Addressing the issues of who saying what to whom in multi-party conversations
(MPCs) has recently attracted a lot of research attention. However, existing
methods on MPC understanding typically embed interlocutors and utterances into
sequential information flows, or utilize only the superficial of inherent graph
structures in MPCs. To this end, we present a plug-and-play and lightweight
method named graph-induced fine-tuning (GIFT) which can adapt various
Transformer-based pre-trained language models (PLMs) for universal MPC
understanding. In detail, the full and equivalent connections among utterances
in regular Transformer ignore the sparse but distinctive dependency of an
utterance on another in MPCs. To distinguish different relationships between
utterances, four types of edges are designed to integrate graph-induced signals
into attention mechanisms to refine PLMs originally designed for processing
sequential texts. We evaluate GIFT by implementing it into three PLMs, and test
the performance on three downstream tasks including addressee recognition,
speaker identification and response selection. Experimental results show that
GIFT can significantly improve the performance of three PLMs on three
downstream tasks and two benchmarks with only 4 additional parameters per
encoding layer, achieving new state-of-the-art performance on MPC
understanding.

通过设计四种边将图诱导信号引入注意力机制，我们提出了一种名为图诱导微调 (GIFT) 的轻量级方法，可用于多方对话的普适性理解。通过将其应用到三个预训练的语言模型中，我们发现 GIFT 可以在三项下游任务中显着提高模型性能，仅每层编码增加 4 个参数，在多方对话理解领域实现了最新的最佳性能。