TURL

Relational tables on the Web store a vast amount of knowledge. Owing to the wealth of such tables, there has been tremendous progress on a variety of tasks in the area of table understanding. However, existing work generally relies on heavily-engineered task-specific features and model architectures. In this paper, we present TURL, a novel framework that introduces the pre-training/fine-tuning paradigm to relational Web tables. During pre-training, our framework learns deep contextualized representations on relational tables in an unsupervised manner. Its universal model design with pre-trained representations can be applied to a wide range of tasks with minimal task-specific fine-tuning. Specifically, we propose a structure-aware Transformer encoder to model the row-column structure of relational tables, and present a new Masked Entity Recovery (MER) objective for pre-training to capture the semantics and knowledge in large-scale unlabeled data. We systematically evaluate TURL with a benchmark consisting of 6 different tasks for table understanding (e.g., relation extraction, cell filling). We show that TURL generalizes well to all tasks and substantially outperforms existing methods in almost all instances.

Microsoft Concept Graph: Mining Semantic Concepts for Short Text Understanding

Knowlege is important for text-related applications. In this paper, we introduce Microsoft Concept Graph, a knowledge graph engine that provides concept tagging APIs to facilitate the understanding of human languages. Microsoft Concept Graph is built upon Probase, a universal probabilistic taxonomy consisting of instances and concepts mined from the Web. We start by introducing the construction of the knowledge graph through iterative semantic extraction and taxonomy construction procedures, which extract 2.7 million concepts from 1.68 billion Web pages. We then use conceptualization models to represent text in the concept space to empower text-related applications, such as topic search, query recommendation, Web table understanding and Ads relevance. Since the release in 2016, Microsoft Concept Graph has received more than 100,000 pageviews, 2 million API calls and 3,000 registered downloads from 50,000 visitors over 64 countries.

“Putting gender on the table”: Understanding reactions to women who discuss gender inequality

Even though gender inequality remains an important challenge across societies, many believe it to be long gone (Marken, 2016). Thus, it is essential to publicly address issues related to gender inequality as a first step towards advancing change in this domain. However, those who address gender inequality may encounter personal costs. In the current research, we examined reactions to women who “put gender on the table.” In Study 1 ( N = 202), men who were exposed to a woman who raised the issue of gender inequality (vs. age inequality or a neutral topic), had more negative attitudes towards both her and gender equality. In Study 2, ( N = 233), women high on feminist identification were more positive toward a woman who discussed gender inequality (vs. other topics), whereas women low on feminist identification were more negative toward both her and the issue. Theoretical and practical implications are discussed.