Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval最新文献

Improving Video Retrieval by Adaptive Margin 基于自适应边界的视频检索改进

Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval Pub Date : 2021-07-11 DOI: 10.1145/3404835.3462927

Feng He, Qi Wang, Zhifan Feng, Wenbin Jiang, Yajuan Lü, Yong Zhu, Xiao Tan

{"title":"Improving Video Retrieval by Adaptive Margin","authors":"Feng He, Qi Wang, Zhifan Feng, Wenbin Jiang, Yajuan Lü, Yong Zhu, Xiao Tan","doi":"10.1145/3404835.3462927","DOIUrl":"https://doi.org/10.1145/3404835.3462927","url":null,"abstract":"Video retrieval is becoming increasingly important owing to the rapid emergence of videos on the Internet. The dominant paradigm for video retrieval learns video-text representations by pushing the distance between the similarity of positive pairs and that of negative pairs apart from a fixed margin. However, negative pairs used for training are sampled randomly, which indicates that the semantics between negative pairs may be related or even equivalent, while most methods still enforce dissimilar representations to decrease their similarity. This phenomenon leads to inaccurate supervision and poor performance in learning video-text representations. While most video retrieval methods overlook that phenomenon, we propose an adaptive margin changed with the distance between positive and negative pairs to solve the aforementioned issue. First, we design the calculation framework of the adaptive margin, including the method of distance measurement and the function between the distance and the margin. Then, we explore a novel implementation called \"Cross-Modal Generalized Self-Distillation\" (CMGSD), which can be built on the top of most video retrieval models with few modifications. Notably, CMGSD adds few computational overheads at train time and adds no computational overhead at test time. Experimental results on three widely used datasets demonstrate that the proposed method can yield significantly better performance than the corresponding backbone model, and it outperforms state-of-the-art methods by a large margin.","PeriodicalId":208104,"journal":{"name":"Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115320850","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 13

ECG Data Modeling and Analyzing via Deep Representation Learning and Nonparametric Hidden Markov Models 基于深度表示学习和非参数隐马尔可夫模型的心电数据建模与分析

Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval Pub Date : 2021-07-11 DOI: 10.1145/3404835.3463044

Jiaojiao Zhu, Wentao Fan

{"title":"ECG Data Modeling and Analyzing via Deep Representation Learning and Nonparametric Hidden Markov Models","authors":"Jiaojiao Zhu, Wentao Fan","doi":"10.1145/3404835.3463044","DOIUrl":"https://doi.org/10.1145/3404835.3463044","url":null,"abstract":"In modern clinical medicine, electrocardiogram (ECG) is a common diagnosis technique of cardiovascular diseases. The purpose of this paper is to propose a novel model-based clustering approach for analyzing ECG data. Our approach is composed of two modules: representation learning and ECG data clustering. In the module of representation learning, a deep generative model referred to as the hyperspherical variational recurrent autoencoder (HVRAE) is developed to extract the representation of observed ECG data, based on the variational autoencoder (VAE) with long short-term memory (LSTM) networks. In the module of ECG data clustering, we develop a nonparametric hidden Markov model (NHMM) based on Dirichlet process in which the number of hidden states is inferred automatically during the learning process. Moreover, the emission density of each hidden state of our NHMM follows a mixture of von Mises-Fisher (VMF) distributions which have better capability for modeling ECG representations than other commonly used distributions (such as the Gaussian distribution). To learn the proposed VMF-based NHMM, we theoretically develop an effective learning algorithm based on variational Bayes. The merits of our model-based clustering approach for analyzing ECG data are verified through experiments on publicly available ECG data sets.","PeriodicalId":208104,"journal":{"name":"Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115490547","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

Morphologically Annotated Amharic Text Corpora 形态注释阿姆哈拉语文本语料库

Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval Pub Date : 2021-07-11 DOI: 10.1145/3404835.3463237

Tilahun Yeshambel, J. Mothe, Yaregal Assabie

引用次数: 3

Long-Tail Hashing 长尾哈希

Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval Pub Date : 2021-07-11 DOI: 10.1145/3404835.3462888

