# Improved Deep Learning Baselines for Ubuntu Corpus Dialogs

arXiv: https://arxiv.org/abs/1510.03753 · HTML: https://mlsanity.com/paper/1510.03753/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Oct 2015.

## Built on by (most cited first, 12 of 12)

- [TWEETSUMM -- A Dialog Summarization Dataset for Customer Service](https://mlsanity.com/paper/2111.11894/) (2021)
- [Advances in Multi-turn Dialogue Comprehension: A Survey](https://mlsanity.com/paper/2103.03125/) (2021)
- [Multi-turn Dialogue Reading Comprehension with Pivot Turns and Knowledge](https://mlsanity.com/paper/2102.05474/) (2021)
- [Dialogue-oriented Pre-training](https://mlsanity.com/paper/2106.00420/) (2021)
- [Multi-turn Dialogue Comprehension from a Topic-aware Perspective](https://mlsanity.com/paper/2309.09666/) (2023)
- [Dial-MAE: ConTextual Masked Auto-Encoder for Retrieval-based Dialogue Systems](https://mlsanity.com/paper/2306.04357/) (2023)
- [Contrastive Speaker-Aware Learning for Multi-party Dialogue Generation with LLMs](https://mlsanity.com/paper/2503.08842/) (2025)
- [Tri-Attention: Explicit Context-Aware Attention Mechanism for Natural Language Processing](https://mlsanity.com/paper/2211.02899/) (2022)
- [A Bi-Encoder LSTM Model For Learning Unstructured Dialogs](https://mlsanity.com/paper/2104.12269/) (2021)
- [Advances in Multi-turn Dialogue Comprehension: A Survey](https://mlsanity.com/paper/2110.04984/) (2021)
- [Sparse and Dense Approaches for the Full-rank Retrieval of Responses for Dialogues](https://mlsanity.com/paper/2204.10558/) (2022)
- [Channel-aware Decoupling Network for Multi-turn Dialogue Comprehension](https://mlsanity.com/paper/2301.03953/) (2023)

## Abstract (arXiv)

This paper presents results of our experiments for the next utterance ranking on the Ubuntu Dialog Corpus -- the largest publicly available multi-turn dialog corpus. First, we use an in-house implementation of previously reported models to do an independent evaluation using the same data. Second, we evaluate the performances of various LSTMs, Bi-LSTMs and CNNs on the dataset. Third, we create an ensemble by averaging predictions of multiple models. The ensemble further improves the performance and it achieves a state-of-the-art result for the next utterance ranking on this dataset. Finally, we discuss our future plans using this corpus.