This portal has been archived. Explore the next generation of this technology.
Evaluating the Utility of Document Embedding Vector Difference for Relation Learning
lib:15d6eb0b46cf9712 (v1.0.0)
Authors: Jingyuan Zhang,Timothy Baldwin
ArXiv: 1907.08184
Document: PDF DOI
Abstract URL: https://arxiv.org/abs/1907.08184v1
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.
ArXiv: 1907.08184
Document: PDF DOI
Abstract URL: https://arxiv.org/abs/1907.08184v1
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.
Relevant initiatives
Related knowledge about this paper
Reproduced results (crowd-benchmarking and competitions)
Artifact and reproducibility checklists
- ACM/cTuning artifact appendix and reproducibility checklist
- NeurIPS reproducibility checklist
- SIGPLAN's checklist for empirical evaluation
- Collective Knowledge (organizing research projects based on FAIR principles)