Multimodal ambiguity is a challenge for understanding text and images. Large pre-trained models have reached a high level of quality already. This paper presents an implementation for solving a image disambiguation task relying solely on the knowledge captured in multimodal and language models. Within the task 1 of SemEval 2023 (Visual Word Sense Disambiguation), this approach managed to achieve an MRR of 0.738 using CLIP-Large and the OPT model for generating text. Applying a generative model to create more text given a phrase with an ambiguous word leads to an improvement of our results. The performance gain from a bigger language model is larger than the performance gain from using the lager CLIP model.

This paper describes the participation of the University of Hildesheim at the SemEval task 5. The task deals with Multimedia Automatic Misogyny Identification (MAMI). Hateful memes need to be detected within a data collection. For this task, we implemented six models for text and image analysis and tested the effectiveness of their combinations. A fusion system implements a multi-modal transformer to integrate the embeddings of these models. The best performing models included BERT for the text of the meme, manually derived associations for words in the memes and a Faster R-CNN network for the image. We evaluated the performance of our approach also with the data of the Facebook Hateful Memes challenge in order to analyze the generalisation capabilities of the approach.

Detecting offensive language in social media in local languages is critical for moderating user-generated content. Thus, the field of offensive language identification in under-resourced Tamil, Malayalam and Kannada languages are essential. As the user-generated content is more code-mixed and not well studied for under-resourced languages, it is imperative to create resources and conduct benchmarking studies to encourage research in under-resourced Dravidian languages. We created a shared task on offensive language detection in Dravidian languages. We summarize here the dataset for this challenge which are openly available at https://competitions.codalab.org/competitions/27654, and present an overview of the methods and the results of the competing systems.

This paper describes the participation of team DA-LD-Hildesheim from the Information Retrieval Lab(IRLAB) at DA-IICT Gandhinagar, India in collaboration with the University of Hildesheim, Germany and LDRP-ITR, Gandhinagar, India in a shared task on Aggression Identification workshop in COLING 2018. The objective of the shared task is to identify the level of aggression from the User-Generated contents within Social media written in English, Devnagiri Hindi and Romanized Hindi. Aggression levels are categorized into three predefined classes namely: ‘Overtly Aggressive‘, ‘Covertly Aggressive‘ and ‘Non-aggressive‘. The participating teams are required to develop a multi-class classifier which classifies User-generated content into these pre-defined classes. Instead of relying on a bag-of-words model, we have used pre-trained vectors for word embedding. We have performed experiments with standard machine learning classifiers. In addition, we have developed various deep learning models for the multi-class classification problem. Using the validation data, we found that validation accuracy of our deep learning models outperform all standard machine learning classifiers and voting based ensemble techniques and results on test data support these findings. We have also found that hyper-parameters of the deep neural network are the keys to improve the results.

In order to extract meaningful phrases from corpora (e. g. in an information retrieval context) intensive knowledge of the domain in question and the respective documents is generally needed. When moving to a new domain or language the underlying knowledge bases and models need to be adapted, which is often time-consuming and labor-intensive. This paper adresses the described challenge of phrase extraction from documents in different domains and languages and proposes an approach, which does not use comprehensive lexica and therefore can be easily transferred to new domains and languages. The effectiveness of the proposed approach is evaluated on user generated content and documents from the patent domain in English and German.

In this paper we describe GikiCLEF, the first evaluation contest that, to our knowledge, was specifically designed to expose and investigate cultural and linguistic issues involved in structured multimedia collections and searching, and which was organized under the scope of CLEF 2009. GikiCLEF evaluated systems that answered hard questions for both human and machine, in ten different Wikipedia collections, namely Bulgarian, Dutch, English, German, Italian, Norwegian (Bokmäl and Nynorsk), Portuguese, Romanian, and Spanish. After a short historical introduction, we present the task, together with its motivation, and discuss how the topics were chosen. Then we provide another description from the point of view of the participants. Before disclosing their results, we introduce the SIGA management system explaining the several tasks which were carried out behind the scenes. We quantify in turn the GIRA resource, offered to the community for training and further evaluating systems with the help of the 50 topics gathered and the solutions identified. We end the paper with a critical discussion of what was learned, advancing possible ways to reuse the data.

Opinion Mining is a discipline that has attracted some attention lately. Most of the research in this field has been done for English or Asian languages, due to the lack of resources in other languages. In this paper we describe an approach of building a manually annotated multilingual corpus for the domain of product reviews, which can be used as a basis for fine-grained opinion analysis also considering direct and indirect opinion targets. For each sentence in a review, the mentioned product features with their respective opinion polarity and strength on a scale from 0 to 3 are labelled manually by two annotators. The languages represented in the corpus are English, German and Spanish and the corpus consists of about 500 product reviews per language. After a short introduction and a description of related work, we illustrate the annotation process, including a description of the annotation methodology and the developed tool for the annotation process. Then first results on the inter-annotator agreement for opinions and product features are presented. We conclude the paper with an outlook on future work.

In this paper we present an evaluation resource for geographic information retrieval developed within the Cross Language Evaluation Forum (CLEF). The GeoCLEF track is dedicated to the evaluation of geographic information retrieval systems. The resource encompasses more than 600,000 documents, 75 topics so far, and more than 100,000 relevance judgments for these topics. Geographic information retrieval requires an evaluation resource which represents realistic information needs and which is geographically challenging. Some experimental results and analysis are reported