{"title":"Session details: Session 5A: Deep Learning","authors":"Berthier Ribeiro-Neto","doi":"10.1145/3255927","DOIUrl":"https://doi.org/10.1145/3255927","url":null,"abstract":"","PeriodicalId":297035,"journal":{"name":"Proceedings of the 38th International ACM SIGIR Conference on Research and Development in Information Retrieval","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-08-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125120979","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}
Many generative language and relevance models assume conditional independence between the likelihood of observing individual terms. This assumption is obviously naive, but also hard to replace or relax. There are only very few term pairs that actually show significant conditional dependencies while the vast majority of co-located terms has no implications on the document's topical nature or relevance towards a given topic. It is exactly this situation that we capture in a formal framework: A limited number of meaningful dependencies in a system of largely independent observations. Making use of the formal copula framework, we describe the strength of causal dependency in terms of a number of established term co-occurrence metrics. Our experiments based on the well known ClueWeb'12 corpus and TREC 2013 topics indicate significant performance gains in terms of retrieval performance when we formally account for the dependency structure underlying pieces of natural language text.
{"title":"Modelling Term Dependence with Copulas","authors":"Carsten Eickhoff, A. D. Vries, Thomas Hofmann","doi":"10.1145/2766462.2767831","DOIUrl":"https://doi.org/10.1145/2766462.2767831","url":null,"abstract":"Many generative language and relevance models assume conditional independence between the likelihood of observing individual terms. This assumption is obviously naive, but also hard to replace or relax. There are only very few term pairs that actually show significant conditional dependencies while the vast majority of co-located terms has no implications on the document's topical nature or relevance towards a given topic. It is exactly this situation that we capture in a formal framework: A limited number of meaningful dependencies in a system of largely independent observations. Making use of the formal copula framework, we describe the strength of causal dependency in terms of a number of established term co-occurrence metrics. Our experiments based on the well known ClueWeb'12 corpus and TREC 2013 topics indicate significant performance gains in terms of retrieval performance when we formally account for the dependency structure underlying pieces of natural language text.","PeriodicalId":297035,"journal":{"name":"Proceedings of the 38th International ACM SIGIR Conference on Research and Development in Information Retrieval","volume":"141 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-08-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125223440","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}
Seyyed Hadi Hashemi, C. Clarke, Adriel Dean-Hall, J. Kamps, Julia Kiseleva
Creating test collections for modern search tasks is increasingly more challenging due to the growing scale and dynamic nature of content, and need for richer contextualization of the statements of request. To address these issues, the TREC Contextual Suggestion Track explored an open test collection, where participants were allowed to submit any web page as a result for a personalized venue recommendation task. This prompts the question on the reusability of the resulting test collection: How does the open nature affect the pooling process? Can participants reliably evaluate variant runs with the resulting qrels? Can other teams evaluate new runs reliably? In short, does the set of pooled and judged documents effectively produce a post hoc test collection? Our main findings are the following: First, while there is a strongly significant rank correlation, the effect of pooling is notable and results in underestimation of performance, implying the evaluation of non-pooled systems should be done with great care. Second, we extensively analyze impacts of open corpus on the fraction of judged documents, explaining how low recall affects the reusability, and how the personalization and low pooling depth aggravate that problem. Third, we outline a potential solution by deriving a fixed corpus from open web submissions.
