Socializing the Semantic Gap

Li, Xirong; Uricchio, Tiberio; Ballan, Lamberto; Bertini, Marco; Snoek, Cees G. M.; Bimbo, Alberto Del

doi:10.1145/2906152

Cited by 111 publications

(12 citation statements)

References 113 publications

(144 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…rel i (j) is an indicator function equaling 1 if the document at rank j in the returned list for the i th query is relevant and 0 otherwise. (Li et al, 2016)…”

Section: B Calculation Of Evaluation Metricsmentioning

confidence: 99%

Article Reranking by Memory-Enhanced Key Sentence Matching for Detecting Previously Fact-Checked Claims

Sheng¹,

Cao²,

Zhang³

et al. 2021

Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Confer

Self Cite

View full text Add to dashboard Cite

5469task.According to the seminal work by Shaar et al. (2020), the task is tackled by a two-stage information retrieval approach. Its typical workflow is illustrated in Figure 1(a). Given a claim as a query, in the first stage a basic searcher (e.g., BM25 Robertson and Zaragoza, 2009) searches for candidate articles from a collection of fact-checking articles (FC-articles). In the second stage, a more powerful model (e.g., BERT, Devlin et al., 2019) reranks the candidates to provide evidence for manual or automatic detection. Existing works focus on the reranking stage: Vo and Lee (2020) model the interactions between a claim and the whole candidate articles, while Shaar et al. ( 2020) extract several semantically similar sentences from FC-articles as a proxy. Nevertheless, these methods treat FCarticles as general documents and ignore characteristics of FC-articles. Figure 1(b) shows three sentences from candidate articles for the given claim. Among them, S1 is more friendly to semantic matching than S2 and S3 because the whole S1 focuses on describing its topic and does not contain tokens irrelevant to the given claim, e.g., "has spread over years" in S2. Thus, a semantic-based model does not require to have strong filtering capability. If we use only general methods on this task, the relevant S2 and S3 may be neglected while irrelevant S1 is focused. To let the model focus on key sentences (i.e., sentences as a good proxy of article-level relevance) like S2 and S3, we need to consider two characteristics of FC-articles besides semantics: C1. Claims are often quoted to describe the checked events (e.g., the underlined text in S2); C2. Event-irrelevant patterns to introduce or debunk claims are common in FC-articles (e.g., bold texts in S2 and S3).

show abstract

“…rel i (j) is an indicator function equaling 1 if the document at rank j in the returned list for the i th query is relevant and 0 otherwise. (Li et al, 2016)…”

Section: B Calculation Of Evaluation Metricsmentioning

confidence: 99%

Article Reranking by Memory-Enhanced Key Sentence Matching for Detecting Previously Fact-Checked Claims

Sheng¹,

Cao²,

Zhang³

et al. 2021

Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Confer

Self Cite

View full text Add to dashboard Cite

show abstract

“…For the most part, AIA approaches are based solely on the visual features of the image using different techniques: one of the most common approaches consists in training a classifier for each concept and obtaining the annotation results by ranking the class probability [34,35]. There are other AIA approaches that aim to improve the quality of image annotation by using the knowledge implicit in a large collection of unstructured text describing images, and are able to label images without having to train a model (Unsupervised Image Annotation approach [36][37][38]). In particular, the image annotation technique we exploited is an Unsupervised Image Annotation technique originally introduced in [39].…”

Section: Related Workmentioning

confidence: 99%

The VISIONE Video Search System: Exploiting Off-the-Shelf Text Search Engines for Large-Scale Video Retrieval

et al. 2021

View full text Add to dashboard Cite

This paper describes in detail VISIONE, a video search system that allows users to search for videos using textual keywords, the occurrence of objects and their spatial relationships, the occurrence of colors and their spatial relationships, and image similarity. These modalities can be combined together to express complex queries and meet users’ needs. The peculiarity of our approach is that we encode all information extracted from the keyframes, such as visual deep features, tags, color and object locations, using a convenient textual encoding that is indexed in a single text retrieval engine. This offers great flexibility when results corresponding to various parts of the query (visual, text and locations) need to be merged. In addition, we report an extensive analysis of the retrieval performance of the system, using the query logs generated during the Video Browser Showdown (VBS) 2019 competition. This allowed us to fine-tune the system by choosing the optimal parameters and strategies from those we tested.

show abstract

“…Search-based annotation enables the automatic annotation of images through massive image retrieval and an analysis of the network [42], [43]. With the research on and development of the Semantic Web, many research results have been achieved through the Semantic Web-based analysis of annotation technology [44], [45]. In summary, the problem of labeling a sample set remains unresolved for images of ancient books.…”

Section: Related Workmentioning

confidence: 99%

Improved Density Peak Clustering Based on Information Entropy for Ancient Character Images

Zhang

Yang

2019

IEEE Access

View full text Add to dashboard Cite

A large number of IoT applications require the use of supervised machine learning, a type of machine learning algorithm that requires data to be labeled before the model can be trained. Because manually labeling large datasets is a time-consuming, error-prone, and expensive task, automated machine learning methods can be used. To tackle the challenge in which an ancient character image needs to be manually labeled, this paper explores the classification method of ancient Chinese character images based on density peak clustering. We design a metric function of density peak clustering and propose an improved density peak clustering method based on information entropy for ancient book image classification. The method enumerates the distance threshold of clustering, then calculates the information entropy of the clustering result, and determines the class distance threshold by analyzing the attenuation of the information entropy, thereby completing the image clustering process. The improved metric function is used to calculate the similarity between images. A greedy strategy is used as the basis of the merging operation of the class members to achieve the purpose of increasing the degree of information entropy attenuation. The experimental results on the dataset of the Yi character images prove that the method can accurately classify unknown character images of ancient books. INDEX TERMS Density peak clustering, information entropy, ancient character image.

show abstract

Socializing the Semantic Gap

Cited by 111 publications

References 113 publications

Article Reranking by Memory-Enhanced Key Sentence Matching for Detecting Previously Fact-Checked Claims

Article Reranking by Memory-Enhanced Key Sentence Matching for Detecting Previously Fact-Checked Claims

The VISIONE Video Search System: Exploiting Off-the-Shelf Text Search Engines for Large-Scale Video Retrieval

Improved Density Peak Clustering Based on Information Entropy for Ancient Character Images

Contact Info

Product

Resources

About