Bridging is an anaphoric phenomenon where the referent of an entity in a discourse is dependent on a previous, non-identical entity for interpretation, such as in "There is 'a house'. 'The door' is red," where the door is specifically understood to be the door of the aforementioned house. While there are several existing resources in English for bridging anaphora, most are small, provide limited coverage of the phenomenon, and/or provide limited genre coverage. In this paper, we introduce GUMBridge, a new resource for bridging, which includes 16 diverse genres of English, providing both broad coverage for the phenomenon and granular annotations for the subtype categorization of bridging varieties. We also present an evaluation of annotation quality and report on baseline performance using open and closed source contemporary LLMs on three tasks underlying our data, showing that bridging resolution and subtype classification remain difficult NLP tasks in the age of LLMs.

In this research note, we show the relationship between two non-admissible argumentation framework semantics: cogent and weakly admissible semantics. We prove that, while cogent extensions are weakly admissible, the converse is not true.

Chat-oriented dialogue systems designed to provide tangible benefits, such as sharing the latest news or preventing frailty in senior citizens, often require Proactive acquisition of specific user Information via chats on user-faVOred Topics (PIVOT). This study proposes the PIVOT task, designed to advance the technical foundation for these systems. In this task, a system needs to acquire the answers of a user to predefined questions without making the user feel abrupt while engaging in a chat on a predefined topic. We found that even recent large language models (LLMs) show a low success rate in the PIVOT task. We constructed a dataset suitable for the analysis to develop more effective systems. Finally, we developed a simple but effective system for this task by incorporating insights obtained through the analysis of this dataset.

Argument graphs provide an abstract representation of an argumentative situation. A bipolar argument graph is a directed graph where each node denotes an argument, and each arc denotes the influence of one argument on another. Here we assume that the influence is supporting, attacking, or ambiguous. In a bipolar argument graph, each argument is atomic and so it has no internal structure. Yet to better understand the nature of the individual arguments, and how they interact, it is important to consider their internal structure. To address this need, this paper presents a framework based on the use of logical arguments to instantiate bipolar argument graphs, and a set of possible constraints on instantiating arguments that take into account the internal structure of the arguments, and the types of relationship between arguments.

Many deep learning-based computerized respiratory sound analysis methods have previously been developed. However, these studies focus on either lung sound only or tracheal sound only. The effectiveness of using a lung sound analysis algorithm on tracheal sound and vice versa has never been investigated. Furthermore, no one knows whether using lung and tracheal sounds together in training a respiratory sound analysis model is beneficial. In this study, we first constructed a tracheal sound database, HF_Tracheal_V1, containing 10448 15-s tracheal sound recordings, 21741 inhalation labels, 15858 exhalation labels, and 6414 continuous adventitious sound (CAS) labels. HF_Tracheal_V1 and our previously built lung sound database, HF_Lung_V2, were either combined (mixed set), used one after the other (domain adaptation), or used alone to train convolutional neural network bidirectional gate recurrent unit models for inhalation, exhalation, and CAS detection in lung and tracheal sounds. The results revealed that the models trained using lung sound alone performed poorly in tracheal sound analysis and vice versa. However, mixed set training or domain adaptation improved the performance for 1) inhalation and exhalation detection in lung sounds and 2) inhalation, exhalation, and CAS detection in tracheal sounds compared to positive controls (the models trained using lung sound alone and used in lung sound analysis and vice versa). In particular, the model trained on the mixed set had great flexibility to serve two purposes, lung and tracheal sound analyses, at the same time.

Although it may sound blunt, the truth is that several organizations have no idea about how to implement AI correctly. Unlike what many business executives may believe, AI is not just about the automation of business processes. Enterprise AI implementation must be made with long-term data-driven strategies in mind. To ingrain the technology within the fabric of your business, you'll need to clearly explore how your business and AI can align perfectly to maximize its potential for widening your ROI, revenue generation, growth and diversification. For that purpose, understanding the symbiotic relationship between AI and your enterprise is vital.

Over the past few years, there has been a great deal of theoretical and empirical work on both of these algorithms. As part of the research conducted on these algorithms, some interesting theoretical properties were proven for fMM and not for GBFSH and vice versa. In addition, both of them are used as benchmarks for evaluation bidirectional heuristic search algorithms. In this paper we show that fMM infused by a lower-bound propagation and GBFSH are equivalent. In essence, every instance of fMM can be mapped to an instance of GBFSH that expands the exact sequence of nodes and vice versa.

While solving classification problems using deep learning models, we use cross entropy to tell the model how good or bad it's predictions are during training. What is this cross entropy loss? Cross entropy in a way can be looked as the difference between 2 probability distributions in the case of supervised learning with one-hot encoded labels. Let's say we are trying to classify an input between 3 categories. It is okay if you don't understand this next piece of code, this is just to show us the cross entropy value. If we consider the probabilities as 2 vectors and find the squared distance between them, we get the L2 loss.

In an interview with Mathias Döpfner, the CEO of Axel Springer, Business Insider's parent company, Elon Musk revealed his thoughts on self-driving cars, oversight of artificial intelligence, and reasons behind his quest to be buried on Mars. Musk, who had announced in October Tesla's release of a beta version of its long-awaited "full self-driving" software, clarified that he is "definitely not trying to take anyone's steering wheel away from them." "I'm just saying what will most likely occur, and I am certain about this, is that self-driving will become much safer than a human driver. Probably by a factor of 10," he told Döpfner, adding that the bar for whether a person will be able to drive or not will be much more "stringent" in the future when autonomous driving is "10 times safer." But as Business Insider's Graham Rapier reported, the top US safety regulator, the National Highway Traffic Safety Administration, has repeated that "no vehicle available for purchase today is capable of driving itself." "The most advanced vehicle technologies available for purchase today provide driver assistance and require a fully attentive human driver at all times performing the driving task and monitoring the surrounding environment. Abusing these technologies is, at a minimum, distracted driving. Every State in the Nation holds the driver responsible for the safe operation of the vehicle," the agency said.