Related papers: Reading Order Matters: Information Extraction from…

Named Entity Recognition (NER) is a crucial upstream task in Natural Language Processing (NLP). Traditional tag scheme approaches offer a single recognition that does not meet the needs of many downstream tasks such as coreference…

Tagging has been recognized as a successful practice to boost relevance matching for information retrieval (IR), especially when items lack rich textual descriptions. A lot of research has been done for either multi-label text…

Named entity recognition (NER) is a well-studied task in natural language processing. Traditional NER research only deals with flat entities and ignores nested entities. The span-based methods treat entity recognition as a span…

Generative recommender systems have recently attracted attention by formulating next-item prediction as an autoregressive sequence generation task. However, most existing methods optimize standard next-token likelihood and implicitly treat…

The output structure of database-like tables, consisting of values structured in horizontal rows and vertical columns identifiable by name, can cover a wide range of NLP tasks. Following this constatation, we propose a framework for…

Visual grounding (VG) is the capability to identify the specific regions in an image associated with a particular text description. In medical imaging, VG enhances interpretability by highlighting relevant pathological features…

Vision Transformers (ViTs) have shown impressive performance in computer vision, but their high computational cost, quadratic in the number of tokens, limits their adoption in computation-constrained applications. However, this large number…

Medical systematic reviews typically require assessing all the documents retrieved by a search. The reason is two-fold: the task aims for ``total recall''; and documents retrieved using Boolean search are an unordered set, and thus it is…

Tokenization is a key component of autoregressive (AR) generative models, converting raw data into more manageable units for modeling. Commonly, tokens describe local information, such as regions of pixels in images or word pieces in text,…

Learning to Rank (LTR) methods generally assume that each document in a top-K ranking is presented in an equal format. However, previous work has shown that users' perceptions of relevance can be changed by varying presentations, i.e.,…

Reading order detection is the cornerstone to understanding visually-rich documents (e.g., receipts and forms). Unfortunately, no existing work took advantage of advanced deep learning models because it is too laborious to annotate a large…

Document retrieval has greatly benefited from the advancements of large-scale pre-trained language models (PLMs). However, their effectiveness is often limited in theme-specific applications for specialized areas or industries, due to…

Text classification has long been a staple within Natural Language Processing (NLP) with applications spanning across diverse areas such as sentiment analysis, recommender systems and spam detection. With such a powerful solution, it is…

Named Entity Recognition (NER) is a challenging and widely studied task that involves detecting and typing entities in text. So far,NER still approaches entity typing as a task of classification into universal classes (e.g. date, person, or…

Recent studies on scaling up ranking models have achieved substantial improvement for recommendation systems and search engines. However, most large-scale ranking systems rely on item IDs, where each item is treated as an independent…

As more and more Arabic texts emerged on the Internet, extracting important information from these Arabic texts is especially useful. As a fundamental technology, Named entity recognition (NER) serves as the core component in information…

In the domain of Natural Language Processing (NLP), Named Entity Recognition (NER) stands out as a pivotal mechanism for extracting structured insights from unstructured text. This manuscript offers an exhaustive exploration into the…

In standard large vision-language models (LVLMs) pre-training, the model typically maximizes the joint probability of the caption conditioned on the image via next-token prediction (NTP); however, since only a small subset of caption tokens…

We present a novel method for mapping unrestricted text to knowledge graph entities by framing the task as a sequence-to-sequence problem. Specifically, given the encoded state of an input text, our decoder directly predicts paths in the…

Large Vision-Language Models (LVLMs) have recently demonstrated strong multimodal understanding, yet their fine-grained visual perception is often constrained by low input resolutions. A common remedy is to partition high-resolution images…