At LinkedIn, we want to create economic opportunity for everyone in the global workforce. A critical aspect of this goal is matching jobs with qualified applicants. To improve hiring efficiency and reduce the need to manually screening each applicant, we develop a new product where recruiters can ask screening questions online so that they can filter qualified candidates easily. To add screening questions to all $20$M active jobs at LinkedIn, we propose a new task that aims to automatically generate screening questions for a given job posting. To solve the task of generating screening questions, we develop a two-stage deep learning model called Job2Questions, where we apply a deep learning model to detect intent from the text description, and then rank the detected intents by their importance based on other contextual features. Since this is a new product with no historical data, we employ deep transfer learning to train complex models with limited training data. We launched the screening question product and our AI models to LinkedIn users and observed significant impact in the job marketplace. During our online A/B test, we observed $+53.10\%$ screening question suggestion acceptance rate, $+22.17\%$ job coverage, $+190\%$ recruiter-applicant interaction, and $+11$ Net Promoter Score. In sum, the deployed Job2Questions model helps recruiters to find qualified applicants and job seekers to find jobs they are qualified for.

In the era of Industry 4.0, the focus is on the minimization of human element and maximizing the automation in almost all the industrial and manufacturing establishments. These establishments contain numerous processing systems, which can execute a number of tasks, in parallel with minimum number of human beings. This parallel execution of tasks is done in accordance to a scheduling policy. However, the minimization of human element beyond a certain point is difficult. In fact, the expertise and experience of a group of humans, called the experts, becomes imminent to design a fruitful scheduling policy. The aim of the scheduling policy is to achieve the optimal value of an objective, like production time, cost, etc. In real-life situations, there are more often than not, multiple objectives in any parallel processing scenario. Furthermore, the experts generally provide their opinions, about various scheduling criteria (pertaining to the scheduling policies) in linguistic terms or words. Word semantics are best modeled using fuzzy sets (FSs). Thus, all these factors have motivated us to model the parallel processing scenario as a multi-objective linguistic optimization problem (MOLOP) and use the novel perceptual reasoning (PR) based methodology for solving it. We have also compared the results of the PR based solution methodology with those obtained from the 2-tuple based solution methodology. PR based solution methodology offers three main advantages viz., it generates unique recommendations, here the linguistic recommendations match a codebook word, and also the word model comes before the word. 2-tuple based solution methodology fails to give all these advantages. Thus, we feel that our work is novel and will provide directions for the future research.

In peer selection agents must choose a subset of themselves for an award or a prize. As agents are self-interested, we want to design algorithms that are impartial, so that an individual agent cannot affect their own chance of being selected. This problem has broad application in resource allocation and mechanism design and has received substantial attention in the artificial intelligence literature. Here, we present a novel algorithm for impartial peer selection, PeerNomination, and provide a theoretical analysis of its accuracy. Our algorithm possesses various desirable features. In particular, it does not require an explicit partitioning of the agents, as previous algorithms in the literature. We show empirically that it achieves higher accuracy than the exiting algorithms over several metrics.

Decision making in real-life scenarios may often be modeled as an optimization problem. It requires the consideration of various attributes like human preferences and thinking, which constrain achieving the optimal value of the problem objectives. The value of the objectives may be maximized or minimized, depending on the situation. Numerous times, the values of these problem parameters are in linguistic form, as human beings naturally understand and express themselves using words. These problems are therefore termed as linguistic optimization problems (LOPs), and are of two types, namely single objective linguistic optimization problems (SOLOPs) and multi-objective linguistic optimization problems (MOLOPs). In these LOPs, the value of the objective function(s) may not be known at all points of the decision space, and therefore, the objective function(s) as well as problem constraints are linked by the if-then rules. Tsukamoto inference method has been used to solve these LOPs; however, it suffers from drawbacks. As, the use of linguistic information inevitably calls for the utilization of computing with words (CWW), and therefore, 2-tuple linguistic model based solution methodologies were proposed for LOPs. However, we found that 2-tuple linguistic model based solution methodologies represent the semantics of the linguistic information using a combination of type-1 fuzzy sets and ordinal term sets. As, the semantics of linguistic information are best modeled using the interval type-2 fuzzy sets, hence we propose solution methodologies for LOPs based on CWW approach of perceptual computing, in this paper. The perceptual computing based solution methodologies use a novel design of CWW engine, called the perceptual reasoning (PR). PR in the current form is suitable for solving SOLOPs and, hence, we have also extended it to the MOLOPs.

