相关论文: Relation Discovery with Out-of-Relation Knowledge …

Hypergraph is a data structure that enables us to model higher-order associations among data entities. Conventional graph-structured data can represent pairwise relationships only, whereas hypergraph enables us to associate any number of…

Semantic novelty detection aims at discovering unknown categories in the test data. This task is particularly relevant in safety-critical applications, such as autonomous driving or healthcare, where it is crucial to recognize unknown…

We propose a new scientific application of unsupervised learning techniques to boost our ability to search for new phenomena in data, by detecting discrepancies between two datasets. These could be, for example, a simulated standard-model…

Unsupervised pre-trained word embeddings are used effectively for many tasks in natural language processing to leverage unlabeled textual data. Often these embeddings are either used as initializations or as fixed word representations for…

Unsupervised machine learning is widely used to mine large, unlabeled datasets to make data-driven discoveries in critical domains such as climate science, biomedicine, astronomy, chemistry, and more. However, despite its widespread…

Knowledge graphs have attracted lots of attention in academic and industrial environments. Despite their usefulness, popular knowledge graphs suffer from incompleteness of information, especially in their type assertions. This has…

In many machine learning systems that jointly learn from multiple modalities, a core research question is to understand the nature of multimodal interactions: how modalities combine to provide new task-relevant information that was not…

There have been multiple recent proposals on using deep neural networks for code search using natural language. Common across these proposals is the idea of $\mathit{embedding}$ code and natural language queries, into real vectors and then…

Efficient explorative data analysis systems must take into account both what a user knows and wants to know. This paper proposes a principled framework for interactive visual exploration of relations in data, through views most informative…

Understanding the connections between unstructured text and semi-structured table is an important yet neglected problem in natural language processing. In this work, we focus on content-based table retrieval. Given a query, the task is to…

We introduce an approach for open-domain question answering (QA) that retrieves and reads a passage graph, where vertices are passages of text and edges represent relationships that are derived from an external knowledge base or…

While recent research on natural language inference has considerably benefited from large annotated datasets, the amount of inference-related knowledge (including commonsense) provided in the annotated data is still rather limited. There…

We investigate the possibilities of employing dictionary learning to address the requirements of most anomaly detection applications, such as absence of supervision, online formulations, low false positive rates. We present new results of…

Semantic Image Interpretation is the task of extracting a structured semantic description from images. This requires the detection of visual relationships: triples (subject,relation,object) describing a semantic relation between a subject…

We show that state-of-the-art self-supervised language models can be readily used to extract relations from a corpus without the need to train a fine-tuned extractive head. We introduce RE-Flex, a simple framework that performs constrained…

We present the zero-shot entity linking task, where mentions must be linked to unseen entities without in-domain labeled data. The goal is to enable robust transfer to highly specialized domains, and so no metadata or alias tables are…

Uncovering latent community structure in complex networks is a field that has received an enormous amount of attention. Unfortunately, whilst potentially very powerful, unsupervised methods for uncovering labels based on topology alone has…

When looking at the structure of natural language, "phrases" and "words" are central notions. We consider the problem of identifying such "meaningful subparts" of language of any length and underlying composition principles in a completely…

Despite the recent attention to DeepFakes, one of the most prevalent ways to mislead audiences on social media is the use of unaltered images in a new but false context. To address these challenges and support fact-checkers, we propose a…

Many data we collect today are in tabular form, with rows as records and columns as attributes associated with each record. Understanding the structural relationship in tabular data can greatly facilitate the data science process.…