{"title":"On the Reusability of Open Test Collections","authors":"Seyyed Hadi Hashemi, C. Clarke, Adriel Dean-Hall, J. Kamps, Julia Kiseleva","doi":"10.1145/2766462.2767788","DOIUrl":"https://doi.org/10.1145/2766462.2767788","url":null,"abstract":"Creating test collections for modern search tasks is increasingly more challenging due to the growing scale and dynamic nature of content, and need for richer contextualization of the statements of request. To address these issues, the TREC Contextual Suggestion Track explored an open test collection, where participants were allowed to submit any web page as a result for a personalized venue recommendation task. This prompts the question on the reusability of the resulting test collection: How does the open nature affect the pooling process? Can participants reliably evaluate variant runs with the resulting qrels? Can other teams evaluate new runs reliably? In short, does the set of pooled and judged documents effectively produce a post hoc test collection? Our main findings are the following: First, while there is a strongly significant rank correlation, the effect of pooling is notable and results in underestimation of performance, implying the evaluation of non-pooled systems should be done with great care. Second, we extensively analyze impacts of open corpus on the fraction of judged documents, explaining how low recall affects the reusability, and how the personalization and low pooling depth aggravate that problem. Third, we outline a potential solution by deriving a fixed corpus from open web submissions.","PeriodicalId":297035,"journal":{"name":"Proceedings of the 38th International ACM SIGIR Conference on Research and Development in Information Retrieval","volume":"34 3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-08-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131151302","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}
This paper describes our deep learning system for sentiment analysis of tweets. The main contribution of this work is a new model for initializing the parameter weights of the convolutional neural network, which is crucial to train an accurate model while avoiding the need to inject any additional features. Briefly, we use an unsupervised neural language model to train initial word embeddings that are further tuned by our deep learning model on a distant supervised corpus. At a final stage, the pre-trained parameters of the network are used to initialize the model. We train the latter on the supervised training data recently made available by the official system evaluation campaign on Twitter Sentiment Analysis organized by Semeval-2015. A comparison between the results of our approach and the systems participating in the challenge on the official test sets, suggests that our model could be ranked in the first two positions in both the phrase-level subtask A (among 11 teams) and on the message-level subtask B (among 40 teams). This is an important evidence on the practical value of our solution.
{"title":"Twitter Sentiment Analysis with Deep Convolutional Neural Networks","authors":"Aliaksei Severyn, Alessandro Moschitti","doi":"10.1145/2766462.2767830","DOIUrl":"https://doi.org/10.1145/2766462.2767830","url":null,"abstract":"This paper describes our deep learning system for sentiment analysis of tweets. The main contribution of this work is a new model for initializing the parameter weights of the convolutional neural network, which is crucial to train an accurate model while avoiding the need to inject any additional features. Briefly, we use an unsupervised neural language model to train initial word embeddings that are further tuned by our deep learning model on a distant supervised corpus. At a final stage, the pre-trained parameters of the network are used to initialize the model. We train the latter on the supervised training data recently made available by the official system evaluation campaign on Twitter Sentiment Analysis organized by Semeval-2015. A comparison between the results of our approach and the systems participating in the challenge on the official test sets, suggests that our model could be ranked in the first two positions in both the phrase-level subtask A (among 11 teams) and on the message-level subtask B (among 40 teams). This is an important evidence on the practical value of our solution.","PeriodicalId":297035,"journal":{"name":"Proceedings of the 38th International ACM SIGIR Conference on Research and Development in Information Retrieval","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-08-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131484161","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}
