We present the outcomes of the Multimodal Figurative Language Shared Task held at the 4th Workshop on Figurative Language Processing (FigLang 2024) co-located at NAACL 2024. The task utilized the V-FLUTE dataset which is comprised of <image, text> pairs that use figurative language and includes detailed textual explanations for the entailment or contradiction relationship of each pair. The challenge for participants was to develop models capable of accurately identifying the visual entailment relationship in these multimodal instances and generating persuasive free-text explanations. The results showed that the participants’ models significantly outperformed the initial baselines in both automated and human evaluations. We also provide an overview of the systems submitted and analyze the results of the evaluations. All participating systems outperformed the LLaVA-ZS baseline, provided by us in F1-score.

Automatic Speech Recognition and its applications are rising in popularity across applications with reasonable inference results. Recent state-of-the-art approaches, often employ significantly large-scale models to show high accuracy for ASR as a whole but often do not consider detailed analysis of performance across low-resource languages applications. In this preliminary work, we propose to revisit ASR in the context of Connected Number Recognition (CNR). More specifically, we (i) present a new dataset HCNR collected to understand various errors of ASR models for CNR, (ii) establish preliminary benchmark and baseline model for CNR, (iii) explore error mitigation strategies and their after-effects on CNR. In the due process, we also compare with end-to-end large scale ASR models for reference, to show its effectiveness.

E-commerce websites (e.g. Amazon, Alibaba) have a plethora of structured and unstructured information (text and images) present on the product pages. Sellers often don’t label or mislabel values of the attributes (e.g. color, size etc.) for their products. Automatically identifying these attribute values from an eCommerce product page that contains both text and images is a challenging task, especially when the attribute value is not explicitly mentioned in the catalog. In this paper, we present a scalable solution for this problem where we pose attribute extraction problem as a question-answering task, which we solve using MXT, that consists of three key components: (i) MAG (Multimodal Adaptation Gate), (ii) Xception network, and (iii) T5 encoder-decoder. Our system consists of a generative model that generates attribute-values for a given product by using both textual and visual characteristics (e.g. images) of the product. We show that our system is capable of handling zero-shot attribute prediction (when attribute value is not seen in training data) and value-absent prediction (when attribute value is not mentioned in the text) which are missing in traditional classification-based and NER-based models respectively. We have trained our models using distant supervision, removing dependency on human labeling, thus making them practical for real-world applications. With this framework, we are able to train a single model for 1000s of (product-type, attribute) pairs, thus reducing the overhead of training and maintaining separate models. Extensive experiments on two real world datasets (total 57 attributes) show that our framework improves the absolute recall@90P by 10.16% and 6.9 from the existing state of the art models. In a popular e-commerce store, we have productionized our models that cater to 12K (product-type, attribute) pairs, and have extracted 150MM attribute values.