Conversational search (CS) requires a complex software engineering pipeline that integrates query reformulation, ranking, and response generation. CS researchers currently face two barriers: the lack of a unified framework for efficiently sharing contributions with the community, and the difficulty of deploying end-to-end prototypes needed for user evaluation. We introduce Orcheo, an open-source platform designed to bridge this gap. Orcheo offers three key advantages: (i)A modular architecture promotes component reuse through single-file node modules, facilitating sharing and reproducibility in CS research; (ii)Production-ready infrastructure bridges the prototype-to-system gap via dual execution modes, secure credential management, and execution telemetry, with built-in AI coding support that lowers the learning curve; (iii)Starter-kit assets include 45+ off-the-shelf components for query understanding, ranking, and response generation, enabling the rapid bootstrapping of complete CS pipelines. We describe the framework architecture and validate Orcheo's utility through case studies that highlight modularity and ease of use. Orcheo is released as open source under the MIT License at https://github.com/AI-Colleagues/orcheo.

Engagingness is an important measurement for evaluating open-domain conversational systems. The standard approach to evaluating dialogue engagingness is by measuring conversation turns per session (CTPS), which implies that the dialogue length is the main predictor of the user engagement with a dialogue system. The main limitation of CTPS is that it can only be measured at the session level, i.e., once the dialogue is over. But a dialogue system has to continuously monitor user engagement throughout the dialogue session as well. Existing approaches to measuring turn-level engagingness require human annotations for training. We pioneer an alternative approach, Weakly Supervised Engagingness Evaluator (WeSEE), which uses the remaining depth for each turn as a heuristic weak label for engagingness. Weakly Supervised Engagingness Evaluator (WeSEE) does not require human annotations and also relates closely to CTPS, thus serving as a good learning proxy for this metric. We show that WeSEE achieves the new state-of-the-art results on the Fine-grained Evaluation of Dialog dataset (0.38 Spearman correlation coefficient) and the DailyDialog dataset (0.62 Spearman correlation coefficient).

Sequence-to-Sequence (Seq2Seq) models have achieved encouraging performance on the dialogue response generation task. However, existing Seq2Seq-based response generation methods suffer from a low-diversity problem: they frequently generate generic responses, which make the conversation less interesting. In this paper, we address the low-diversity problem by investigating its connection with model over-confidence reflected in predicted distributions. Specifically, we first analyze the influence of the commonly used Cross-Entropy (CE) loss function, and find that the CE loss function prefers high-frequency tokens, which results in low-diversity responses. We then propose a Frequency-Aware Cross-Entropy (FACE) loss function that improves over the CE loss function by incorporating a weighting mechanism conditioned on token frequency. Extensive experiments on benchmark datasets show that the FACE loss function is able to substantially improve the diversity of existing state-of-the-art Seq2Seq response generation methods, in terms of both automatic and human evaluations.

Structured support vector machine (SSVM) based methods have demonstrated encouraging performance in recent object tracking benchmarks. However, the complex and expensive optimization limits their deployment in real-world applications. In this paper, we present a simple yet efficient dual linear SSVM (DLSSVM) algorithm to enable fast learning and execution during tracking. By analyzing the dual variables, we propose a primal classifier update formula where the learning step size is computed in closed form. This online learning method significantly improves the robustness of the proposed linear SSVM with lower computational cost. Second, we approximate the intersection kernel for feature representations with an explicit feature map to further improve tracking performance. Finally, we extend the proposed DLSSVM tracker with multi-scale estimation to address the "drift" problem. Experimental results on large benchmark datasets with 50 and 100 video sequences show that the proposed DLSSVM tracking algorithm achieves state-of-the-art performance.