用实体表示压缩输入，让序列到序列共指消解更高效
Efficient Seq2seq Coreference Resolution Using Entity Representations
- 提取并重组实体级标记，丢弃大部分非实体内容
- 在OntoNotes上仅比基准低0.6的CoNLL F1，压缩比达1.8
- 适合对话等需逐步处理的增量场景，保持顶尖性能
序列到序列共指消解模型通过生成对应共指标签的文本，引入了新范式，无需特定任务参数。尽管性能达到新最佳，但灵活性与效率不足，尤其在对话等增量场景中表现不佳。本文提出一种压缩表示方法，通过提取和重组实体级标记，并丢弃大部分其他输入标记，提升效率。在OntoNotes数据集上，最佳模型仅比全前缀增量基线低0.6的CoNLL F1，同时实现1.8的压缩比；在标注单例提及的LitBank上，性能超过现有最佳。结果表明，在序列到序列消解器中丢弃大量标记是实现增量共指消解的可行策略。
原文摘要 · Abstract (English)
Seq2seq coreference models have introduced a new paradigm for coreference resolution by learning to generate text corresponding to coreference labels, without requiring task-specific parameters. While these models achieve new state-of-the-art performance, they do so at the cost of flexibility and efficiency. In particular, they do not efficiently handle incremental settings such as dialogue, where text must processed sequentially. We propose a compressed representation in order to improve the efficiency of these methods in incremental settings. Our method works by extracting and re-organizing entity-level tokens, and discarding the majority of other input tokens. On OntoNotes, our best model achieves just 0.6 CoNLL F1 points below a full-prefix, incremental baseline while achieving a compression ratio of 1.8. On LitBank, where singleton mentions are annotated, it passes state-of-the-art performance. Our results indicate that discarding a wide portion of tokens in seq2seq resolvers is a feasible strategy for incremental coreference resolution.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。