Yong Chen, Y. Hou, Shuguang Leng, Qing Zhang, Zhouchen Lin, Dell Zhang

{"title":"Long-Tail Hashing","authors":"Yong Chen, Y. Hou, Shuguang Leng, Qing Zhang, Zhouchen Lin, Dell Zhang","doi":"10.1145/3404835.3462888","DOIUrl":"https://doi.org/10.1145/3404835.3462888","url":null,"abstract":"Hashing, which represents data items as compact binary codes, has been becoming a more and more popular technique, e.g., for large-scale image retrieval, owing to its super fast search speed as well as its extremely economical memory consumption. However, existing hashing methods all try to learn binary codes from artificially balanced datasets which are not commonly available in real-world scenarios. In this paper, we propose Long-Tail Hashing Network (LTHNet), a novel two-stage deep hashing approach that addresses the problem of learning to hash for more realistic datasets where the data labels roughly exhibit a long-tail distribution. Specifically, the first stage is to learn relaxed embeddings of the given dataset with its long-tail characteristic taken into account via an end-to-end deep neural network; the second stage is to binarize those obtained embeddings. A critical part of LTHNet is its dynamic meta-embedding module extended with a determinantal point process which can adaptively realize visual knowledge transfer between head and tail classes, and thus enrich image representations for hashing. Our experiments have shown that LTHNet achieves dramatic performance improvements over all state-of-the-art competitors on long-tail datasets, with no or little sacrifice on balanced datasets. Further analyses reveal that while to our surprise directly manipulating class weights in the loss function has little effect, the extended dynamic meta-embedding module, the usage of cross-entropy loss instead of square loss, and the relatively small batch-size for training all contribute to LTHNet's success.","PeriodicalId":208104,"journal":{"name":"Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval","volume":"2003 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127316653","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 5

Files of a Feather Flock Together? Measuring and Modeling How Users Perceive File Similarity in Cloud Storage 一根羽毛的文件聚集在一起?测量和建模用户如何感知云存储中的文件相似度

Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval Pub Date : 2021-07-11 DOI: 10.1145/3404835.3462845

Will Brackenbury, Galen Harrison, K. Chard, Aaron J. Elmore, Blase Ur

{"title":"Files of a Feather Flock Together? Measuring and Modeling How Users Perceive File Similarity in Cloud Storage","authors":"Will Brackenbury, Galen Harrison, K. Chard, Aaron J. Elmore, Blase Ur","doi":"10.1145/3404835.3462845","DOIUrl":"https://doi.org/10.1145/3404835.3462845","url":null,"abstract":"Prior work suggests that users conceptualize the organization of personal collections of digital files through the lens of similarity. However, it is unclear to what degree similar files are actually located near one another (e.g., in the same directory) in actual file collections, or whether leveraging file similarity can improve information retrieval and organization for disorganized collections of files. To this end, we conducted an online study combining automated analysis of 50 Google Drive and Dropbox users' cloud accounts with a survey asking about pairs of files from those accounts. We found that many files located in different parts of file hierarchies were similar in how they were perceived by participants, as well as in their algorithmically extractable features. Participants often wished to co-manage similar files (e.g., deleting one file implied deleting the other file) even if they were far apart in the file hierarchy. To further understand this relationship, we built regression models, finding several algorithmically extractable file features to be predictive of human perceptions of file similarity and desired file co-management. Our findings pave the way for leveraging file similarity to automatically recommend access, move, or delete operations based on users' prior interactions with similar files.","PeriodicalId":208104,"journal":{"name":"Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127537647","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 4

HONto: A Bottom-Up Knowledge Base from Textbooks for Recommending Contextually Relevant Documents HONto:从教科书中自底向上的知识库，用于推荐上下文相关的文档

Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval Pub Date : 2021-07-11 DOI: 10.1145/3404835.3463267

Sabine Wehnert

{"title":"HONto: A Bottom-Up Knowledge Base from Textbooks for Recommending Contextually Relevant Documents","authors":"Sabine Wehnert","doi":"10.1145/3404835.3463267","DOIUrl":"https://doi.org/10.1145/3404835.3463267","url":null,"abstract":"This research presents a recommender system designed on the basis of a bottom-up knowledge base from textbooks. While other ontologies that are usually applied to such tasks are hand-crafted, our automated approach is a possible answer to the knowledge acquisition bottleneck. We extract concept hierarchies from section titles and use co-occurrences in book sections as evidence for possible contextual relationships between the therein mentioned entities. Motivated by a legal use case of recommending upcoming changes in law, the design is targeting three major challenges: different abstraction levels between entities of legal documents and the parliament protocols announcing norm changes, as well as engineering an explainable retrieval mechanism using the knowledge base which can additionally offer decent usability despite a high-recall requirement. Although the system is developed for a specific legal use case, there are many aspects of general applicability in the fields of recommender systems, information retrieval and information extraction, entity resolution, explainable artificial intelligence and usability. We validate selected parts of the system design also on other applications, such as educational media research.","PeriodicalId":208104,"journal":{"name":"Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127047927","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

LS-DST: Long and Sparse Dialogue State Tracking with Smart History Collector in Insurance Marketing LS-DST:基于智能历史收集器的保险营销长稀疏对话状态跟踪

Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval Pub Date : 2021-07-11 DOI: 10.1145/3404835.3463058

Liqiang Song, Mengqiu Yao, Ye Bi, Zhenyu Wu, Jianming Wang, Jing Xiao, Juan Wen, Xin Yu

