Related papers: Obj2Sub: Unsupervised Conversion of Objective to S…

Recent years have witnessed an abundance of new publications and approaches on meta-learning. This community-wide enthusiasm has sparked great insights but has also created a plethora of seemingly different frameworks, which can be hard to…

Exploring the tremendous amount of data efficiently to make a decision, similar to answering a complicated question, is challenging with many real-world application scenarios. In this context, automatic summarization has substantial…

We present a novel unsupervised framework for focused meeting summarization that views the problem as an instance of relation extraction. We adapt an existing in-domain relation learner (Chen et al., 2011) by exploiting a set of…

Learning compositional representation is a key aspect of object-centric learning as it enables flexible systematic generalization and supports complex visual reasoning. However, most of the existing approaches rely on auto-encoding…

Inverse optimization has been increasingly used to estimate unknown parameters in an optimization model based on decision data. We show that such a point estimation is insufficient in a prescriptive setting where the estimated parameters…

We propose a simple, statistically principled, and theoretically justified method to improve supervised learning when the training set is not representative, a situation known as covariate shift. We build upon a well-established methodology…

We equip a smaller Language Model to generalise to answering challenging compositional questions that have not been seen in training. To do so we propose a combination of multitask supervised pretraining on up to 93 tasks designed to…

This dissertation presents several new methods of supervised and unsupervised learning of word sense disambiguation models. The supervised methods focus on performing model searches through a space of probabilistic models, and the…

In implicit discourse relation classification, we want to predict the relation between adjacent sentences in the absence of any overt discourse connectives. This is challenging even for humans, leading to shortage of annotated data, a fact…

Subjectivity is the expression of internal opinions or beliefs which cannot be objectively observed or verified, and has been shown to be important for sentiment analysis and word-sense disambiguation. Furthermore, subjectivity is an…

Semi-supervised learning improves the performance of supervised machine learning by leveraging methods from unsupervised learning to extract information not explicitly available in the labels. Through the design of a system that enables a…

Our goal is to extract meaningful transformations from raw images, such as varying the thickness of lines in handwriting or the lighting in a portrait. We propose an unsupervised approach to learn such transformations by attempting to…

Self-supervision provides effective representations for downstream tasks without requiring labels. However, existing approaches lag behind fully supervised training and are often not thought beneficial beyond obviating or reducing the need…

Deep learning algorithms are often said to be data hungry. The performance of such algorithms generally improve as more and more annotated data is fed into the model. While collecting unlabelled data is easier (as they can be scraped easily…

Unlike well-structured text, such as news reports and encyclopedia articles, dialogue content often comes from two or more interlocutors, exchanging information with each other. In such a scenario, the topic of a conversation can vary upon…

The key challenge in learning dense correspondences lies in the lack of ground-truth matches for real image pairs. While photometric consistency losses provide unsupervised alternatives, they struggle with large appearance changes, which…

A new method is presented, that can help a person become aware of his or her unconscious preferences, and convey them to others in the form of verbal explanation. The method combines the concepts of reflection, visualization, and…

This paper explores the outcome of training state-of-the-art dereverberation models with supervision settings ranging from weakly-supervised to virtually unsupervised, relying solely on reverberant signals and an acoustic model for…

This paper tackles the problem of learning a questioner in the goal-oriented visual dialog task. Several previous works adopt model-free reinforcement learning. Most pretrain the model from a finite set of human-generated data. We argue…

Compositional, structured models are appealing because they explicitly decompose problems and provide interpretable intermediate outputs that give confidence that the model is not simply latching onto data artifacts. Learning these models…