Linkages are essentially determined by similarity measures that may be derived from multiple perspectives. For example, spatial linkages are usually generated based on localities of heterogeneous data, whereas semantic linkages can come from various properties, such as different physical meanings behind social relations. Many existing metric learning models focus on spatial linkages, but leave the rich semantic factors unconsidered. Similarities based on these models are usually overdetermined on linkages. We propose a Unified Multi-Metric Learning (UM2L) framework to exploit multiple types of metrics. In UM2L, a type of combination operator is introduced for distance characterization from multiple perspectives, and thus can introduce flexibilities for representing and utilizing both spatial and semantic linkages. Besides, we propose a uniform solver for UM2L which is guaranteed to converge.

Linkages are essentially determined by similarity measures that may be derived from multiple perspectives. For example, spatial linkages are usually generated based on localities of heterogeneous data, whereas semantic linkages can come from various properties, such as different physical meanings behind social relations. Many existing metric learning models focus on spatial linkages, but leave the rich semantic factors unconsidered. Similarities based on these models are usually overdetermined on linkages. We propose a Unified Multi-Metric Learning (UM2L) framework to exploit multiple types of metrics. In UM2L, a type of combination operator is introduced for distance characterization from multiple perspectives, and thus can introduce flexibilities for representing and utilizing both spatial and semantic linkages. Besides, we propose a uniform solver for UM2L which is guaranteed to converge.

"I teach computer science, and that is all," wrote Boaz Barak, of Harvard University, in a recent op-ed in The New York Times.a The main point of the op-ed was to protest the growing politicization of U.S. higher education, especially at elite universities, where we have seen many faculty members proceed from scholarship to advocacy. But in spite of the provocative title, the content of Barak's op-ed is quite more nuanced. "We should not normalize bringing one's ideology to the classroom," wrote Barak, and I could not agree more. But he also wrote that "The interaction of computer science and policy sometimes arises in my classes, and I make sure to present multiple perspectives." Here, Barak is advocating fairness and balance, rather than neutrality and avoidance of non-technical topics.

Textual personality detection aims to identify personality traits by analyzing user-generated content. To achieve this effectively, it is essential to thoroughly examine user-generated content from various perspectives. However, previous studies have struggled with automatically extracting and effectively integrating information from multiple perspectives, thereby limiting their performance on personality detection. To address these challenges, we propose the Multi-view Mixture-of-Experts Model for Textual Personality Detection (MvP). MvP introduces a Multi-view Mixture-of-Experts (MoE) network to automatically analyze user posts from various perspectives. Additionally, it employs User Consistency Regularization to mitigate conflicts among different perspectives and learn a multi-view generic user representation. The model's training is optimized via a multi-task joint learning strategy that balances supervised personality detection with self-supervised user consistency constraints. Experimental results on two widely-used personality detection datasets demonstrate the effectiveness of the MvP model and the benefits of automatically analyzing user posts from diverse perspectives for textual personality detection.

Considerable advancements have been made in various NLP tasks based on the impressive power of large language models (LLMs) and many NLP applications are deployed in our daily lives. In this work, we challenge the capability of LLMs with the new task of Ethical Quandary Generative Question Answering. Ethical quandary questions are more challenging to address because multiple conflicting answers may exist to a single quandary. We explore the current capability of LLMs in providing an answer with a deliberative exchange of different perspectives to an ethical quandary, in the approach of Socratic philosophy, instead of providing a closed answer like an oracle. We propose a model that searches for different ethical principles applicable to the ethical quandary and generates an answer conditioned on the chosen principles through prompt-based few-shot learning. We also discuss the remaining challenges and ethical issues involved in this task and suggest the direction toward developing responsible NLP systems by incorporating human values explicitly.

Linkages are essentially determined by similarity measures that may be derived from multiple perspectives. For example, spatial linkages are usually generated based on localities of heterogeneous data, whereas semantic linkages can come from various properties, such as different physical meanings behind social relations. Many existing metric learning models focus on spatial linkages, but leave the rich semantic factors unconsidered. Similarities based on these models are usually overdetermined on linkages. We propose a Unified Multi-Metric Learning (UM2L) framework to exploit multiple types of metrics.

Over the next decade, artificial intelligence (AI) is expected to impact all kinds of industries and fundamentally shift the way we work. In an article by former McKinsey consultant Pedro Uria Recio, "More than 80% of process-oriented tasks will be done by AI systems ... while humans will continue to do more than 80% of cross-functional reasoning tasks." Furthermore, in a survey conducted by The Economist Intelligence Unit, 75% of executives say "AI will be'actively implemented' in companies within the next three years." The impact of AI on our work is not something in the distant future. Leaders will have to shift into roles that require them to think strategically, operate in uncertain environments and learn quickly.

Conversion optimization tools are estimated to have an average ROI of 223%. And that is totally expected as they're largely responsible for most conversions and revenue. However, CRO tools are more expensive than many other marketing tools, too (as you'll soon see in this article). And there are so many of them out there. But at the end of the day, it's not using these tools that matters but what they do for your business.

This is the latest installment in a regular series of conversations with William McDonough (@billmcdonough), designer, architect, author and entrepreneur. Joel Makower: Tell me about the innovation future roundtable you recently convened. Bill McDonough: I have been working with companies that are looking at the future of mobility in India, and designing factories and other things for them. The chairman said he would like to connect to some of the advanced thinking across many sectors and integrate that with some conversations that he could participate in. The first person I thought of for that was Jack Hidary.

My dissertation describes an approach to automatically formulating or selecting models of a target physical system for a given qualitative reasoning task. It was motivated by two observations regarding modeling in general and work in qualitative physics in particular. First, all model-based reasoning is only as good as the model used (Davis and Hamscher 1988). Second, no single model is adequate or appropriate for a wide range of tasks (Weld 1989).