Related papers: Syntactic and Semantic-driven Learning for Open In…

Effective exploration is critical for reinforcement learning agents in environments with sparse rewards or high-dimensional state-action spaces. Recent works based on state-visitation counts, curiosity and entropy-maximization generate…

A challenge in training discriminative models like neural networks is obtaining enough labeled training data. Recent approaches use generative models to combine weak supervision sources, like user-defined heuristics or knowledge bases, to…

Spoken semantic parsing (SSP) involves generating machine-comprehensible parses from input speech. Training robust models for existing application domains represented in training data or extending to new domains requires corresponding…

We are interested in learning models of non-stationary environments, which can be framed as a multi-task learning problem. Model-free reinforcement learning algorithms can achieve good asymptotic performance in multi-task learning at a cost…

Unsupervised learning has been an attractive method for easily deriving meaningful data representations from vast amounts of unlabeled data. These representations, or embeddings, often yield superior results in many tasks, whether used…

Currently, machine learning techniques have seen significant success across various applications. Most of these techniques rely on supervision from human-generated labels or a mixture of noisy and imprecise labels from multiple sources.…

As a fundamental NLP task, semantic role labeling (SRL) aims to discover the semantic roles for each predicate within one sentence. This paper investigates how to incorporate syntactic knowledge into the SRL task effectively. We present…

Recent advancements in open vocabulary models, like CLIP, have notably advanced zero-shot classification and segmentation by utilizing natural language for class-specific embeddings. However, most research has focused on improving model…

End-to-end training from scratch of current deep architectures for new computer vision problems would require Imagenet-scale datasets, and this is not always possible. In this paper we present a method that is able to take advantage of…

Semantic role labeling (SRL) is dedicated to recognizing the semantic predicate-argument structure of a sentence. Previous studies in terms of traditional models have shown syntactic information can make remarkable contributions to SRL…

In this paper, we propose SemanticAC, a semantics-assisted framework for Audio Classification to better leverage the semantic information. Unlike conventional audio classification methods that treat class labels as discrete vectors, we…

Extracting useful entities and attribute values from illicit domains such as human trafficking is a challenging problem with the potential for widespread social impact. Such domains employ atypical language models, have `long tails' and…

Prior works have demonstrated that implicit representations trained only for reconstruction tasks typically generate encodings that are not useful for semantic tasks. In this work, we propose a method that contextualises the encodings of…

Large-scale datasets possessing clean label annotations are crucial for training Convolutional Neural Networks (CNNs). However, labeling large-scale data can be very costly and error-prone, and even high-quality datasets are likely to…

Named entity recognition (NER) is highly sensitive to sentential syntactic and semantic properties where entities may be extracted according to how they are used and placed in the running text. To model such properties, one could rely on…

This study investigates the use of unsupervised word embeddings and sequence features for sample representation in an active learning framework built to extract clinical concepts from clinical free text. The objective is to further reduce…

Cross-lingual Speech Emotion Recognition (CLSER) aims to identify emotional states in unseen languages. However, existing methods heavily rely on the semantic synchrony of complete labels and static feature stability, hindering low-resource…

Semantic parsing has emerged as a significant and powerful paradigm for natural language interface and question answering systems. Traditional methods of building a semantic parser rely on high-quality lexicons, hand-crafted grammars and…

State-of-the-art slot filling models for goal-oriented human/machine conversational language understanding systems rely on deep learning methods. While multi-task training of such models alleviates the need for large in-domain annotated…

Contrastive learning has been the dominant approach to train state-of-the-art sentence embeddings. Previous studies have typically learned sentence embeddings either through the use of human-annotated natural language inference (NLI) data…