Incorporating factual knowledge into pre-trained language models (PLM) such as BERT is an emerging trend in recent NLP studies. However, most of the existing methods combine the external knowledge integration module with a modified pre-training loss and re-implement the pre-training process on the large-scale corpus. Re-pretraining these models is usually resource-consuming, and difficult to adapt to another domain with a different knowledge graph (KG). Besides, those works either cannot embed knowledge context dynamically according to textual context or struggle with the knowledge ambiguity issue. In this paper, we propose a novel knowledge-aware language model framework based on fine-tuning process, which equips PLM with a unified knowledge-enhanced text graph that contains both text and multi-relational sub-graphs extracted from KG. We design a hierarchical relational-graph-based message passing mechanism, which can allow the representations of injected KG and text to mutually update each other and can dynamically select ambiguous mentioned entities that share the same text. Our empirical results show that our model can efficiently incorporate world knowledge from KGs into existing language models such as BERT, and achieve significant improvement on the machine reading comprehension (MRC) task compared with other knowledge-enhanced models.

With the prevalence of social media, there has recently been a proliferation of recommenders that shift their focus from individual modeling to group recommendation. Since the group preference is a mixture of various predilections from group members, the fundamental challenge of group recommendation is to model the correlations among members. Existing methods mostly adopt heuristic or attention-based preference aggregation strategies to synthesize group preferences. However, these models mainly focus on the pairwise connections of users and ignore the complex high-order interactions within and beyond groups. Besides, group recommendation suffers seriously from the problem of data sparsity due to severely sparse group-item interactions. In this paper, we propose a self-supervised hypergraph learning framework for group recommendation to achieve two goals: (1) capturing the intra- and inter-group interactions among users; (2) alleviating the data sparsity issue with the raw data itself. Technically, for (1), a hierarchical hypergraph convolutional network based on the user- and group-level hypergraphs is developed to model the complex tuplewise correlations among users within and beyond groups. For (2), we design a double-scale node dropout strategy to create self-supervision signals that can regularize user representations with different granularities against the sparsity issue. The experimental analysis on multiple benchmark datasets demonstrates the superiority of the proposed model and also elucidates the rationality of the hypergraph modeling and the double-scale self-supervision.

Temporal knowledge graph (TKG) reasoning is a crucial task that has gained increasing research interest in recent years. Most existing methods focus on reasoning at past timestamps to complete the missing facts, and there are only a few works of reasoning on known TKGs to forecast future facts. Compared with the completion task, the forecasting task is more difficult that faces two main challenges: (1) how to effectively model the time information to handle future timestamps? (2) how to make inductive inference to handle previously unseen entities that emerge over time? To address these challenges, we propose the first reinforcement learning method for forecasting. Specifically, the agent travels on historical knowledge graph snapshots to search for the answer. Our method defines a relative time encoding function to capture the timespan information, and we design a novel time-shaped reward based on Dirichlet distribution to guide the model learning. Furthermore, we propose a novel representation method for unseen entities to improve the inductive inference ability of the model. We evaluate our method for this link prediction task at future timestamps. Extensive experiments on four benchmark datasets demonstrate substantial performance improvement meanwhile with higher explainability, less calculation, and fewer parameters when compared with existing state-of-the-art methods.

Neural conversation models have shown great potentials towards generating fluent and informative responses by introducing external background knowledge. Nevertheless, it is laborious to construct such knowledge-grounded dialogues, and existing models usually perform poorly when transfer to new domains with limited training samples. Therefore, building a knowledge-grounded dialogue system under the low-resource setting is a still crucial issue. In this paper, we propose a novel three-stage learning framework based on weakly supervised learning which benefits from large scale ungrounded dialogues and unstructured knowledge base. To better cooperate with this framework, we devise a variant of Transformer with decoupled decoder which facilitates the disentangled learning of response generation and knowledge incorporation. Evaluation results on two benchmarks indicate that our approach can outperform other state-of-the-art methods with less training data, and even in zero-resource scenario, our approach still performs well.

