淘系搜索算法技术团队
团队介绍：
我们负责阿里电商的核心搜索算法，包括淘宝/天猫商品搜索，店铺搜索。我们致力于研究最前沿的人工智能技术，引领深度学习，人工智能在电商搜索中的应用和创新。
近期工作：
WWW 2021: Learning a Product Relevance Model from Click-Through Data in e-Commerce.
WWW 2021: FINN: Feedback Interactive Neural Network for Intent Recommendation.
WSDM 2021: Modeling Across-Context Attention For Long-Tail Query Classification in E-commerce.
AAAI 2021: Capturing Delayed Feedback in Conversion Rate Prediction via Elapsed-Time Sampling.
SIGMOD 2020: AliCoCo: Alibaba E-commerce Cognitive Concept Net.
NIPS 2020: Neuron-level Structured Pruning using Polarization Regularizer.
CIKM 2020: Deep Time-Aware Item Evolution Network for Click-Through Rate Prediction.
WWW 2020: Adversarial Multimodal Representation Learning for Click-Through Rate Prediction.
ICDE 2020: Cross-Graph Convolution Learning for Large-Scale Text-Picture Shopping Guide in E-Commerce Search.
SIGIR 2020: ESAM: Discriminative Domain Adaptation with Non-Displayed Items to Improve Long-Tail Performance.
KDD 2020: A Dual Heterogeneous Graph Attention Network to Improve Long-Tail Performance for Shop Search in E-Commerce.
WWW 2020: Adversarial Multimodal Representation Learning for Click-Through Rate Prediction.
WWW 2019: Aggregating E-commerce Search Results from Heterogeneous Sources via Hierarchical Reinforcement Learning.
CIKM 2019: Cross-domain Attention Network with Wasserstein Regularizers for E-commerce Search.
CIKM 2019: Conceptualize and Infer User Needs in E-commerce.
KDD 2019: A Minimax Game for Instance based Selective Transfer Learning.
研究方向：
1.认知图谱：实体识别、常识关系抽取、构建商品知识图谱。
2.搜索导购：搜前和搜中的Query推荐，如Query下拉补全。
3.用户增长：通过多渠道分人群的拉新和留存，帮助搜索和手淘实现高质量用户增长。
4.召回和相关性：负责Query意图理解和多模态召回；负责搜索相关性，实现语义搜索、认知搜索。
5.搜索排序：负责超大规模点击率/成交转化率（CTR/CVR）预估，包括用户、商品表征学习，AutoML，端上智能等技术创新。
6.机制策略：负责异构多源结果融合，商家成长和顶层机制设计。
岗位要求
1.计算机、数学或统计学相关专业硕士及以上学历
2.熟悉机器学习/深度学习算法
3.在以上领域的顶级会议（SIGIR、SIGKDD、ICML、NIPS、WSDM、WWW、AAAI、CIKM、ACL、RECSYS等）或者期刊上发表过论文者更佳
4.参加过ACM或数据挖掘/机器学习类竞赛（天池大奖赛、 Kaggle）并取得好名次者更佳
猜您喜欢：
附下载 |《TensorFlow 2.0 深度学习算法实战》
附下载 | 超100篇！CVPR 2020最全GAN论文梳理汇总！
2585
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
