Zero-Shot Dialogue Disentanglement by Self-Supervised Entangled Response Selection (2110.12646v2)
Abstract: Dialogue disentanglement aims to group utterances in a long and multi-participant dialogue into threads. This is useful for discourse analysis and downstream applications such as dialogue response selection, where it can be the first step to construct a clean context/response set. Unfortunately, labeling all~\emph{reply-to} links takes quadratic effort w.r.t the number of utterances: an annotator must check all preceding utterances to identify the one to which the current utterance is a reply. In this paper, we are the first to propose a~\textbf{zero-shot} dialogue disentanglement solution. Firstly, we train a model on a multi-participant response selection dataset harvested from the web which is not annotated; we then apply the trained model to perform zero-shot dialogue disentanglement. Without any labeled data, our model can achieve a cluster F1 score of 25. We also fine-tune the model using various amounts of labeled data. Experiments show that with only 10\% of the data, we achieve nearly the same performance of using the full dataset\footnote{Code is released at \url{https://github.com/chijames/zero_shot_dialogue_disentanglement}}.
- Longformer: The long-document transformer. arXiv preprint arXiv:2004.05150.
- Model ensembling of esim and bert for dialogue response selection. DSTC8.
- Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805.
- Micha Elsner and Eugene Charniak. 2008. You talking to me? a corpus and algorithm for conversation disentanglement. In Proceedings of ACL-08: HLT, pages 834–842.
- Micha Elsner and Eugene Charniak. 2011. Disentangling chat with local coherence models. In Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, pages 1179–1189.
- Pre-trained and attention-based neural networks for building noetic task-oriented dialogue systems. arXiv preprint arXiv:2004.01940.
- Noesis ii: Predicting responses, identifying success, and managing complexity in task-oriented dialogue. In 8th Edition of the Dialog System Technology Challenges at AAAI 2019.
- Learning to disentangle interleaved conversational threads with a siamese hierarchical network and similarity ranking. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers), pages 1812–1822.
- A large-scale corpus for conversation disentanglement. arXiv preprint arXiv:1810.11118.
- Dialbert: A hierarchical pre-trained model for conversation disentanglement. arXiv preprint arXiv:2004.03760.
- Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692.
- Thread detection in dynamic text message streams. In Proceedings of the 29th annual international ACM SIGIR conference on Research and development in information retrieval, pages 35–42.
- Lidan Wang and Douglas W Oard. 2009. Context-based message expansion for disentanglement of interleaved text conversations. In Proceedings of human language technologies: The 2009 annual conference of the North American chapter of the association for computational linguistics, pages 200–208. Citeseer.
- Response selection for multi-party conversations with dynamic topic tracking. arXiv preprint arXiv:2010.07785.
- Enhancing response selection with advanced context modeling and post-training. DSTC8.
- Xlnet: Generalized autoregressive pretraining for language understanding. arXiv preprint arXiv:1906.08237.
- Tao Yu and Shafiq Joty. 2020. Online conversation disentanglement with pointer networks. arXiv preprint arXiv:2010.11080.
- Big bird: Transformers for longer sequences. arXiv preprint arXiv:2007.14062.
- Who did they respond to? conversation structure modeling using masked hierarchical transformer. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 34, pages 9741–9748.
- Ta-Chung Chi (19 papers)
- Alexander I. Rudnicky (9 papers)