Search Results
Estimating the information gap between textual and visual representations
2017, Henning, Christian, Ewerth, Ralph
Photos, drawings, figures, etc. supplement textual information in various kinds of media, for example, in web news or scientific pub- lications. In this respect, the intended effect of an image can be quite different, e.g., providing additional information, focusing on certain details of surrounding text, or simply being a general il- lustration of a topic. As a consequence, the semantic correlation between information of different modalities can vary noticeably, too. Moreover, cross-modal interrelations are often hard to describe in a precise way. The variety of possible interrelations of textual and graphical information and the question, how they can be de- scribed and automatically estimated have not been addressed yet by previous work. In this paper, we present several contributions to close this gap. First, we introduce two measures to describe cross- modal interrelations: cross-modal mutual information (CMI) and semantic correlation (SC). Second, a novel approach relying on deep learning is suggested to estimate CMI and SC of textual and visual information. Third, three diverse datasets are leveraged to learn an appropriate deep neural network model for the demanding task. The system has been evaluated on a challenging test set and the experimental results demonstrate the feasibility of the approach.
On the Impact of Features and Classifiers for Measuring Knowledge Gain during Web Search - A Case Study
2021, Gritz, Wolfgang, Hoppe, Anett, Ewerth, Ralph, Cong, Gao, Ramanath, Maya
Search engines are normally not designed to support human learning intents and processes. The ÿeld of Search as Learning (SAL) aims to investigate the characteristics of a successful Web search with a learning purpose. In this paper, we analyze the impact of text complexity of Web pages on predicting knowledge gain during a search session. For this purpose, we conduct an experimental case study and investigate the in˝uence of several text-based features and classiÿers on the prediction task. We build upon data from a study of related work, where 104 participants were given the task to learn about the formation of lightning and thunder through Web search. We perform an extensive evaluation based on a state-of-the-art approach and extend it with additional features related to textual complexity of Web pages. In contrast to prior work, we perform a systematic search for optimal hyperparameters and show the possible in˝uence of feature selection strategies on the knowledge gain prediction. When using the new set of features, state-of-the-art results are noticeably improved. The results indicate that text complexity of Web pages could be an important feature resource for knowledge gain prediction.
On the effects of spam filtering and incremental learning for web-supervised visual concept classification
2016, Springstein , Matthias, Ewerth, Ralph
Deep neural networks have been successfully applied to the task of visual concept classification. However, they require a large number of training examples for learning. Although pre-trained deep neural networks are available for some domains, they usually have to be fine-tuned for an envisaged target domain. Recently, some approaches have been suggested that are aimed at incrementally (or even endlessly) learning visual concepts based on Web data. Since tags of Web images are often noisy, normally some filtering mechanisms are employed in order to remove ``spam'' images that are not appropriate for training. In this paper, we investigate several aspects of a web-supervised system that has to be adapted to another target domain: 1.) the effect of incremental learning, 2.) the effect of spam filtering, and 3.) the behavior of particular concept classes with respect to 1.) and 2.). The experimental results provide some insights under which conditions incremental learning and spam filtering are useful.
The STEM-ECR Dataset: Grounding Scientific Entity References in STEM Scholarly Content to Authoritative Encyclopedic and Lexicographic Sources
2020, D'Souza, Jennifer, Hoppe, Anett, Brack, Arthur, Jaradeh, Mohamad Yaser, Auer, Sören, Ewerth, Ralph
We introduce the STEM (Science, Technology, Engineering, and Medicine) Dataset for Scientific Entity Extraction, Classification, and Resolution, version 1.0 (STEM-ECR v1.0). The STEM-ECR v1.0 dataset has been developed to provide a benchmark for the evaluation of scientific entity extraction, classification, and resolution tasks in a domain-independent fashion. It comprises abstracts in 10 STEM disciplines that were found to be the most prolific ones on a major publishing platform. We describe the creation of such a multidisciplinary corpus and highlight the obtained findings in terms of the following features: 1) a generic conceptual formalism for scientific entities in a multidisciplinary scientific context; 2) the feasibility of the domain-independent human annotation of scientific entities under such a generic formalism; 3) a performance benchmark obtainable for automatic extraction of multidisciplinary scientific entities using BERT-based neural models; 4) a delineated 3-step entity resolution procedure for human annotation of the scientific entities via encyclopedic entity linking and lexicographic word sense disambiguation; and 5) human evaluations of Babelfy returned encyclopedic links and lexicographic senses for our entities. Our findings cumulatively indicate that human annotation and automatic learning of multidisciplinary scientific concepts as well as their semantic disambiguation in a wide-ranging setting as STEM is reasonable.
