Related papers: DeepCPCFG: Deep Learning and Context Free Grammars…
Document-level relation extraction is a complex human process that requires logical inference to extract relationships between named entities in text. Existing approaches use graph-based neural models with words as nodes and edges as…
Text-to-image diffusion models are capable of generating high-quality images, but suboptimal pre-trained text representations often result in these images failing to align closely with the given text prompts. Classifier-free guidance (CFG)…
We present an end-to-end, multimodal, fully convolutional network for extracting semantic structures from document images. We consider document semantic structure extraction as a pixel-wise segmentation task, and propose a unified model…
Extractive text summarization aims at extracting the most representative sentences from a given document as its summary. To extract a good summary from a long text document, sentence embedding plays an important role. Recent studies have…
Deep neural networks have achieved significant improvements in information retrieval (IR). However, most existing models are computational costly and can not efficiently scale to long documents. This paper proposes a novel End-to-End neural…
Document-level Relation Extraction (DocRE), which aims to extract relations from a long context, is a critical challenge in achieving fine-grained structural comprehension and generating interpretable document representations. Inspired by…
Background and Objectives: Clinical Practice Guidelines (CPGs) represent the foremost methodology for sharing state-of-the-art research findings in the healthcare domain with medical practitioners to limit practice variations, reduce…
Open-ended survey data constitute an important basis in research as well as for making business decisions. Collecting and manually analysing free-text survey data is generally more costly than collecting and analysing survey data consisting…
The extraction of information from semi-structured text, such as resumes, has long been a challenge due to the diverse formatting styles and subjective content organization. Conventional solutions rely on specialized logic tailored for…
Lying at the core of human intelligence, relational thinking is characterized by initially relying on innumerable unconscious percepts pertaining to relations between new sensory signals and prior knowledge, consequently becoming a…
Grammar-based sentence generation has been thoroughly explored for Context-Free Grammars (CFGs), but remains unsolved for recognition-based approaches such as Parsing Expression Grammars (PEGs). Lacking tool support, language designers…
Classifier-Free Guidance (CFG) is a widely adopted technique in diffusion and flow-based generative models, enabling high-quality conditional generation. A key theoretical challenge is characterizing the distribution induced by CFG,…
This paper presents a comprehensive study on the role of Classifier-Free Guidance (CFG) in text-conditioned diffusion models from the perspective of inference efficiency. In particular, we relax the default choice of applying CFG in all…
This paper reports on the "Learning Computational Grammars" (LCG) project, a postdoc network devoted to studying the application of machine learning techniques to grammars suitable for computational use. We were interested in a more…
Document-level relation extraction requires integrating information within and across multiple sentences of a document and capturing complex interactions between inter-sentence entities. However, effective aggregation of relevant…
Unstructured enterprise data such as reports, manuals and guidelines often contain tables. The traditional way of integrating data from these tables is through a two-step process of table detection/extraction and mapping the table layouts…
Structured learning is appropriate when predicting structured outputs such as trees, graphs, or sequences. Most prior work requires the training set to consist of complete trees, graphs or sequences. Specifying such detailed ground truth…
Large Language Models (LLMs) have achieved impressive progress in natural language processing, but their limited ability to retain long-term context constrains performance on document-level or multi-turn tasks. Retrieval-Augmented…
A fundamental trade-off between effectiveness and efficiency needs to be balanced when designing an online question answering system. Effectiveness comes from sophisticated functions such as extractive machine reading comprehension (MRC),…
Extracting action sequences from natural language texts is challenging, as it requires commonsense inferences based on world knowledge. Although there has been work on extracting action scripts, instructions, navigation actions, etc., they…