Related papers: Filling in the Gaps: Efficient Event Coreference R…

The task of event extraction (EE) aims to find the events and event-related argument information from the text and represent them in a structured format. Most previous works try to solve the problem by separately identifying multiple…

Click-through-rate (CTR) prediction has an essential impact on improving user experience and revenue in e-commerce search. With the development of deep learning, graph-based methods are well exploited to utilize graph structure extracted…

Identifying related entities and events within and across documents is fundamental to natural language understanding. We present an approach to entity and event coreference resolution utilizing contrastive representation learning. Earlier…

We propose a deep graph approach to address the task of speech emotion recognition. A compact, efficient and scalable way to represent data is in the form of graphs. Following the theory of graph signal processing, we propose to model…

Coreference resolution has been mostly investigated within a single document scope, showing impressive progress in recent years based on end-to-end models. However, the more challenging task of cross-document (CD) coreference resolution…

Retrieval-Augmented Generation (RAG) enhances large language models by incorporating external knowledge. However, existing vector-based methods often fail on global sensemaking tasks that require reasoning across many documents. GraphRAG…

Recent studies on event detection (ED) haveshown that the syntactic dependency graph canbe employed in graph convolution neural net-works (GCN) to achieve state-of-the-art per-formance. However, the computation of thehidden vectors in such…

In this work, we focus on continual semantic segmentation (CSS), where segmentation networks are required to continuously learn new classes without erasing knowledge of previously learned ones. Although storing images of old classes and…

Generative retrieval has recently emerged as a promising approach to sequential recommendation, framing candidate item retrieval as an autoregressive sequence generation problem. However, existing generative methods typically focus solely…

Textual data question answering has gained significant attention due to its growing applicability. Recently, a novel approach leveraging the Retrieval-Augmented Generation (RAG) method was introduced, utilizing the Prize-Collecting Steiner…

Network alignment, or the task of finding corresponding nodes in different networks, is an important problem formulation in many application domains. We propose CAPER, a multilevel alignment framework that Coarsens the input graphs, Aligns…

Recurrent Neural Networks (RNN) received a vast amount of attention last decade. Recently, the architectures of Recurrent AutoEncoders (RAE) found many applications in practice. RAE can extract the semantically valuable information, called…

Composed Image Retrieval (CIR) is a pivotal and complex task in multimodal understanding. Current CIR benchmarks typically feature limited query categories and fail to capture the diverse requirements of real-world scenarios. To bridge this…

Variational autoencoder (VAE) is a widely used generative model for learning latent representations. Burda et al. in their seminal paper showed that learning capacity of VAE is limited by over-pruning. It is a phenomenon where a significant…

To resolve the semantic ambiguity in texts, we propose a model, which innovatively combines a knowledge graph with an improved attention mechanism. An existing knowledge base is utilized to enrich the text with relevant contextual concepts.…

Research question answering requires accurate retrieval and contextual understanding of scientific literature. However, current Retrieval-Augmented Generation (RAG) methods often struggle to balance complex document relationships with…

Knowledge graph (KG) embedding methods which map entities and relations to unique embeddings in the KG have shown promising results on many reasoning tasks. However, the same embedding dimension for both dense entities and sparse entities…

Retrieval-Augmented Generation (RAG) systems enhance text generation by incorporating external knowledge but often struggle when retrieving context across different text modalities due to semantic gaps. We introduce a generalized…

Research in CDCR remains fragmented due to heterogeneous dataset formats, varying annotation standards, and the predominance of the CDCR definition as the event coreference resolution (ECR). To address these challenges, we introduce uCDCR,…

Query Rewriting (QR) plays a critical role in large-scale dialogue systems for reducing frictions. When there is an entity error, it imposes extra challenges for a dialogue system to produce satisfactory responses. In this work, we propose…