Proceedings of the 2019 ACM SIGIR International Conference on Theory of Information Retrieval最新文献_第3页

Neural Learning to Rank using TensorFlow Ranking: A Hands-on Tutorial 神经学习排名使用TensorFlow排名:动手教程

Proceedings of the 2019 ACM SIGIR International Conference on Theory of Information Retrieval Pub Date : 2019-09-23 DOI: 10.1145/3341981.3350530

Rama Kumar Pasumarthi, Sebastian Bruch, Michael Bendersky, Xuanhui Wang

{"title":"Neural Learning to Rank using TensorFlow Ranking: A Hands-on Tutorial","authors":"Rama Kumar Pasumarthi, Sebastian Bruch, Michael Bendersky, Xuanhui Wang","doi":"10.1145/3341981.3350530","DOIUrl":"https://doi.org/10.1145/3341981.3350530","url":null,"abstract":"A number of open source packages harnessing the power of deep learning have emerged in recent years and are under active development, including TensorFlow, PyTorch and others. Supervised learning is one of the main use cases of deep learning packages. However, compared with the comprehensive support for classification or regression in open-source deep learning packages, there is a paucity of support for ranking problems. To address this gap, we developed TensorFlow Ranking: an open-source library for training large scale learning-to-rank models using deep learning in TensorFlow. The library is flexible and highly configurable: it provides an easy-to-use API to support different scoring mechanisms, loss functions, example weights, and evaluation metrics. In this tutorial, we will combine the theoretical and the practical aspects of TF-Ranking, and will cover how TF-Ranking can be effectively employed in a variety of learning-to-rank scenarios, and demonstrate how it can handle advanced losses, scoring functions and sparse textual features. Finally, we will provide a hands-on codelab using a learning-to-rank dataset which shows how to effective incorporate sparse features for ranking.","PeriodicalId":173154,"journal":{"name":"Proceedings of the 2019 ACM SIGIR International Conference on Theory of Information Retrieval","volume":"97 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134042927","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: 2

Personal Knowledge Graphs: A Research Agenda 个人知识图谱:一个研究议程

Proceedings of the 2019 ACM SIGIR International Conference on Theory of Information Retrieval Pub Date : 2019-09-23 DOI: 10.1145/3341981.3344241

K. Balog, Tom Kenter

引用次数: 58

SADHAN: Hierarchical Attention Networks to Learn Latent Aspect Embeddings for Fake News Detection 层次注意网络学习潜在方面嵌入的假新闻检测

Proceedings of the 2019 ACM SIGIR International Conference on Theory of Information Retrieval Pub Date : 2019-09-23 DOI: 10.1145/3341981.3344229

Rahul Mishra, Vinay Setty

{"title":"SADHAN: Hierarchical Attention Networks to Learn Latent Aspect Embeddings for Fake News Detection","authors":"Rahul Mishra, Vinay Setty","doi":"10.1145/3341981.3344229","DOIUrl":"https://doi.org/10.1145/3341981.3344229","url":null,"abstract":"Recently false claims and misinformation have become rampant in the web, affecting election outcomes, societies and economies. Consequently, fact checking websites such as snopes.com and politifact.com are becoming popular. However, these websites require expert analysis which is slow and not scalable. Many recent works try to solve these challenges using machine learning models trained on a variety of features and a rich lexicon or more recently, deep neural networks to avoid feature engineering. In this paper, we propose hierarchical deep attention networks to learn embeddings for various latent aspects of news. Contrary to existing solutions which only apply word-level self-attention, our model jointly learns the latent aspect embeddings for classifying false claims by applying hierarchical attention. Using several manually annotated high quality datasets such as Politifact, Snopes and Fever we show that these learned aspect embeddings are strong predictors of false claims. We show that latent aspect embeddings learned from attention mechanisms improve the accuracy of false claim detection by up to 13.5% in terms of Macro F1 compared to a state-of-the-art attention mechanism guided by claim-text DeClarE. We also extract and visualize the evidence from the external articles which supports or disproves the claims","PeriodicalId":173154,"journal":{"name":"Proceedings of the 2019 ACM SIGIR International Conference on Theory of Information Retrieval","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128470522","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: 18

