In the context of a voice assistant system, steering refers to the phenomenon
in which a user issues a follow-up command attempting to direct or clarify a
previous turn. We propose STEER, a steering detection model that predicts
whether a follow-up turn is a user's attempt to steer the previous command.
Constructing a training dataset for steering use cases poses challenges due to
the cold-start problem. To overcome this, we developed heuristic rules to
sample opt-in usage data, approximating positive and negative samples without
any annotation. Our experimental results show promising performance in
identifying steering intent, with over 95% accuracy on our sampled data.
Moreover, STEER, in conjunction with our sampling strategy, aligns effectively
with real-world steering scenarios, as evidenced by its strong zero-shot
performance on a human-graded evaluation set. In addition to relying solely on
user transcripts as input, we introduce STEER+, an enhanced version of the
model. STEER+ utilizes a semantic parse tree to provide more context on
out-of-vocabulary words, such as named entities that often occur at the
sentence boundary. This further improves model performance, reducing error rate
in domains where entities frequently appear, such as messaging. Lastly, we
present a data analysis that highlights the improvement in user experience when
voice assistants support steering use cases.

在语音助手系统中，steering 是指用户发出后续指令以引导或澄清上一轮对话的现象。我们提出了一种名为 STEER 的 steering 检测模型，能够预测后续指令是否是用户试图引导上一个指令的意图。我们通过开发启发式规则来构建训练数据集，以应对 steering 用例的冷启动问题，并且在我们的采样数据上取得了超过 95% 的准确率。此外，我们引入了 STEER+，它在用户转录的基础上利用语义解析树来提供更多上下文信息，特别是对于通常出现在句子边界的命名实体等生词。我们还展示了一项数据分析，突出了语音助手支持 steering 用例时用户体验的改善。

STEER: 语义转向扩展识别对话助理

STEER: Semantic Turn Extension-Expansion Recognition for Voice  Assistants

Predictions in the social world generally influence the target of prediction,
a phenomenon known as performativity. Self-fulfilling and self-negating
predictions are examples of performativity. Of fundamental importance to
economics, finance, and the social sciences, the notion has been absent from
the development of machine learning. In machine learning applications,
performativity often surfaces as distribution shift. A predictive model
deployed on a digital platform, for example, influences consumption and thereby
changes the data-generating distribution. We survey the recently founded area
of performative prediction that provides a definition and conceptual framework
to study performativity in machine learning. A consequence of performative
prediction is a natural equilibrium notion that gives rise to new optimization
challenges. Another consequence is a distinction between learning and steering,
two mechanisms at play in performative prediction. The notion of steering is in
turn intimately related to questions of power in digital markets. We review the
notion of performative power that gives an answer to the question how much a
platform can steer participants through its predictions. We end on a discussion
of future directions, such as the role that performativity plays in contesting
algorithmic systems.

社会世界中的预测通常会影响预测的目标，这称为表现性，而表现性预测又可分为自我实现和自我否定的预测。在机器学习的发展中，表现性这个概念在经济学、金融学和社会科学中具有基本重要性，但在机器学习应用中往往表现为分布转移。我们对最近建立的表现性预测领域进行了调查，提供了定义和概念框架，以研究机器学习中的表现性。表现性预测的一个结果是自然均衡概念的出现，从而产生了新的优化挑战。另一个结果是学习和操纵之间的区别，这是表现性预测中发挥作用的两种机制。操纵的概念与数字市场中的权力问题密切相关。我们审查了表现性权力的概念，给出了这样一个答案：一个平台通过其预测有多大程度上能够操纵参与者。最后，我们讨论了未来的方向，比如表现性对抗算法系统中的作用。

行为预测：回顾与展望

Performative Prediction: Past and Future

The concept of steering was introduced by Schrodinger in 1935 as a
generalization of the EPR paradox for arbitrary pure bipartite entangled states
and arbitrary measurements by one party. Until now, it has never been
rigorously defined, so it has not been known (for example) what mixed states
are steerable (that is, can be used to exhibit steering). We provide an
operational definition, from which we prove (by considering Werner states and
Isotropic states) that steerable states are a strict subset of the entangled
states, and a strict superset of the states that can exhibit Bell-nonlocality.
For arbitrary bipartite Gaussian states we derive a linear matrix inequality
that decides the question of steerability via Gaussian measurements, and we
relate this to the original EPR paradox.

提出了操作性定义，在 Werner 状态和 Isotropic 状态上证明了可操纵状态是纠缠态的一个严格子集和能够展示 Bell - 本地性的状态的一个严格超集。对于任意双部分高斯态，我们推导出一个线性矩阵不等式，通过高斯测量来决定是否可操作，并将其与 EPR 佯谬联系起来。