Related papers: MMAPS: End-to-End Multi-Grained Multi-Modal Attrib…
Missing-modality information on e-commerce platforms, such as absent product images or textual descriptions, often arises from annotation errors or incomplete metadata, impairing both product presentation and downstream applications such as…
automated Production Systems (aPS) are highly complex, mechatronic systems that usually have to operate reliably for many decades. Standardization and reuse of control software modules is a core prerequisite to achieve the required system…
To improve users' experience as they navigate the myriad of options offered by online marketplaces, it is essential to have well-organized product catalogs. One key ingredient to that is the availability of product attributes such as color…
With the rapid advancement of e-commerce, exploring general representations rather than task-specific ones has attracted increasing research attention. For product understanding, although existing discriminative dual-flow architectures…
Multi-modal learning aims to enhance performance by unifying models from various modalities but often faces the "modality imbalance" problem in real data, leading to a bias towards dominant modalities and neglecting others, thereby limiting…
Automatically summarizing large text collections is a valuable tool for document research, with applications in journalism, academic research, legal work, and many other fields. In this work, we contrast two classes of systems for…
Abstractive summarization has been studied using neural sequence transduction methods with datasets of large, paired document-summary examples. However, such datasets are rare and the models trained from them do not generalize to other…
Automatic generation of summaries from multiple news articles is a valuable tool as the number of online publications grows rapidly. Single document summarization (SDS) systems have benefited from advances in neural encoder-decoder model…
With the prosperity of e-commerce industry, various modalities, e.g., vision and language, are utilized to describe product items. It is an enormous challenge to understand such diversified data, especially via extracting the…
Multimodal summarization requires models to jointly understand textual and visual inputs to generate concise, semantically coherent summaries. Existing methods often inject shallow visual features into deep language models, leading to…
Product review nowadays has become an important source of information, not only for customers to find opinions about products easily and share their reviews with peers, but also for product manufacturers to get feedback on their products.…
Text summarization is a well-established task within the natural language processing (NLP) community. However, the focus on controllable summarization tailored to user requirements is gaining traction only recently. While several efforts…
Withthegrowthofknowledgegraphs, entity descriptions are becoming extremely lengthy. Entity summarization task, aiming to generate diverse, comprehensive, and representative summaries for entities, has received increasing interest recently.…
Summarizing text-rich documents has been long studied in the literature, but most of the existing efforts have been made to summarize a static and predefined multi-document set. With the rapid development of online platforms for generating…
Source code summarization aims to generate natural language descriptions of code snippets. Many existing studies learn the syntactic and semantic knowledge of code snippets from their token sequences and Abstract Syntax Trees (ASTs). They…
Obtaining training data for multi-document summarization (MDS) is time consuming and resource-intensive, so recent neural models can only be trained for limited domains. In this paper, we propose SummPip: an unsupervised method for…
Obeying precise constraints on top of multiple external attributes is a common computational problem underlying seemingly different domains, from controlled text generation to protein engineering. Existing language model (LM)…
Product attribute values are essential in many e-commerce scenarios, such as customer service robots, product recommendations, and product retrieval. While in the real world, the attribute values of a product are usually incomplete and vary…
Pre-trained on extensive text and image corpora, current Multi-Modal Large Language Models (MLLM) have shown strong capabilities in general visual reasoning tasks. However, their performance is still lacking in physical domains that require…
Multimodal summarization (MS) aims to generate a summary from multimodal input. Previous works mainly focus on textual semantic coverage metrics such as ROUGE, which considers the visual content as supplemental data. Therefore, the summary…