Computing with words (CWW) has emerged as a powerful tool for processing the linguistic information, especially the one generated by human beings. Various CWW approaches have emerged since the inception of CWW, such as perceptual computing, extension principle based CWW approach, symbolic method based CWW approach, and 2-tuple based CWW approach. Furthermore, perceptual computing can use interval approach (IA), enhanced interval approach (EIA), or Hao-Mendel approach (HMA), for data processing. There have been numerous works in which HMA was shown to be better at word modelling than EIA, and EIA better than IA. But, a deeper study of these works reveals that HMA captures lesser fuzziness than the EIA or IA. Thus, we feel that EIA is more suited for word modelling in multi-person systems and HMA for single-person systems (as EIA is an improvement over IA). Furthermore, another set of works, compared the performances perceptual computing to the other above said CWW approaches. In all these works, perceptual computing was shown to be better than other CWW approaches. However, none of the works tried to investigate the reason behind this observed better performance of perceptual computing. Also, no comparison has been performed for scenarios where the inputs are differentially weighted. Thus, the aim of this work is to empirically establish that EIA is suitable for multi-person systems and HMA for single-person systems. Another dimension of this work is also to empirically prove that perceptual computing gives better performance than other CWW approaches based on extension principle, symbolic method and 2-tuple especially in scenarios where inputs are differentially weighted.

In this white paper we provide a vision for 6G Edge Intelligence. Moving towards 5G and beyond the future 6G networks, intelligent solutions utilizing data-driven machine learning and artificial intelligence become crucial for several real-world applications including but not limited to, more efficient manufacturing, novel personal smart device environments and experiences, urban computing and autonomous traffic settings. We present edge computing along with other 6G enablers as a key component to establish the future 2030 intelligent Internet technologies as shown in this series of 6G White Papers. In this white paper, we focus in the domains of edge computing infrastructure and platforms, data and edge network management, software development for edge, and real-time and distributed training of ML/AI algorithms, along with security, privacy, pricing, and end-user aspects. We discuss the key enablers and challenges and identify the key research questions for the development of the Intelligent Edge services. As a main outcome of this white paper, we envision a transition from Internet of Things to Intelligent Internet of Intelligent Things and provide a roadmap for development of 6G Intelligent Edge.

Knowledge graph embeddings are now a widely adopted approach to knowledge representation in which entities and relationships are embedded in vector spaces. In this chapter, we introduce the reader to the concept of knowledge graph embeddings by explaining what they are, how they can be generated and how they can be evaluated. We summarize the state-of-the-art in this field by describing the approaches that have been introduced to represent knowledge in the vector space. In relation to knowledge representation, we consider the problem of explainability, and discuss models and methods for explaining predictions obtained via knowledge graph embeddings.

Transferring learning-based models to the real world remains one of the hardest problems in model-free control theory. Due to the cost of data collection on a real robot and the limited sample efficiency of Deep Reinforcement Learning algorithms, models are usually trained in a simulator which theoretically provides an infinite amount of data. Despite offering unbounded trial and error runs, the reality gap between simulation and the physical world brings little guarantee about the policy behavior in real operation. Depending on the problem, expensive real fine-tuning and/or a complex domain randomization strategy may be required to produce a relevant policy. In this paper, a Soft-Actor Critic (SAC) training strategy using incremental environment complexity is proposed to drastically reduce the need for additional training in the real world. The application addressed is depth-based mapless navigation, where a mobile robot should reach a given waypoint in a cluttered environment with no prior mapping information. Experimental results in simulated and real environments are presented to assess quantitatively the efficiency of the proposed approach, which demonstrated a success rate twice higher than a naive strategy.

Argumentation is a type of discourse where speakers try to persuade their audience about the reasonableness of a claim by presenting supportive arguments. Most work in argument mining has focused on modeling arguments in monologues. We propose a computational model for argument mining in online persuasive discussion forums that brings together the micro-level (argument as product) and macro-level (argument as process) models of argumentation. Fundamentally, this approach relies on identifying relations between components of arguments in a discussion thread. Our approach for relation prediction uses contextual information in terms of fine-tuning a pre-trained language model and leveraging discourse relations based on Rhetorical Structure Theory. We additionally propose a candidate selection method to automatically predict what parts of one's argument will be targeted by other participants in the discussion. Our models obtain significant improvements compared to recent state-of-the-art approaches using pointer networks and a pre-trained language model.

Learning a good representation is an essential component for deep reinforcement learning (RL). Representation learning is especially important in multitask and partially observable settings where building a representation of the unknown environment is crucial to solve the tasks. Here we introduce Prediction of Bootstrap Latents (PBL), a simple and flexible self-supervised representation learning algorithm for multitask deep RL. PBL builds on multistep predictive representations of future observations, and focuses on capturing structured information about environment dynamics. Specifically, PBL trains its representation by predicting latent embeddings of future observations. These latent embeddings are themselves trained to be predictive of the aforementioned representations. These predictions form a bootstrapping effect, allowing the agent to learn more about the key aspects of the environment dynamics. In addition, by defining prediction tasks completely in latent space, PBL provides the flexibility of using multimodal observations involving pixel images, language instructions, rewards and more. We show in our experiments that PBL delivers across-the-board improved performance over state of the art deep RL agents in the DMLab-30 and Atari-57 multitask setting.