Related papers: Denoising Table-Text Retrieval for Open-Domain Que…
Systematic reviews in medicine play a critical role in evidence-based decision-making by aggregating findings from multiple studies. A central bottleneck in automating this process is extracting numeric evidence and determining study-level…
When recalling information in conversation, people often arrive at the recollection after multiple turns. However, existing benchmarks for evaluating agent capabilities in such tip-of-the-tongue search processes are restricted to…
Table Retrieval (TR) has traditionally been formulated as an ad-hoc retrieval problem, where relevance is primarily determined by topical semantic similarity. With the growing adoption of LLM-based agentic systems, access to structured data…
DETR-like models have significantly boosted the performance of detectors and even outperformed classical convolutional models. However, all tokens are treated equally without discrimination brings a redundant computational burden in the…
Conversational search supports multi-turn user-system interactions to solve complex information needs. Different from the traditional single-turn ad-hoc search, conversational search encounters a more challenging problem of…
Tables are a prevalent format for structured data, yet their metadata, such as semantic types and column relationships, is often incomplete or ambiguous. Column annotation tasks, including Column Type Annotation (CTA) and Column Property…
Named Entity Recognition (NER) plays an important role in a wide range of natural language processing tasks, such as relation extraction, question answering, etc. However, previous studies on NER are limited to particular genres, using…
Recently, numerous efforts have continued to push up performance boundaries of document-level relation extraction (DocRE) and have claimed significant progress in DocRE. In this paper, we do not aim at proposing a novel model for DocRE.…
Tabular data in digital documents is widely used to express compact and important information for readers. However, it is challenging to parse tables from unstructured digital documents, such as PDFs and images, into machine-readable format…
Tables are pervasive in diverse documents, making table recognition (TR) a fundamental task in document analysis. Existing modular TR pipelines separately model table structure and content, leading to suboptimal integration and complex…
In this paper, we propose LaPraDoR, a pretrained dual-tower dense retriever that does not require any supervised data for training. Specifically, we first present Iterative Contrastive Learning (ICoL) that iteratively trains the query and…
Portable Document Format (PDF) files are dominantly used for storing and disseminating scientific research, legal documents, and tax information. LaTeX is a popular application for creating PDF documents. Despite its advantages, LaTeX is…
Table detection is the task of classifying and localizing table objects within document images. With the recent development in deep learning methods, we observe remarkable success in table detection. However, a significant amount of labeled…
The current state-of-the-art generative models for open-domain question answering (ODQA) have focused on generating direct answers from unstructured textual information. However, a large amount of world's knowledge is stored in structured…
Data cleaning is a long-standing challenge in data management. While powerful logic and statistical algorithms have been developed to detect and repair data errors in tables, existing algorithms predominantly rely on domain-experts to first…
This paper presents the system description of our entry for the COLING 2025 RegNLP RIRAG (Regulatory Information Retrieval and Answer Generation) challenge, focusing on leveraging advanced information retrieval and answer generation…
Dense retrievers have demonstrated significant potential for neural information retrieval; however, they exhibit a lack of robustness to domain shifts, thereby limiting their efficacy in zero-shot settings across diverse domains. Previous…
Multimodal Large Language Models (MLLMs) have demonstrated remarkable capabilities in document understanding. However, their reasoning processes remain largely black-box, making it difficult to ensure reliability and trustworthiness,…
This paper addresses the unsupervised learning of content-style decomposed representation. We first give a definition of style and then model the content-style representation as a token-level bipartite graph. An unsupervised framework,…
Annotation noise is widespread in datasets, but manually revising a flawed corpus is time-consuming and error-prone. Hence, given the prior knowledge in Pre-trained Language Models and the expected uniformity across all annotations, we…