Related papers: Dynamic Hybrid Relation Network for Cross-Domain C…

Machine learning algorithms such as linear regression, SVM and neural network have played an increasingly important role in the process of scientific discovery. However, none of them is both interpretable and accurate on nonlinear datasets.…

Natural language understanding often requires deep semantic knowledge. Expanding on previous proposals, we suggest that some important aspects of semantic knowledge can be modeled as a language model if done at an appropriate level of…

Effective token compression remains a critical challenge for scaling models to handle increasingly complex and diverse datasets. A novel mechanism based on contextual reinforcement is introduced, dynamically adjusting token importance…

This paper presents a reactive planning system that enriches the topological representation of an environment with a tightly integrated semantic representation, achieved by incorporating and exploiting advances in deep perceptual learning…

In this paper, we tackle a critical challenge in model evaluation: how to keep code benchmarks useful when models might have already seen them during training. We introduce a novel solution, dynamic benchmarking framework, to address this…

This study investigates a hybrid method for text classification that integrates deep feature extraction from large language models, multi-scale fusion through feature pyramids, and structured modeling with graph neural networks to enhance…

The state-of-the-art semantic communication (SC) schemes typically rely on end-to-end deep learning frameworks that lack interpretability and struggle with robust semantic selection and reconstruction under noisy conditions. To address this…

Machine reading comprehension (MRC) poses new challenges over logical reasoning, which aims to understand the implicit logical relations entailed in the given contexts and perform inference over them. Due to the complexity of logic, logical…

Modelling long-range dependencies is critical for scene understanding tasks in computer vision. Although CNNs have excelled in many vision tasks, they are still limited in capturing long-range structured relationships as they typically…

We introduce a relational graph neural network with bi-directional attention mechanism and hierarchical representation learning for open-domain question answering task. Our model can learn contextual representation by jointly learning and…

In this paper, we propose a dynamic shared context processing method based on DSC (Dynamic Shared Context) model, applied in an e-collaborative learning environment. Firstly, we present the model. This is a way to measure the relevance…

The schema-guided paradigm overcomes scalability issues inherent in building task-oriented dialogue (TOD) agents with static ontologies. Instead of operating on dialogue context alone, agents have access to hierarchical schemas containing…

The key to integrating visual language tasks is to establish a good alignment strategy. Recently, visual semantic representation has achieved fine-grained visual understanding by dividing grids or image patches. However, the coarse-grained…

Syntactic structures used to play a vital role in natural language processing (NLP), but since the deep learning revolution, NLP has been gradually dominated by neural models that do not consider syntactic structures in their design. One…

Graph-based representations such as Scene Graphs enable localization in structured indoor environments by matching a locally observed graph, constructed from sensor data, to a prior map. This process is particularly challenging in…

Semantic parsing, as an important approach to question answering over knowledge bases (KBQA), transforms a question into the complete query graph for further generating the correct logical query. Existing semantic parsing approaches mainly…

Reasoning about images/objects and their hierarchical interactions is a key concept for the next generation of computer vision approaches. Here we present a new framework to deal with it through a visual hierarchical context-based…

Compared to traditional visual question answering, video-grounded dialogues require additional reasoning over dialogue context to answer questions in a multi-turn setting. Previous approaches to video-grounded dialogues mostly use dialogue…

In this work, we propose contextual language models that incorporate dialog level discourse information into language modeling. Previous works on contextual language model treat preceding utterances as a sequence of inputs, without…

Modern deep learning approaches have achieved groundbreaking performance in modeling and classifying sequential data. Specifically, attention networks constitute the state-of-the-art paradigm for capturing long temporal dynamics. This paper…