Research map / Large language models / Language, safety and interpretability
Dictionary-Guided Editing Networks for Paraphrase Generation
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Add PPDB-guided dictionary editing to sequence generation | Paraphrase generation · MSCOCO, beam size 1 | BLEU: 39.2 -> 40.3 | Helped |
| Add PPDB-guided dictionary editing to sequence generation | Paraphrase generation · MSCOCO, beam size 10 | METEOR: 30.9 -> 31.3 | Helped |
| Add PPDB-guided dictionary editing to sequence generation | Paraphrase generation · Quora, beam size 1 | METEOR: 26.2 -> 29.9 | Helped |
| Use beam search with beam size 10 instead of greedy search | Dictionary-Guided Editing Networks · Quora | BLEU: 27.6 -> 28.4 | Mixed |
| Use dictionary-guided editing instead of VAE-SVG-eq | Paraphrase generation · Quora, beam size 10 | BLEU: 37.1 -> 28.4 | Hurt |
Closest papers by meaning
- Integrating Linguistic Knowledge to Sentence Paraphrase Generation (AAAI 2020 · similarity 0.90)
- Joint Copying and Restricted Generation for Paraphrase (AAAI 2017 · similarity 0.88)
- A Deep Generative Framework for Paraphrase Generation (AAAI 2018 · similarity 0.87)
- LAMPAT: Low-Rank Adaption for Multilingual Paraphrasing Using Adversarial Training (AAAI 2024 · similarity 0.83)
- Latent Paraphrasing: Perturbation on Layers Improves Knowledge Injection in Language Models (NeurIPS 2024 · similarity 0.83)
- Resolving Lexical Bias in Model Editing (ICML 2025 · similarity 0.82)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.