Check square at CheckThat! 2020: Claim Detection in Social Media via Fusion of Transformer and Syntactic Features
2020, Cheema, Gullasl S., Hakimov, Sherzod, Ewerth, Ralph, Cappellato, Linda, Eickhoff, Carsten, Ferro, Nicola, Névéol, Aurélie
In this digital age of news consumption, a news reader has the ability to react, express and share opinions with others in a highly interactive and fast manner. As a consequence, fake news has made its way into our daily life because of very limited capacity to verify news on the Internet by large companies as well as individuals. In this paper, we focus on solving two problems which are part of the fact-checking ecosystem that can help to automate fact-checking of claims in an ever increasing stream of content on social media. For the first prob-lem, claim check-worthiness prediction, we explore the fusion of syntac-tic features and deep transformer Bidirectional Encoder Representations from Transformers (BERT) embeddings, to classify check-worthiness of a tweet, i.e. whether it includes a claim or not. We conduct a detailed feature analysis and present our best performing models for English and Arabic tweets. For the second problem, claim retrieval, we explore the pre-trained embeddings from a Siamese network transformer model (sentence-transformers) specifically trained for semantic textual similar-ity, and perform KD-search to retrieve verified claims with respect to a query tweet.
On the Role of Images for Analyzing Claims in Social Media
2021, Cheema, Gullal S., Hakimov, Sherzod, Müller-Budack, Eric, Ewerth, Ralph
Fake news is a severe problem in social media. In this paper, we present an empirical study on visual, textual, and multimodal models for the tasks of claim, claim check-worthiness, and conspiracy detection, all of which are related to fake news detection. Recent work suggests that images are more influential than text and often appear alongside fake text. To this end, several multimodal models have been proposed in recent years that use images along with text to detect fake news on social media sites like Twitter. However, the role of images is not well understood for claim detection, specifically using transformer-based textual and multimodal models. We investigate state-of-the-art models for images, text (Transformer-based), and multimodal information for four different datasets across two languages to understand the role of images in the task of claim and conspiracy detection.
A Multimodal Approach for Semantic Patent Image Retrieval
2021, Pustu-Iren, Kader, Bruns, Gerrit, Ewerth, Ralph
Patent images such as technical drawings contain valuable information and are frequently used by experts to compare patents. However, current approaches to patent information retrieval are largely focused on textual information. Consequently, we review previous work on patent retrieval with a focus on illustrations in figures. In this paper, we report on work in progress for a novel approach for patent image retrieval that uses deep multimodal features. Scene text spotting and optical character recognition are employed to extract numerals from an image to subsequently identify references to corresponding sentences in the patent document. Furthermore, we use a neural state-of-the-art CLIP model to extract structural features from illustrations and additionally derive textual features from the related patent text using a sentence transformer model. To fuse our multimodal features for similarity search we apply re-ranking according to averaged or maximum scores. In our experiments, we compare the impact of different modalities on the task of similarity search for patent images. The experimental results suggest that patent image retrieval can be successfully performed using the proposed feature sets, while the best results are achieved when combining the features of both modalities.
Combining Textual Features for the Detection of Hateful and Offensive Language
2021, Hakimov, Sherzod, Ewerth, Ralph, Mehta, Parth, Mandl, Thomas, Majumder, Prasenjit, Mitra, Mandar
The detection of offensive, hateful and profane language has become a critical challenge since many users in social networks are exposed to cyberbullying activities on a daily basis. In this paper, we present an analysis of combining different textual features for the detection of hateful or offensive posts on Twitter. We provide a detailed experimental evaluation to understand the impact of each building block in a neural network architecture. The proposed architecture is evaluated on the English Subtask 1A: Identifying Hate, offensive and profane content from the post datasets of HASOC-2021 dataset under the team name TIB-VA. We compared different variants of the contextual word embeddings combined with the character level embeddings and the encoding of collected hate terms.
TIB's visual analytics group at MediaEval '20: Detecting fake news on corona virus and 5G conspiracy
2020, Cheema, Gullal S., Hakimov, Sherzod, Ewerth, Ralph, Hicks, Steven
Fake news on social media has become a hot topic of research as it negatively impacts the discourse of real news in the public. Specifi-cally, the ongoing COVID-19 pandemic has seen a rise of inaccurate and misleading information due to the surrounding controversies and unknown details at the beginning of the pandemic. The Fak-eNews task at MediaEval 2020 tackles this problem by creating a challenge to automatically detect tweets containing misinformation based on text and structure from Twitter follower network. In this paper, we present a simple approach that uses BERT embeddings and a shallow neural network for classifying tweets using only text, and discuss our findings and limitations of the approach in text-based misinformation detection.
Semi-supervised identification of rarely appearing persons in video by correcting weak labels
2016, Müller, Eric, Otto, Christian, Ewerth, Ralph
Some recent approaches for character identification in movies and TV broadcasts are realized in a semi-supervised manner by assigning transcripts and/or subtitles to the speakers. However, the labels obtained in this way achieve only an accuracy of 80% - 90% and the number of training examples for the different actors is unevenly distributed. In this paper, we propose a novel approach for person identification in video by correcting and extending the training data with reliable predictions to reduce the number of annotation errors. Furthermore, the intra-class diversity of rarely speaking characters is enhanced. To address the imbalance of training data per person, we suggest two complementary prediction scores. These scores are also used to recognize whether or not a face track belongs to a (supporting) character whose identity does not appear in the transcript etc. Experimental results demonstrate the feasibility of the proposed approach, outperforming the current state of the art.
- «
- 1 (current)
- 2
- 3
- »