Related papers: Domain Agnostic Real-Valued Specificity Prediction

The prediction of valence from speech is an important, but challenging problem. The externalization of valence in speech has speaker-dependent cues, which contribute to performances that are often significantly lower than the prediction of…

Recent approaches for weakly supervised instance segmentations depend on two components: (i) a pseudo label generation model that provides instances which are consistent with a given annotation; and (ii) an instance segmentation model,…

Recent reports suggest that a generic supervised deep CNN model trained on a large-scale dataset reduces, but does not remove, dataset bias. Fine-tuning deep models in a new domain can require a significant amount of labeled data, which for…

The amount of labeled data to train models for speech tasks is limited for most languages, however, the data scarcity is exacerbated for speech translation which requires labeled data covering two different languages. To address this issue,…

We propose a novel setting for learning, where the input domain is the image of a map defined on the product of two sets, one of which completely determines the labels. We derive a new risk bound for this setting that decomposes into a bias…

State-of-the-art deep neural networks demonstrate outstanding performance in semantic segmentation. However, their performance is tied to the domain represented by the training data. Open world scenarios cause inaccurate predictions which…

Semantic segmentation has achieved significant advances in recent years. While deep neural networks perform semantic segmentation well, their success rely on pixel level supervision which is expensive and time-consuming. Further, training…

We consider the problem of unsupervised domain adaptation for image classification. To learn target-domain-aware features from the unlabeled data, we create a self-supervised pretext task by augmenting the unlabeled data with a certain type…

Time series anomaly detection is a challenging task with a wide range of real-world applications. Due to label sparsity, training a deep anomaly detector often relies on unsupervised approaches. Recent efforts have been devoted to time…

RST-style discourse parsing plays a vital role in many NLP tasks, revealing the underlying semantic/pragmatic structure of potentially complex and diverse documents. Despite its importance, one of the most prevailing limitations in modern…

Topic models are widely used in natural language processing, allowing researchers to estimate the underlying themes in a collection of documents. Most topic models use unsupervised methods and hence require the additional step of attaching…

Automatic sentence summarization produces a shorter version of a sentence, while preserving its most important information. A good summary is characterized by language fluency and high information overlap with the source sentence. We model…

Segmenting text into fine-grained units of meaning is important to a wide range of NLP applications. The default approach of segmenting text into sentences is often insufficient, especially since sentences are usually complex enough to…

Domain mismatch between training and testing can lead to significant degradation in performance in many machine learning scenarios. Unfortunately, this is not a rare situation for automatic speech recognition deployments in real-world…

In this paper, we propose a variational approach to unsupervised sentiment analysis. Instead of using ground truth provided by domain experts, we use target-opinion word pairs as a supervision signal. For example, in a document snippet "the…

News Discourse Profiling seeks to scrutinize the event-related role of each sentence in a news article and has been proven useful across various downstream applications. Specifically, within the context of a given news discourse, each…

Identifying and extracting data elements such as study descriptors in publication full texts is a critical yet manual and labor-intensive step required in a number of tasks. In this paper we address the question of identifying data elements…

Discourse parsing could not yet take full advantage of the neural NLP revolution, mostly due to the lack of annotated datasets. We propose a novel approach that uses distant supervision on an auxiliary task (sentiment classification), to…

Sentiment analysis is an important task in natural language processing (NLP). Most of existing state-of-the-art methods are under the supervised learning paradigm. However, human annotations can be scarce. Thus, we should leverage more weak…

Deep learning has produced state-of-the-art results for a variety of tasks. While such approaches for supervised learning have performed well, they assume that training and testing data are drawn from the same distribution, which may not…