{"title":"LS-DST: Long and Sparse Dialogue State Tracking with Smart History Collector in Insurance Marketing","authors":"Liqiang Song, Mengqiu Yao, Ye Bi, Zhenyu Wu, Jianming Wang, Jing Xiao, Juan Wen, Xin Yu","doi":"10.1145/3404835.3463058","DOIUrl":"https://doi.org/10.1145/3404835.3463058","url":null,"abstract":"Different from traditional task-oriented and open-domain dialogue systems, insurance agents aim to engage customers for helping them satisfy specific demands and emotional companionship. As a result, customer-to-agent dialogues are usually very long, and many turns of them are pure chit-chat without any useful marketing clues. This brings challenges to dialogue state tracking task in insurance marketing. To deal with these long and sparse dialogues, we propose a new dialogue state tracking architecture containing three components: dialogue encoder, Smart History Collector (SHC) and dialogue state classifier. SHC, a deliberately designed memory network, effectively selects relevant dialogue history via slot-attention, and then updates dialogue history memory. With SHC, our model is able to keep track of the vital information and filter out pure chit-chat. Experimental results demonstrate that our proposed LS-DST significantly outperforms the state-of-the-art baselines on real insurance dialogue dataset.","PeriodicalId":208104,"journal":{"name":"Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115216914","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 3

Fast Attention-based Learning-To-Rank Model for Structured Map Search 基于快速注意的结构化地图搜索排序学习模型

Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval Pub Date : 2021-07-11 DOI: 10.1145/3404835.3462904

Chiqun Zhang, Michael R. Evans, Max Lepikhin, Dragomir Yankov

{"title":"Fast Attention-based Learning-To-Rank Model for Structured Map Search","authors":"Chiqun Zhang, Michael R. Evans, Max Lepikhin, Dragomir Yankov","doi":"10.1145/3404835.3462904","DOIUrl":"https://doi.org/10.1145/3404835.3462904","url":null,"abstract":"Recent works show that Transformer-based learning-to-rank (LTR) approaches can outperform previous well-established ranking methods, such as gradient-boosted decision trees (GBDT), on document and passage re-ranking problems. A common assumption in these works is that the query and the result documents are comprised of purely textual information without explicit structure. In map search, the relevance of results is determined based on rich heterogeneous features - textual features derived from the query and the results, geospatial features such as proximity of a result to the user, structured features reflecting the address format of the result, and the perceived structure of the query. In this work, we propose a novel deep neural network LTR architecture, capable of seamlessly handling heterogeneous inputs, similar to GBDT-based methods. At the same time, unlike GBDT, the architecture does not require human input via (numerous) carefully-crafted features. Instead, features are inferred through a self-attention mechanism. Our model implements two lightweight attention layers optimized for ranking: the first layer computes query-result similarities, the second implements listwise ranking inference. We perform evaluation on several single language and one multilingual dataset. Our model outperforms by a wide margin other Transformer-based ranking architectures and has equal or better performance than GBDT models. Equally important, runtime inference is orders of magnitude faster than other Transformer architectures, significantly reducing hardware serving costs. The model is a low-cost alternative suitable to power ranking in industrial map search engines across a variety of languages and markets.","PeriodicalId":208104,"journal":{"name":"Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval","volume":"894 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116386360","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

Automatic Form Filling with Form-BERT 使用Form- bert自动填写表格

Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval Pub Date : 2021-07-11 DOI: 10.1145/3404835.3463063

Gilad Fuchs, Haggai Roitman, Matan Mandelbrod

引用次数: 5

Follow the Prophet: Accurate Online Conversion Rate Prediction in the Face of Delayed Feedback 跟随先知:面对延迟反馈的准确在线转化率预测

Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval Pub Date : 2021-07-11 DOI: 10.1145/3404835.3463045

Haoming Li, Feiyang Pan, Xiang Ao, Zhao Yang, Min Lu, Junwei Pan, Dapeng Liu, Lei Xiao, Qing He

{"title":"Follow the Prophet: Accurate Online Conversion Rate Prediction in the Face of Delayed Feedback","authors":"Haoming Li, Feiyang Pan, Xiang Ao, Zhao Yang, Min Lu, Junwei Pan, Dapeng Liu, Lei Xiao, Qing He","doi":"10.1145/3404835.3463045","DOIUrl":"https://doi.org/10.1145/3404835.3463045","url":null,"abstract":"The delayed feedback problem is one of the imperative challenges in online advertising, which is caused by the highly diversified feedback delay of a conversion varying from a few minutes to several days. It is hard to design an appropriate online learning system under these non-identical delay for different types of ads and users. In this paper, we propose to tackle the delayed feedback problem in online advertising by \"Following the Prophet\" (FTP for short). The key insight is that, if the feedback came instantly for all the logged samples, we could get a model without delayed feedback, namely the \"prophet\". Although the prophet cannot be obtained during online learning, we show that we could predict the prophet's predictions by an aggregation policy on top of a set of multi-task predictions, where each task captures the feedback patterns of different periods. We propose the objective and optimization approach for the policy, and use the logged data to imitate the prophet. Extensive experiments on three real-world advertising datasets show that our method outperforms the previous state-of-the-art baselines.","PeriodicalId":208104,"journal":{"name":"Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval","volume":"150 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122928273","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 8