{"title":"Session details: Session 7A: Assessing","authors":"J. Zobel","doi":"10.1145/3255934","DOIUrl":"https://doi.org/10.1145/3255934","url":null,"abstract":"","PeriodicalId":297035,"journal":{"name":"Proceedings of the 38th International ACM SIGIR Conference on Research and Development in Information Retrieval","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-08-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133327849","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}
There are many informational queries that could be answered with a text passage, thereby not requiring the searcher to access the full web document. When building manual annotations of answer passages for TREC queries, Keikha et al. [6] confirmed that many such queries can be answered with just passages. By presenting the answers directly in the search result page, user information needs will be addressed more rapidly so that reduces user interaction (click) with the search result page [3] and gives a significant positive effect on user satisfaction [2, 7]. In the context of general web search, the problem of finding answer passages has not been explored extensively. Retrieving relevant passages has been studied in TREC HARD track [1] and in INEX [5], but relevant passages are not required to contain answers. One of the tasks in the TREC genomics track [4] was to find answer passages on biomedical literature. Previous work has shown that current passage retrieval methods that focus on topical relevance are not effective at finding answers [6]. Therefore, more knowledge is required to identify answers in a document. Bernstein et al. [2] has studied an approach to extract inline direct answers for search result using paid crowdsourcing service. Such an approach, however, is expensive and not practical to be applied for all possible information needs. A fully automatic process in finding answers remains a research challenge. The aim of this thesis is to find passages in the documents that contain answers to a user's query. In this research, we proposed to use a summarization technique through taking advantage of Community Question Answering (CQA) content. In our previous work, we have shown the benefit of using social media to generate more accurate summaries of web documents [8], but this was not designed to present answer in the summary. With the high volume of questions and answers posted in CQA, we believe that there are many questions that have been previously asked in CQA that are the same as or related to actual web queries, for which their best answers can guide us to extract answers in the document. As an initial work, we proposed using term distributions extracted from best answers for top matching questions in one of leading CQA sites, Yahoo! Answers (Y!A), for answer summaries generation. An experiment was done by comparing our summaries with reference answers built in previous work [6], finding some level of success. A manuscript is prepared for this result. Next, as an extension of our work above, we were interested to see whether the documents that have better quality answer summaries should be ranked higher in the result list. A set of features are derived from answer summaries to re-rank documents in the result list. Our experiment shows that answer summaries can be used to improve state-of-the-art document ranking. The method is also shown to outperform a current re-ranking approach using comprehensive document quality features. A
有许多信息查询可以用文本段落来回答，因此不需要搜索者访问完整的web文档。Keikha等人[6]在为TREC查询构建答案段落的手动注释时，证实了许多这样的查询可以只用段落来回答。通过在搜索结果页面中直接呈现答案，可以更快地满足用户的信息需求，减少用户与搜索结果页面的交互(点击)[3]，对用户满意度有显著的正向影响[2,7]。在一般网络搜索的背景下，寻找答案段落的问题还没有得到广泛的探讨。TREC HARD track[1]和INEX[5]已经研究了检索相关文章，但相关文章不需要包含答案。TREC基因组学轨道[4]的任务之一是查找生物医学文献的答案段落。先前的研究表明，当前关注主题相关性的文章检索方法在寻找答案方面并不有效[6]。因此，需要更多的知识来识别文档中的答案。Bernstein等人[2]研究了一种使用付费众包服务提取搜索结果内联直接答案的方法。然而，这种方法代价高昂，而且不实际，不能适用于所有可能的信息需求。寻找答案的全自动过程仍然是一项研究挑战。本文的目的是在文档中找到包含用户查询答案的段落。在本研究中，我们提出了利用社区问答(CQA)内容的摘要技术。在我们之前的工作中，我们已经展示了使用社交媒体生成更准确的web文档摘要的好处[8]，但这并不是为了在摘要中给出答案。由于CQA中发布了大量的问题和答案，我们相信在CQA中有许多之前被问过的问题与实际的web查询相同或相关，它们的最佳答案可以指导我们在文档中提取答案。作为一项初步工作，我们建议使用从最佳答案中提取的术语分布来解决一个领先的CQA网站Yahoo!答案(Y!A)，用于生成答案摘要。我们做了一个实验，将我们的总结与之前工作[6]中构建的参考答案进行比较，发现了一定程度的成功。为这个结果准备了一份手稿。接下来，作为我们上述工作的延伸，我们很想知道具有更好质量的答案摘要的文档是否应该在结果列表中排名更高。从答案摘要中派生出一组特性，以便在结果列表中对文档重新排序。我们的实验表明，答案摘要可以用来提高最先进的文档排名。该方法还显示优于当前使用综合文档质量特征的重新排序方法。为此结果提交了一份手稿。在未来的工作中，我们计划对Y!的顶级匹配问题及其对应的最佳答案进行更深入的分析。以便更好地了解它们对生成的摘要和重新排序结果的好处。例如，Y!的最佳答案在不同的相关度上的结果有何不同?A，用来生成摘要。也有机会改进Y!生成答案摘要，例如通过预测Y的最佳答案的质量。A对应于查询。我们还打算结合相关的Y!当有来自Y!的问题时，在初始结果列表中添加一个页面。A，与查询匹配得很好。接下来，重要的是要考虑为没有来自CQA的相关结果的查询生成答案摘要的方法。
