly lower than that for Western region. We analyze the reasons behind the performance disparity and find that the performance gap is larger on QA pairs that: 1) are concerned with culture-related scenarios, e.g., weddings, religious activities, and festivals; 2) require high-level geo-diverse commonsense reasoning rather than low-order perception and recognition. Dataset and code are released at https://github.com/WadeYin9712/GD-VCR.

Recent language models can generate interesting and grammatically correct text in story generation but often lack plot development and long-term coherence. This paper experiments with a latent vector planning approach based on a TD-VAE (Temporal Difference Variational Autoencoder), using the model for conditioning and reranking for text generation. The results demonstrate strong performance in automatic cloze and swapping evaluations. The human judgments show stories generated with TD-VAE reranking improve on a GPT-2 medium baseline and show comparable performance to a hierarchical LSTM reranking model. Conditioning on the latent vectors proves disappointing and deteriorates performance in human evaluation because it reduces the diversity of generation, and the models don't learn to progress the narrative. This highlights an important difference between technical task performance (e.g. cloze) and generating interesting stories.

Relevance in summarization is typically defined based on textual information alone, without incorporating insights about a particular decision. As a result, to support risk analysis of pancreatic cancer, summaries of medical notes may include irrelevant information such as a knee injury. We propose a novel problem, decision-focused summarization, where the goal is to summarize relevant information for a decision. We leverage a predictive model that makes the decision based on the full text to provide valuable insights on how a decision can be inferred from text. To build a summary, we then select representative sentences that lead to similar model decisions as using the full text while accounting for textual non-redundancy. To evaluate our method (DecSum), we build a testbed where the task is to summarize the first ten reviews of a restaurant in support of predicting its future rating on Yelp. DecSum substantially outperforms text-only summarization methods and model-based explanation methods in decision faithfulness and representativeness. We further demonstrate that DecSum is the only method that enables humans to outperform random chance in predicting which restaurant will be better rated in the future.

Artificial Intelligence (AI) is rapidly becoming integrated into military Command and Control (C2) systems as a strategic priority for many defence forces. The successful implementation of AI is promising to herald a significant leap in C2 agility through automation. However, realistic expectations need to be set on what AI can achieve in the foreseeable future. This paper will argue that AI could lead to a fragility trap, whereby the delegation of C2 functions to an AI could increase the fragility of C2, resulting in catastrophic strategic failures. This calls for a new framework for AI in C2 to avoid this trap. We will argue that antifragility along with agility should form the core design principles for AI-enabled C2 systems. This duality is termed Agile, Antifragile, AI-Enabled Command and Control (A3IC2). An A3IC2 system continuously improves its capacity to perform in the face of shocks and surprises through overcompensation from feedback during the C2 decision-making cycle. An A3IC2 system will not only be able to survive within a complex operational environment, it will also thrive, benefiting from the inevitable shocks and volatility of war.

Simultaneous Localization and Mapping (SLAM) techniques play a key role towards long-term autonomy of mobile robots due to the ability to correct localization errors and produce consistent maps of an environment over time. Contrarily to urban or man-made environments, where the presence of unique objects and structures offer unique cues for localization, the appearance of unstructured natural environments is often ambiguous and self-similar, hindering the performances of loop closure detection. In this paper, we present an approach to improve the robustness of place recognition in the context of a submap-based stereo SLAM based on Gaussian Process Gradient Maps (GPGMaps). GPGMaps embed a continuous representation of the gradients of the local terrain elevation by means of Gaussian Process regression and Structured Kernel Interpolation, given solely noisy elevation measurements. We leverage the image-like structure of GPGMaps to detect loop closures using traditional visual features and Bag of Words. GPGMap matching is performed as an SE(2) alignment to establish loop closure constraints within a pose graph. We evaluate the proposed pipeline on a variety of datasets recorded on Mt. Etna, Sicily and in the Morocco desert, respectively Moon- and Mars-like environments, and we compare the localization performances with state-of-the-art approaches for visual SLAM and visual loop closure detection.