Research map / Large language models / Language, safety and interpretability
Multiresolution Recurrent Neural Networks: An Application to Dialogue Response 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 |
|---|---|---|---|
| Model coarse activity-entity sequences jointly with dialogue words | Ubuntu response generation · Ubuntu | Activity F1: 5.46 -> 11.43 | Helped |
| Model coarse noun sequences jointly with dialogue words | Ubuntu response generation · Ubuntu | Entity F1: 2.44 -> 6.31 | Helped |
| Model coarse noun sequences jointly with dialogue words | Ubuntu response generation · Ubuntu | Human fluency: 2.98 -> 3.48 | Helped |
| Model coarse noun sequences jointly with dialogue words | Ubuntu response generation · Ubuntu | Human relevancy: 1.01 -> 1.32 | Helped |
| Use activity-entity coarse representations instead of noun representations (ablation) | MrRNN · Ubuntu | Activity F1: 4.04 -> 11.43 | Helped |
| Use noun coarse representations instead of activity-entity representations (ablation) | MrRNN · Ubuntu | Entity F1: 3.72 -> 6.31 | Helped |
| Model coarse noun sequences jointly with dialogue words | Twitter response generation · Twitter | Noun F1: 0.65 -> 4.63 | Helped |
| Model coarse noun sequences jointly with dialogue words | Twitter response generation · Twitter | Tense accuracy: 27.06 -> 34.48 | Helped |
| Model coarse noun sequences jointly with dialogue words | Twitter response generation · Twitter | Embedding Average: 53.26 -> 49.77 | Hurt |
| Model coarse noun sequences jointly with dialogue words | Twitter response generation · Twitter | Embedding Greedy: 39.64 -> 40.44 | Helped |
Closest papers by meaning
- Building End-To-End Dialogue Systems Using Generative Hierarchical Neural Network Models (AAAI 2016 · similarity 0.89)
- A Hierarchical Latent Variable Encoder-Decoder Model for Generating Dialogues (AAAI 2017 · similarity 0.88)
- Hierarchical Recurrent Attention Network for Response Generation (AAAI 2018 · similarity 0.87)
- DialogBERT: Discourse-Aware Response Generation via Learning to Recover and Rank Utterances (AAAI 2021 · similarity 0.87)
- Neural Response Generation With Dynamic Vocabularies (AAAI 2018 · similarity 0.87)
- Memory Architectures in Recurrent Neural Network Language Models (ICLR 2018 · similarity 0.87)
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.