{"title":"Finding Answers in Web Search","authors":"E. Yulianti","doi":"10.1145/2766462.2767846","DOIUrl":"https://doi.org/10.1145/2766462.2767846","url":null,"abstract":"There are many informational queries that could be answered with a text passage, thereby not requiring the searcher to access the full web document. When building manual annotations of answer passages for TREC queries, Keikha et al. [6] confirmed that many such queries can be answered with just passages. By presenting the answers directly in the search result page, user information needs will be addressed more rapidly so that reduces user interaction (click) with the search result page [3] and gives a significant positive effect on user satisfaction [2, 7]. In the context of general web search, the problem of finding answer passages has not been explored extensively. Retrieving relevant passages has been studied in TREC HARD track [1] and in INEX [5], but relevant passages are not required to contain answers. One of the tasks in the TREC genomics track [4] was to find answer passages on biomedical literature. Previous work has shown that current passage retrieval methods that focus on topical relevance are not effective at finding answers [6]. Therefore, more knowledge is required to identify answers in a document. Bernstein et al. [2] has studied an approach to extract inline direct answers for search result using paid crowdsourcing service. Such an approach, however, is expensive and not practical to be applied for all possible information needs. A fully automatic process in finding answers remains a research challenge. The aim of this thesis is to find passages in the documents that contain answers to a user's query. In this research, we proposed to use a summarization technique through taking advantage of Community Question Answering (CQA) content. In our previous work, we have shown the benefit of using social media to generate more accurate summaries of web documents [8], but this was not designed to present answer in the summary. With the high volume of questions and answers posted in CQA, we believe that there are many questions that have been previously asked in CQA that are the same as or related to actual web queries, for which their best answers can guide us to extract answers in the document. As an initial work, we proposed using term distributions extracted from best answers for top matching questions in one of leading CQA sites, Yahoo! Answers (Y!A), for answer summaries generation. An experiment was done by comparing our summaries with reference answers built in previous work [6], finding some level of success. A manuscript is prepared for this result. Next, as an extension of our work above, we were interested to see whether the documents that have better quality answer summaries should be ranked higher in the result list. A set of features are derived from answer summaries to re-rank documents in the result list. Our experiment shows that answer summaries can be used to improve state-of-the-art document ranking. The method is also shown to outperform a current re-ranking approach using comprehensive document quality features. A ","PeriodicalId":297035,"journal":{"name":"Proceedings of the 38th International ACM SIGIR Conference on Research and Development in Information Retrieval","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-08-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133774279","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}
B-CUBED metrics have recently been adopted in the evaluation of clustering results as well as in many other related tasks. However, this family of metrics is not well adapted when datasets are unbalanced. This issue is extremely frequent in Web results, where classes are distributed following a strong unbalanced pattern. In this paper, we present a modified version of B-CUBED metrics to overcome this situation. Results in toy and real datasets indicate that the proposed adaptation correctly considers the particularities of unbalanced cases.