A Dataset and Baselines for e-Commerce Product Categorization 电子商务产品分类的数据集和基线

Proceedings of the 2019 ACM SIGIR International Conference on Theory of Information Retrieval Pub Date : 2019-09-23 DOI: 10.1145/3341981.3344237

Yiu-Chang Lin, Pradipto Das, A. Trotman, S. Kallumadi

引用次数: 6

SearchIE SearchIE

Proceedings of the 2019 ACM SIGIR International Conference on Theory of Information Retrieval Pub Date : 2019-09-23 DOI: 10.1145/3341981.3344248

Sheikh Muhammad Sarwar, J. Allan

引用次数: 2

Performance Prediction for Non-Factoid Question Answering 非因素问答的性能预测

Proceedings of the 2019 ACM SIGIR International Conference on Theory of Information Retrieval Pub Date : 2019-09-23 DOI: 10.1145/3341981.3344249

Helia Hashemi, Hamed Zamani, W. Bruce Croft

引用次数: 26

Why does this Entity matter?: Support Passage Retrieval for Entity Retrieval 为什么这个实体很重要?:支持实体检索的通道检索

Proceedings of the 2019 ACM SIGIR International Conference on Theory of Information Retrieval Pub Date : 2019-09-23 DOI: 10.1145/3341981.3344243

Shubham Chatterjee, Laura Dietz

引用次数: 9

Tutorial on Explainable Recommendation and Search 可解释推荐和搜索教程

Proceedings of the 2019 ACM SIGIR International Conference on Theory of Information Retrieval Pub Date : 2019-09-23 DOI: 10.1145/3341981.3353768

Yongfeng Zhang

引用次数: 4

An Analysis of the Softmax Cross Entropy Loss for Learning-to-Rank with Binary Relevance 基于二元关联的排序学习中Softmax交叉熵损失分析

Proceedings of the 2019 ACM SIGIR International Conference on Theory of Information Retrieval Pub Date : 2019-09-23 DOI: 10.1145/3341981.3344221

Sebastian Bruch, Xuanhui Wang, Michael Bendersky, Marc Najork

{"title":"An Analysis of the Softmax Cross Entropy Loss for Learning-to-Rank with Binary Relevance","authors":"Sebastian Bruch, Xuanhui Wang, Michael Bendersky, Marc Najork","doi":"10.1145/3341981.3344221","DOIUrl":"https://doi.org/10.1145/3341981.3344221","url":null,"abstract":"One of the challenges of learning-to-rank for information retrieval is that ranking metrics are not smooth and as such cannot be optimized directly with gradient descent optimization methods. This gap has given rise to a large body of research that reformulates the problem to fit into existing machine learning frameworks or defines a surrogate, ranking-appropriate loss function. One such loss is ListNet's which measures the cross entropy between a distribution over documents obtained from scores and another from ground-truth labels. This loss was designed to capture permutation probabilities and as such is considered to be only loosely related to ranking metrics. In this work, however, we show that the above statement is not entirely accurate. In fact, we establish an analytical connection between ListNet's loss and two popular ranking metrics in a learning-to-rank setup with binary relevance labels. In particular, we show that the loss bounds Mean Reciprocal Rank and Normalized Discounted Cumulative Gain. Our analysis sheds light on ListNet's behavior and explains its superior performance on binary labeled data over data with graded relevance.","PeriodicalId":173154,"journal":{"name":"Proceedings of the 2019 ACM SIGIR International Conference on Theory of Information Retrieval","volume":"77 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122839336","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: 59

Sentence Retrieval for Entity List Extraction with a Seed, Context, and Topic 具有种子、上下文和主题的实体列表提取的句子检索

Proceedings of the 2019 ACM SIGIR International Conference on Theory of Information Retrieval Pub Date : 2019-09-23 DOI: 10.1145/3341981.3344250

Sheikh Muhammad Sarwar, John Foley, Liu Yang, J. Allan

引用次数: 3