# Structural Characterization for Dialogue Disentanglement Source: [Structural Characterization for Dialogue Disentanglement]() Collection index: [llms.txt]() Data updated: 2026-01-04T05:10:14.048Z Authors: Xinbei Ma, Zhuosheng Zhang, Hai Zhao Published: 2021-10-15T11:28:43.000Z ## Abstract Tangled multi-party dialogue contexts lead to challenges for dialogue reading comprehension, where multiple dialogue threads flow simultaneously within a common dialogue record, increasing difficulties in understanding the dialogue history for both human and machine. Previous studies mainly focus on utterance encoding methods with carefully designed features but pay inadequate attention to characteristic features of the structure of dialogues. We specially take structure factors into account and design a novel model for dialogue disentangling. Based on the fact that dialogues are constructed on successive participation and interactions between speakers, we model structural information of dialogues in two aspects: 1)speaker property that indicates whom a message is from, and 2) reference dependency that shows whom a message may refer to. The proposed method achieves new state-of-the-art on the Ubuntu IRC benchmark dataset and contributes to dialogue-related comprehension. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Dialogue Disentanglement on Ubuntu IRC (test)](): Dialogue Disentanglement; Ubuntu IRC (test); VI: 94.6. - [Dialogue Disentanglement on Ubuntu IRC (dev)](): Dialogue Disentanglement; Ubuntu IRC (dev); VI: 0.944. ## Original sources and implementation [Original paper]() [PDF]() [Implementation]()