b - cube指标最近被用于聚类结果的评估以及许多其他相关任务。然而，当数据集不平衡时，这一系列指标不能很好地适应。这个问题在Web结果中非常常见，因为类是按照强烈的不平衡模式分布的。在本文中，我们提出了一个修改版本的B-CUBED度量来克服这种情况。在玩具和实际数据集上的结果表明，所提出的自适应方法正确地考虑了不平衡情况的特殊性。
{"title":"Adapted B-CUBED Metrics to Unbalanced Datasets","authors":"Jose G. Moreno, G. Dias","doi":"10.1145/2766462.2767836","DOIUrl":"https://doi.org/10.1145/2766462.2767836","url":null,"abstract":"B-CUBED metrics have recently been adopted in the evaluation of clustering results as well as in many other related tasks. However, this family of metrics is not well adapted when datasets are unbalanced. This issue is extremely frequent in Web results, where classes are distributed following a strong unbalanced pattern. In this paper, we present a modified version of B-CUBED metrics to overcome this situation. Results in toy and real datasets indicate that the proposed adaptation correctly considers the particularities of unbalanced cases.","PeriodicalId":297035,"journal":{"name":"Proceedings of the 38th International ACM SIGIR Conference on Research and Development in Information Retrieval","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-08-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114026371","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}
N. Spirin, Mikhail Kuznetsov, Julia Kiseleva, Yaroslav V. Spirin, Pavel A. Izhutov
Sorting tuples by an attribute value is a common search scenario and many search engines support such capabilities, e.g. price-based sorting in e-commerce, time-based sorting on a job or social media website. However, sorting purely by the attribute value might lead to poor user experience because the relevance is not taken into account. Hence, at the top of the list the users might see irrelevant results. In this paper we choose a different approach. Rather than just returning the entire list of results sorted by the attribute value, additionally we suggest doing the relevance-aware search results (post-) filtering. Following this approach, we develop a new algorithm based on the dynamic programming that directly optimizes a given search quality metric. It can be seamlessly integrated as the final step of a query processing pipeline and provides a theoretical guarantee on optimality. We conduct a comprehensive evaluation of our algorithm on synthetic data and real learning to rank data sets. Based on the experimental results, we conclude that the proposed algorithm is superior to typically used heuristics and has a clear practical value for the search and related applications.
{"title":"Relevance-aware Filtering of Tuples Sorted by an Attribute Value via Direct Optimization of Search Quality Metrics","authors":"N. Spirin, Mikhail Kuznetsov, Julia Kiseleva, Yaroslav V. Spirin, Pavel A. Izhutov","doi":"10.1145/2766462.2767822","DOIUrl":"https://doi.org/10.1145/2766462.2767822","url":null,"abstract":"Sorting tuples by an attribute value is a common search scenario and many search engines support such capabilities, e.g. price-based sorting in e-commerce, time-based sorting on a job or social media website. However, sorting purely by the attribute value might lead to poor user experience because the relevance is not taken into account. Hence, at the top of the list the users might see irrelevant results. In this paper we choose a different approach. Rather than just returning the entire list of results sorted by the attribute value, additionally we suggest doing the relevance-aware search results (post-) filtering. Following this approach, we develop a new algorithm based on the dynamic programming that directly optimizes a given search quality metric. It can be seamlessly integrated as the final step of a query processing pipeline and provides a theoretical guarantee on optimality. We conduct a comprehensive evaluation of our algorithm on synthetic data and real learning to rank data sets. Based on the experimental results, we conclude that the proposed algorithm is superior to typically used heuristics and has a clear practical value for the search and related applications.","PeriodicalId":297035,"journal":{"name":"Proceedings of the 38th International ACM SIGIR Conference on Research and Development in Information Retrieval","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-08-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115558903","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}
Effective postings list compression techniques, and the efficiency of postings list processing schemes such as WAND, have significantly improved the practical performance of ranked document retrieval using inverted indexes. Recently, suffix array-based index structures have been proposed as a complementary tool, to support phrase searching. The relative merits of these alternative approaches to ranked querying using phrase components are, however, unclear. Here we provide: (1) an overview of existing phrase indexing techniques; (2) a description of how to incorporate recent advances in list compression and processing; and (3) an empirical evaluation of state-of-the-art suffix-array and inverted file-based phrase retrieval indexes using a standard IR test collection.
