Related papers: C2T-ID: Converting Semantic Codebooks to Textual D…

Attribute-based document image retrieval (ABDIR) was recently proposed as an alternative to query-by-example (QBE) searches, the dominant document image retrieval (DIR) paradigm. One drawback of QBE searches is that they require sample…

Knowledge-intensive tasks, such as open-domain question answering (QA), require access to a large amount of world or domain knowledge. A common approach for knowledge-intensive tasks is to employ a retrieve-then-read pipeline that first…

Constructing taxonomies from citation graphs is essential for organizing scientific knowledge, facilitating literature reviews, and identifying emerging research trends. However, manual taxonomy construction is labor-intensive,…

Despite astonishing progress, generating realistic images of complex scenes remains a challenging problem. Recently, layout-to-image synthesis approaches have attracted much interest by conditioning the generator on a list of bounding boxes…

Generative retrieval (Wang et al., 2022; Tay et al., 2022) is a popular approach for end-to-end document retrieval that directly generates document identifiers given an input query. We introduce summarization-based document IDs, in which…

Most existing named entity recognition (NER) approaches are based on sequence labeling models, which focus on capturing the local context dependencies. However, the way of taking one sentence as input prevents the modeling of non-sequential…

The growing capability of large language models to produce fluent, contextually coherent text has created mounting pressure on the systems and institutions responsible for ensuring the authenticity of digital content. Advanced generative…

Recent advances in generative recommendation have leveraged pretrained LLMs by formulating sequential recommendation as autoregressive generation over a unified token space comprising language tokens and itemic identifiers, where each item…

Keyword-based information processing has limitations due to simple treatment of words. In this paper, we introduce named entities as objectives into document clustering, which are the key elements defining document semantics and in many…

Computational morphology has the potential to support language documentation through tasks like morphological segmentation and the generation of Interlinear Glossed Text (IGT). However, our research outputs have seen limited use in…

Generative retrieval directly decode a document identifier (i.e., docid) in response to a query, making it impossible to provide users with explanations as an answer for ``why is this document retrieved?''. To address this limitation, we…

Medical coding is essential for standardizing clinical data and communication but is often time-consuming and prone to errors. Traditional Natural Language Processing (NLP) methods struggle with automating coding due to the large label…

Document categorization, which aims to assign a topic label to each document, plays a fundamental role in a wide variety of applications. Despite the success of existing studies in conventional supervised document classification, they are…

A major challenge in evaluating data-to-text (D2T) generation is measuring the semantic accuracy of the generated text, i.e. checking if the output text contains all and only facts supported by the input data. We propose a new metric for…

Information Retrieval (IR) systems are crucial tools for users to access information, which have long been dominated by traditional methods relying on similarity matching. With the advancement of pre-trained language models, generative…

For understanding generic documents, information like font sizes, column layout, and generally the positioning of words may carry semantic information that is crucial for solving a downstream document intelligence task. Our novel BERTgrid,…

Tagging-based systems enable users to categorize web resources by means of tags (freely chosen keywords), in order to refinding these resources later. Tagging is implicitly also a social indexing process, since users share their tags and…

We introduce G2T-LLM, a novel approach for molecule generation that uses graph-to-tree text encoding to transform graph-based molecular structures into a hierarchical text format optimized for large language models (LLMs). This encoding…

The key challenge in semantic search is to create models that are both accurate and efficient in pinpointing relevant sentences for queries. While BERT-style bi-encoders excel in efficiency with pre-computed embeddings, they often miss…

Code generation remains a challenging task that requires precise and structured reasoning. Existing Test Time Scaling (TTS) methods, including structured tree search, have made progress in exploring reasoning paths but still face two major…