具有自我中心記憶的混合式對話

Mixed-Session Conversation with Egocentric Memory

October 3, 2024

作者: Jihyoung Jang, Taeyoung Kim, Hyounghun Kim

cs.AI

摘要

最近推出的對話系統展示了很高的可用性。然而，它們仍然無法反映現實世界中的對話情境。目前的對話系統表現出無法複製動態、連續、長期涉及多個參與者的互動的能力。這種不足是因為對於現實世界對話的兩個方面的考量有限：長期對話中的深層互動以及涉及多個參與者的對話網絡的擴展。隨著將這些方面結合的努力，我們引入了混合會話（Mixed-Session Conversation），這是一個旨在在多個對話階段中與不同合作夥伴建立對話的對話系統。我們提出了一個名為 MiSC 的新數據集來實現這個系統。MiSC 的對話情節由 6 個連續對話階段組成，每個情節中有四位演講者（一位主要演講者和三位合作夥伴）。此外，我們提出了一個新的對話模型，具有一種新穎的記憶管理機制，稱為自我中心記憶增強混合會話代理（EMMA）。EMMA 在與合作夥伴對話期間從主要演講者的角度收集和保留記憶，從而實現在後續互動中的無縫連續性。廣泛的人類評估驗證了 MiSC 中的對話展示了無縫的對話流暢性，即使每個對話階段的合作夥伴都有所變化。使用 MiSC 訓練的 EMMA 也經過評估，確保在整個對話過程中保持高度的可記憶性並且沒有矛盾。

English

Recently introduced dialogue systems have demonstrated high usability. However, they still fall short of reflecting real-world conversation scenarios. Current dialogue systems exhibit an inability to replicate the dynamic, continuous, long-term interactions involving multiple partners. This shortfall arises because there have been limited efforts to account for both aspects of real-world dialogues: deeply layered interactions over the long-term dialogue and widely expanded conversation networks involving multiple participants. As the effort to incorporate these aspects combined, we introduce Mixed-Session Conversation, a dialogue system designed to construct conversations with various partners in a multi-session dialogue setup. We propose a new dataset called MiSC to implement this system. The dialogue episodes of MiSC consist of 6 consecutive sessions, with four speakers (one main speaker and three partners) appearing in each episode. Also, we propose a new dialogue model with a novel memory management mechanism, called Egocentric Memory Enhanced Mixed-Session Conversation Agent (EMMA). EMMA collects and retains memories from the main speaker's perspective during conversations with partners, enabling seamless continuity in subsequent interactions. Extensive human evaluations validate that the dialogues in MiSC demonstrate a seamless conversational flow, even when conversation partners change in each session. EMMA trained with MiSC is also evaluated to maintain high memorability without contradiction throughout the entire conversation.