Synthetic data is widely adopted in embedding models to ensure diversity in training data distributions across dimensions such as difficulty, length, and language. However, existing prompt-based synthesis methods struggle to capture domain-specific data distributions, particularly in data-scarce domains, and often overlook fine-grained relevance diversity. In this paper, we present a Chinese short video dataset with 4-level relevance annotations, filling a critical resource void. Further, we propose a semi-supervised synthetic data pipeline where two collaboratively trained models generate domain-adaptive short video data with controllable relevance labels. Our method enhances relevance-level diversity by synthesizing samples for underrepresented intermediate relevance labels, resulting in a more balanced and semantically rich training data set. Extensive offline experiments show that the embedding model trained on our synthesized data outperforms those using data generated based on prompting or vanilla supervised fine-tuning(SFT). Moreover, we demonstrate that incorporating more diverse fine-grained relevance levels in training data enhances the model's sensitivity to subtle semantic distinctions, highlighting the value of fine-grained relevance supervision in embedding learning. In the search enhanced recommendation pipeline of Douyin's dual-column scenario, through online A/B testing, the proposed model increased click-through rate(CTR) by 1.45%, raised the proportion of Strong Relevance Ratio (SRR) by 4.9%, and improved the Image User Penetration Rate (IUPR) by 0.1054%.

Breast cancer, the predominant malignancy among women, is characterized by significant heterogeneity, leading to the emergence of distinct molecular subtypes. Accurate differentiation of these molecular subtypes holds paramount clinical significance, owing to substantial variations in prognosis, therapeutic strategies, and survival outcomes. In this study, we propose a cross-sequence joint representation and hypergraph convolution network (CORONet) for classifying molecular subtypes of breast cancer using incomplete DCE-MRI. Specifically, we first build a cross-sequence joint representation (COR) module to integrate image imputation and feature representation into a unified framework, encouraging effective feature extraction for subsequent classification. Then, we fuse multiple COR features and applied feature selection to reduce the redundant information between sequences. Finally, we deploy hypergraph structures to model high-order correlation among different subjects and extracted high-level semantic features by hypergraph convolutions for molecular subtyping. Extensive experiments on incomplete DCE-MRIs of 395 patients from the TCIA repository showed a significant improvement of our CORONet over state of the arts, with the area under the curve (AUC) of 0.891 and 0.903 for luminal and triple-negative (TN) subtype prediction, respectively. Similar advantages of CORONet were also confirmed in partial complete DCE-MRIs of 144 patients, achieving an AUC of 0.858 and 0.832 for predicting luminal and TN subtypes of breast cancer, respectively. Nevertheless, both of these values were lower compared to the scenario where DCE-MRIs from all 395 patients were utilized. Our study contributes to the precise molecular subtyping using incomplete multi-sequence DCE-MRI, thereby offering promising prospects for future risk stratification of breast cancer patients.

The NOESIS II challenge, as the Track 2 in the Eighth Dialogue System Technology Challenge (DSTC 8), is the extension of Track 1 in DSTC 7. Three new elements are incorporated into the extended track, i.e., dialogue with multiple participants, dialogue success, and dialogue disentanglement. These are vital for the creation of a deployed task-oriented dialogue system. This track is divided into four subtasks, the first two of which are evaluated in the form of response selection and the last two focus on dialogue analysis. This paper describes our methods developed for these four subtasks, which all employ deep contextualized utterance representations to make models aware of contextual information and to keep the intrinsic property of multi-turn dialogue systems. In the released evaluation results of Track 2 in DSTC 8, our proposed methods ranked fourth in subtask 1, third in subtask 2, and first in subtask 3 and subtask 4 respectively. In addition to the challenge tasks, we also compare our proposed methods with previous ones on public benchmark datasets. Experimental results show that our proposed methods outperform existing ones by large margins and achieve new state-of-the-art performances on multi-turn response selection and dialogue disentanglement.

In this paper, we study the problem of employing pre-trained language models for multi-turn response selection in retrieval-based chatbots. A new model, named Speaker-Aware BERT (SA-BERT), is proposed in order to make the model aware of the speaker change information, which is an important and intrinsic property of multi-turn dialogues. Furthermore, a speaker-aware disentanglement strategy is proposed to tackle the entangled dialogues. This strategy selects a small number of most important utterances as the filtered context according to the speakers' information in them. Finally, domain adaptation is performed to incorporate the in-domain knowledge into pre-trained language models. Experiments on five public datasets show that our proposed model outperforms the present models on all metrics by large margins and achieves new state-of-the-art performances for multi-turn response selection.

Head pose and facial feature detection are important for face analysis. However, many studies reported good results in constrained environment, the performance could be decreased due to the high variations in facial appearance, poses, illumination, occlusion, expression and make-up. In this paper, we propose a hierarchical regression approach, Dirichlet-tree enhanced random forests (D-RF) for face analysis in unconstrained environment. D-RF introduces Dirichlet-tree probabilistic model into regression RF framework in the hierarchical way to achieve the efficiency and robustness. To eliminate noise influence of unconstrained environment, facial patches extracted from face area are classified as positive or negative facial patches, only positive facial patches are used for face analysis. The proposed hierarchical D-RF works in two iterative procedures. First, coarse head pose is estimated to constrain the facial features detection, then the head pose is updated based on the estimated facial features. Second, the facial feature localization is refined based on the updated head pose. In order to further improve the efficiency and robustness, multiple probabilitic models are learned in leaves of the D-RF, i.e. the patch’s classification, the head pose probabilities, the locations of facial points and face deformation models (FDM). Moreover, our algorithm takes a composite weight voting method, where each patch extracted from the image can directly cast a vote for the head pose or each of the facial features. Extensive experiments have been done with different publicly available databases. The experimental results demonstrate that the proposed approach is robust and efficient for head pose and facial feature detection.