Discourse analysis is an important task because it models intrinsic semantic
structures between sentences in a document. Discourse markers are natural
representations of discourse in our daily language. One challenge is that the
markers as well as pre-defined and human-labeled discourse relations can be
ambiguous when describing the semantics between sentences. We believe that a
better approach is to use a contextual-dependent distribution over the markers
to express discourse information. In this work, we propose to learn a
Distributed Marker Representation (DMR) by utilizing the (potentially)
unlimited discourse marker data with a latent discourse sense, thereby bridging
markers with sentence pairs. Such representations can be learned automatically
from data without supervision, and in turn provide insights into the data
itself. Experiments show the SOTA performance of our DMR on the implicit
discourse relation recognition task and strong interpretability. Our method
also offers a valuable tool to understand complex ambiguity and entanglement
among discourse markers and manually defined discourse relations.

通过学习分布式标记表示以及潜在的语篇感，实现了对句子对之间的标记和语段信息的联系，具备自动学习和解释性强的特点，并在隐式语篇关系识别任务中达到了 SOTA 效果。