EMNLP Findings2023
Symbolization, Prompt, and Classification: A Framework for Implicit Speaker Identification in Novels
Yue Chen, Tian-Wei He, Hongbin Zhou, Jia-Chen Gu, Heng Lu, Zhen-Hua Ling
Abstract
Speaker identification in novel dialogues can be widely applied to various downstream tasks, such as producing multi-speaker audiobooks and converting novels into scripts. However, existing state-of-the-art methods are limited to handling explicit narrative patterns like "Tom said, '...'", unable to thoroughly understand long-range contexts and to deal with complex cases. To this end, we propose a framework named SPC, which identifies implicit speakers in novels via symbolization, prompt, and classification. First, SPC symbolizes the mentions of candidate speakers to construct a unified label set. Then, by inserting a prompt we reformulate speaker identification as a classification task to minimize the gap between the training objectives of speaker identification and the pre-training task. Two auxiliary tasks are also introduced in SPC to enhance long-range context understanding. Experimental results show that SPC outperforms previous methods by a large margin of 4.8% accuracy on the web novel collection, which reduces 47% of speaker identification errors, and also outperforms the emerging ChatGPT. In addition, SPC is more accurate in implicit speaker identification cases that require long-range context semantic understanding.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
Lineage
Builds on3
- Training language models to follow instructions with human feedbackLong Ouyang, Jeffrey Wu, Xu Jiang, Diogo Almeida et al.NeurIPS 2022 · 24,707 citations
- Bidirectional Language Models Are Also Few-shot LearnersAjay Patel, Bryan Li, Mohammad Sadegh Rasooli, Noah Constant et al.ICLR 2023 · 18 citations
- MBTI Personality Prediction for Fictional Characters Using Movie ScriptsYisi Sang, Xiangyang Mou, Mo Yu, Dakuo Wang et al.EMNLP Findings 2022 · 8 citations
Related papers
- SIG: Speaker Identification in Literature via Prompt-Based GenerationZhenlin Su, Liyan Xu, Jin Xu, Jiangnan Li et al.AAAI 2024
- What does the sea say to the shore? A BERT based DST style approach for speaker to dialogue attribution in novelsCarolina Cuesta-Lázaro, Animesh Prasad, Trevor WoodACL 2022
- Detecting Speaker Personas from Conversational TextsJia-Chen Gu, Zhen-Hua Ling, Yu Wu, Quan Liu et al.EMNLP 2021
- Multi-level Contrastive Learning for Script-based Character UnderstandingDawei Li, Hengyuan Zhang, Yanran Li, Shiping YangEMNLP 2023 · 2 citations
- Narrate Dialogues for Better SummarizationRuochen Xu, Chenguang Zhu, Michael ZengEMNLP Findings 2022 · 5 citations