Tables provide valuable knowledge that can be used to verify textual statements. While a number of works have considered table-based fact verification, direct alignments of tabular data with tokens in textual statements are rarely available. Moreover, training a generalized fact verification model requires abundant labeled training data. In this paper, we propose a novel system to address these problems. Inspired by counterfactual causality, our system identifies token-level salience in the statement with probing-based salience estimation. Salience estimation allows enhanced learning of fact verification from two perspectives. From one perspective, our system conducts masked salient token prediction to enhance the model for alignment and reasoning between the table and the statement. From the other perspective, our system applies salience-aware data augmentation to generate a more diverse set of training instances by replacing non-salient terms. Experimental results on TabFact show the effective improvement by the proposed salience-aware learning techniques, leading to the new SOTA performance on the benchmark. Our code is publicly available at https://github.com/luka-group/Salience-aware-Learning .

Multimodal sentiment analysis is a trending area of research, and the multimodal fusion is one of its most active topic. Acknowledging humans communicate through a variety of channels (i.e visual, acoustic, linguistic), multimodal systems aim at integrating different unimodal representations into a synthetic one. So far, a consequent effort has been made on developing complex architectures allowing the fusion of these modalities. However, such systems are mainly trained by minimising simple losses such as $L_1$ or cross-entropy. In this work, we investigate unexplored penalties and propose a set of new objectives that measure the dependency between modalities. We demonstrate that our new penalties lead to a consistent improvement (up to $4.3$ on accuracy) across a large variety of state-of-the-art models on two well-known sentiment analysis datasets: \texttt{CMU-MOSI} and \texttt{CMU-MOSEI}. Our method not only achieves a new SOTA on both datasets but also produces representations that are more robust to modality drops. Finally, a by-product of our methods includes a statistical network which can be used to interpret the high dimensional representations learnt by the model.

We propose a score-based DAG structure learning method for time-series data that captures linear, nonlinear, lagged and instantaneous relations among variables while ensuring acyclicity throughout the entire graph. The proposed method extends nonparametric NOTEARS, a recent continuous optimization approach for learning nonparametric instantaneous DAGs. The proposed method is faster than constraint-based methods using nonlinear conditional independence tests. We also promote the use of optimization constraints to incorporate prior knowledge into the structure learning process. A broad set of experiments with simulated data demonstrates that the proposed method discovers better DAG structures than several recent comparison methods. We also evaluate the proposed method on complex real-world data acquired from NHL ice hockey games containing a mixture of continuous and discrete variables. The code is available at https://github.com/xiangyu-sun-789/NTS-NOTEARS/.

When Covid-19 hit Spain last spring, the country quickly hit breaking point. In Madrid, doctors described an "avalanche" of patients as they practised "combat medicine" and emergency triage in intensive care units that were operating on a war-like footing. The first Covid-19 death was recorded on March 1. A month later, just under a thousand people were dying each day. Ambulances choked hospital approach roads and ice rinks were transformed into morgues.

Note that there is also a repository of this article with all the resources clearly identified for you to follow in order as well. In my opinion, the best way to start learning anything is with short YouTube video introductions. This field is no exception. There are thousands of amazing videos and playlists that teach important machine learning concepts for free on this platform, and you should definitely take advantage of them. Here, I list a few of the best videos I found that will give you a great first introduction to the terms you need to know to get started in the field.

When soldiers look through the sights of their assault rifles with the Elbit System's new artificial intelligence data platform, their view is transformed to resemble a first-person shooter video game. Shooters push buttons on a grip to toggle among layers of information about their surroundings, including motion detection, range, ammunition levels and more data that's just a click away. ARCAS, which the Israel-based company is featuring at the DSEI conference in London, incorporates a microcomputer in the weapon to process data and provide a graphical user interface to display the information in the rifle's electro-optical sight and through an optional helmet-mounted eyepiece. The demo used ARCAS systems mounted on M-4s, with testers shooting at stationary targets. The use of ideas from the gaming world is clear when putting the sight up to the eye.