paper-with-me

홈 › Papers

Evaluating the Utility of Document Embedding Vector Difference for Relation Learning

2019-07-18 · Jingyuan Zhang, Timothy Baldwin

Recent work has demonstrated that vector offsets obtained by subtracting pretrained word embedding vectors can be used to predict lexical relations with surprising accuracy. Inspired by this finding, in this paper, we extend the idea to the document level, in generating document-level embeddings, calculating the distance between them, and using a linear classifier to classify the relation between the documents. In the context of duplicate detection and dialogue act tagging tasks, we show that document-level difference vectors have utility in assessing document-level similarity, but perform less well in multi-relational classification.

📄 PDF Abstract BibTeX arXiv:1907.08184

Code (0)

등록된 구현이 없습니다.

Tasks

Document EmbeddingRelation

Similar Papers 제목 키워드 기반

Take and Took, Gaggle and Goose, Book and Read: Evaluating the Utility of Vector Differences for Lexical Relation Learning

2015-09-05 · ACL 2016 8 · Ekaterina Vylomova, Laura Rimell, Trevor Cohn, Timothy Baldwin

Recent work on word embeddings has shown that simple vector subtraction over pre-trained embeddings is surprisingly effective at capturing different lexical relations, despite lacking explicit supervision. Prior work has…

ClusteringRelationWord Embeddings

Representing Mixtures of Word Embeddings with Mixtures of Topic Embeddings

2022-03-03 · ICLR 2022 4 · Dongsheng Wang, Dandan Guo, He Zhao, Huangjie Zheng 외

A topic model is often formulated as a generative model that explains how each word of a document is generated given a set of topics and document-specific topic proportions. It is focused on capturing the word co-occurre…

parameter estimationWord Embeddings

Shadow Queries for Private Retrieval in Vector Databases

2026-09-04 · Xinguo Feng, Zhongkui Ma, Zihan Wang, Chuan Yan 외 arxiv

Large language models (LLMs) increasingly rely on information retrieval (IR) systems, such as Retrieval-Augmented Generation (RAG), to incorporate domain-specific knowledge without costly re-training. These systems often…

Information Retrieval

Vector of Locally-Aggregated Word Embeddings (VLAWE): A Novel Document-level Representation

2019-02-23 · NAACL 2019 6 · Radu Tudor Ionescu, Andrei M. Butnaru

In this paper, we propose a novel representation for text documents based on aggregating word embedding vectors into document embeddings. Our approach is inspired by the Vector of Locally-Aggregated Descriptors used for …

Multi-Label Text ClassificationSentiment AnalysisSubjectivity Analysistext-classification+2

Dirichlet-vMF Mixture Model

2017-02-24 · Shaohua Li

This document is about the multi-document Von-Mises-Fisher mixture model with a Dirichlet prior, referred to as VMFMix. VMFMix is analogous to Latent Dirichlet Allocation (LDA) in that they can capture the co-occurrence …

Document ClassificationGeneral Classificationmodel