Cross-Modal Contextualized Hidden State Projection Method for Expanding of Taxonomic Graphs
Taxonomy is a graph of terms organized hierarchically using is-a (hypernymy) relations. We suggest novel candidate-free task formulation for the taxonomy enrichment task. To solve the task, we leverage lexical knowledge from the pre-trained models to predict new words missing in the taxonomic resource. We propose a method that combines graph-, and text-based contextualized representations from transformer networks to predict new entries to the taxonomy. We have evaluated the method suggested for this task against text-only baselines based on BERT and fastText representations. The results demonstrate that incorporation of graph embedding is beneficial in the task of hyponym prediction using contextualized models. We hope the new challenging task will foster further research in automatic text graph construction methods.
Code (0)
등록된 구현이 없습니다.
Tasks
graph constructionGraph EmbeddingSimilar Papers 제목 키워드 기반
CoRect: Context-Aware Logit Contrast for Hidden State Rectification to Resolve Knowledge Conflicts
Retrieval-Augmented Generation (RAG) often struggles with knowledge conflicts, where model-internal parametric knowledge overrides retrieved evidence, leading to unfaithful outputs. Existing approaches are often limited,…
Question AnsweringMultimodal Embeddings from Language Models
Word embeddings such as ELMo have recently been shown to model word semantics with greater efficacy through contextualized learning on large-scale language corpora, resulting in significant improvement in state of the ar…
Emotion RecognitionLanguage ModelingLanguage ModellingWord EmbeddingsCross-Modal Safety Mechanism Transfer in Large Vision-Language Models
Vision-language alignment in Large Vision-Language Models (LVLMs) successfully enables LLMs to understand visual input. However, we find that existing vision-language alignment methods fail to transfer the existing safet…
Visual Question AnsweringConceptAttention: Diffusion Transformers Learn Highly Interpretable Features
Do the rich representations of multi-modal diffusion transformers (DiTs) exhibit unique properties that enhance their interpretability? We introduce ConceptAttention, a novel method that leverages the expressive power of…
Image SegmentationSegmentationSemantic SegmentationIntegrating Multi-scale Contextualized Information for Byte-based Neural Machine Translation
Subword tokenization is a common method for vocabulary building in Neural Machine Translation (NMT) models. However, increasingly complex tasks have revealed its disadvantages. First, a vocabulary cannot be modified once…
Machine TranslationNMTTranslation