相关论文: Context-Aware Adapter Tuning for Few-Shot Relation…

Self-supervised pre-training of transformer models has shown enormous success in improving performance on a number of downstream tasks. However, fine-tuning on a new task still requires large amounts of task-specific labelled data to…

Controlling the generative model to adapt a new domain with limited samples is a difficult challenge and it is receiving increasing attention. Recently, methods based on meta-learning have shown promising results for few-shot domain…

Large language models (LLMs) often seamlessly adapt to new tasks through in-context learning (ICL) or supervised fine-tuning (SFT). However, ICL is inefficient when handling many demonstrations, and SFT incurs training overhead while…

Pretrained language models (PLM) have recently advanced graph-to-text generation, where the input graph is linearized into a sequence and fed into the PLM to obtain its representation. However, efficiently encoding the graph structure in…

Pre-trained vision-language models, e.g., CLIP, working with manually designed prompts have demonstrated great capacity of transfer learning. Recently, learnable prompts achieve state-of-the-art performance, which however are prone to…

This paper explores the integration of graph knowledge from linguistic ontologies into multilingual Large Language Models (LLMs) using adapters to improve performance for low-resource languages (LRLs) in sentiment analysis (SA) and named…

Standard transformer-based language models, while powerful for general text, often struggle with the fine-grained syntax and entity relationships in complex technical, engineering documents. To address this, we propose the Contextual Graph…

Human mobility is intricately influenced by urban contexts spatially and temporally, constituting essential domain knowledge in understanding traffic systems. While existing traffic forecasting models primarily rely on raw traffic data and…

Embedding knowledge graphs (KGs) into continuous vector spaces is a focus of current research. Early works performed this task via simple models developed over KG triples. Recent attempts focused on either designing more complicated triple…

This paper presents a contextualized graph attention network that combines edge features and multiple sub-graphs for improving relation extraction. A novel method is proposed to use multiple sub-graphs to learn rich node representations in…

Low-resource languages (LRLs) face significant challenges in natural language processing (NLP) due to limited data. While current state-of-the-art large language models (LLMs) still struggle with LRLs, smaller multilingual models (mLMs)…

Real-time cognitive load assessment is essential for adaptive human-computer interaction but remains challenging due to limited labeled data and poor cross-subject generalization. Recent ECG foundation models pre-trained on millions of…

We present a conceptually simple, flexible, and general framework for few-shot learning, where a classifier must learn to recognise new classes given only few examples from each. Our method, called the Relation Network (RN), is trained…

Adapter-based tuning methods have shown significant potential in transferring knowledge from pre-trained Vision-Language Models to the downstream tasks. However, after reviewing existing adapters, we find they generally fail to fully…

Knowledge Graph Question Answering (KGQA) involves retrieving entities as answers from a Knowledge Graph (KG) using natural language queries. The challenge is to learn to reason over question-relevant KG facts that traverse KG entities and…

Large Language Models (LLMs) based on Transformers excel at text processing, but their reliance on prompts for specialized behavior introduces computational overhead. We propose a modification to a Transformer architecture that eliminates…

Recently, commonsense knowledge models - pretrained language models (LM) fine-tuned on knowledge graph (KG) tuples - showed that considerable amounts of commonsense knowledge can be encoded in the parameters of large language models.…

Knowledge graphs (KGs) serve as useful resources for various natural language processing applications. Previous KG completion approaches require a large number of training instances (i.e., head-tail entity pairs) for every relation. The…

Knowledge graphs (KGs), containing many entity-relation-entity triples, provide rich information for downstream applications. Although extracting triples from unstructured texts has been widely explored, most of them require a large number…

Representation learning on text-attributed graphs (TAGs) integrates structural connectivity with rich textual semantics, enabling applications in diverse domains. Current methods largely rely on contrastive learning to maximize cross-modal…