{"title":"On the Cost of Phrase-Based Ranking","authors":"M. Petri, Alistair Moffat","doi":"10.1145/2766462.2767769","DOIUrl":"https://doi.org/10.1145/2766462.2767769","url":null,"abstract":"Effective postings list compression techniques, and the efficiency of postings list processing schemes such as WAND, have significantly improved the practical performance of ranked document retrieval using inverted indexes. Recently, suffix array-based index structures have been proposed as a complementary tool, to support phrase searching. The relative merits of these alternative approaches to ranked querying using phrase components are, however, unclear. Here we provide: (1) an overview of existing phrase indexing techniques; (2) a description of how to incorporate recent advances in list compression and processing; and (3) an empirical evaluation of state-of-the-art suffix-array and inverted file-based phrase retrieval indexes using a standard IR test collection.","PeriodicalId":297035,"journal":{"name":"Proceedings of the 38th International ACM SIGIR Conference on Research and Development in Information Retrieval","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-08-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123030964","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}
Xirong Li, Shuai Liao, Weiyu Lan, Xiaoyong Du, Gang Yang
Given the difficulty of acquiring labeled examples for many fine-grained visual classes, there is an increasing interest in zero-shot image tagging, aiming to tag images with novel labels that have no training examples present. Using a semantic space trained by a neural language model, the current state-of-the-art embeds both images and labels into the space, wherein cross-media similarity is computed. However, for labels of relatively low occurrence, its similarity to images and other labels can be unreliable. This paper proposes Hierarchical Semantic Embedding (HierSE), a simple model that exploits the WordNet hierarchy to improve label embedding and consequently image embedding. Moreover, we identify two good tricks, namely training the neural language model using Flickr tags instead of web documents, and using partial match instead of full match for vectorizing a WordNet node. All this lets us outperform the state-of-the-art. On a test set of over 1,500 visual object classes and 1.3 million images, the proposed model beats the current best results (18.3% versus 9.4% in hit@1).
考虑到获取许多细粒度视觉类的标记样例的困难，人们对零采样图像标记越来越感兴趣，旨在用没有训练样例的新标签标记图像。使用由神经语言模型训练的语义空间，当前最先进的技术将图像和标签嵌入到空间中，其中计算跨媒体相似性。然而，对于出现率相对较低的标签，其与图像和其他标签的相似性可能不可靠。本文提出了层次语义嵌入(HierSE)，这是一种利用WordNet层次结构来改进标签嵌入从而改进图像嵌入的简单模型。此外，我们确定了两个很好的技巧，即使用Flickr标签而不是web文档来训练神经语言模型，以及使用部分匹配而不是完全匹配来向量化WordNet节点。所有这些都让我们超越了最先进的技术。在超过1500个视觉对象类别和130万张图像的测试集上，提出的模型击败了当前的最佳结果(18.3% vs . hit@1中的9.4%)。
{"title":"Zero-shot Image Tagging by Hierarchical Semantic Embedding","authors":"Xirong Li, Shuai Liao, Weiyu Lan, Xiaoyong Du, Gang Yang","doi":"10.1145/2766462.2767773","DOIUrl":"https://doi.org/10.1145/2766462.2767773","url":null,"abstract":"Given the difficulty of acquiring labeled examples for many fine-grained visual classes, there is an increasing interest in zero-shot image tagging, aiming to tag images with novel labels that have no training examples present. Using a semantic space trained by a neural language model, the current state-of-the-art embeds both images and labels into the space, wherein cross-media similarity is computed. However, for labels of relatively low occurrence, its similarity to images and other labels can be unreliable. This paper proposes Hierarchical Semantic Embedding (HierSE), a simple model that exploits the WordNet hierarchy to improve label embedding and consequently image embedding. Moreover, we identify two good tricks, namely training the neural language model using Flickr tags instead of web documents, and using partial match instead of full match for vectorizing a WordNet node. All this lets us outperform the state-of-the-art. On a test set of over 1,500 visual object classes and 1.3 million images, the proposed model beats the current best results (18.3% versus 9.4% in hit@1).","PeriodicalId":297035,"journal":{"name":"Proceedings of the 38th International ACM SIGIR Conference on Research and Development in Information Retrieval","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-08-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123541649","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：