Related papers: Efficient Data Learning for Open Information Extra…
Event argument extraction (EAE) aims to identify the arguments of an event and classify the roles that those arguments play. Despite great efforts made in prior work, there remain many challenges: (1) Data scarcity. (2) Capturing the…
We propose a new method for event extraction (EE) task based on an imitation learning framework, specifically, inverse reinforcement learning (IRL) via generative adversarial network (GAN). The GAN estimates proper rewards according to the…
Research in Document Intelligence and especially in Document Key Information Extraction (DocKIE) has been mainly solved as Token Classification problem. Recent breakthroughs in both natural language processing (NLP) and computer vision…
Ontology (and more generally: Knowledge Graph) Matching is a challenging task where information in natural language is one of the most important signals to process. With the rise of Large Language Models, it is possible to incorporate this…
Text generation under constraints have seen increasing interests in natural language processing, especially with the rapidly improving capabilities of large language models. However, existing benchmarks for constrained generation usually…
Data mixing decides how to combine different sources or types of data and is a consequential problem throughout language model training. In pretraining, data composition is a key determinant of model quality; in continual learning and…
This report argues that, even in the simplest cases, IE is an ontology-driven process. It is not a mere text filtering method based on simple pattern matching and keywords, because the extracted pieces of texts are interpreted with respect…
Current research on the advantages and trade-offs of using characters, instead of tokenized text, as input for deep learning models, has evolved substantially. New token-free models remove the traditional tokenization step; however, their…
Autoregressive language models demonstrate excellent performance in various scenarios. However, the inference efficiency is limited by its one-step-one-word generation mode, which has become a pressing problem recently as the models become…
Event extraction requires high-quality expert human annotations, which are usually expensive. Therefore, learning a data-efficient event extraction model that can be trained with only a few labeled examples has become a crucial challenge.…
Early Exiting is one of the most popular methods to achieve efficient inference. Current early exiting methods adopt the (weighted) sum of the cross entropy loss of all internal classifiers during training, imposing all these classifiers to…
We propose end-to-end document classification and key information extraction (KIE) for automating document processing in forms. Through accurate document classification we harness known information from templates to enhance KIE from forms.…
Detecting out-of-distribution (OOD) samples is essential when deploying machine learning models in open-world scenarios. Zero-shot OOD detection, requiring no training on in-distribution (ID) data, has been possible with the advent of…
We present a study on leveraging multilingual pre-trained generative language models for zero-shot cross-lingual event argument extraction (EAE). By formulating EAE as a language generation task, our method effectively encodes event…
Recently, pre-trained models have achieved state-of-the-art results in various language understanding tasks, which indicates that pre-training on large-scale corpora may play a crucial role in natural language processing. Current…
The multi-format information extraction task in the 2021 Language and Intelligence Challenge is designed to comprehensively evaluate information extraction from different dimensions. It consists of an multiple slots relation extraction…
Early exiting allows instances to exit at different layers according to the estimation of difficulty. Previous works usually adopt heuristic metrics such as the entropy of internal outputs to measure instance difficulty, which suffers from…
Effective ontology transfer has been a major goal of recent work on event argument extraction (EAE). Two methods in particular -- question answering (QA) and template infilling (TI) -- have emerged as promising approaches to this problem.…
Information extraction from textual data, where the query is represented by a finite transducer and the task is to enumerate all results without repetition, and its extension to the weighted case, where each output element has a weight and…
Automating information extraction from form-like documents at scale is a pressing need due to its potential impact on automating business workflows across many industries like financial services, insurance, and healthcare. The key challenge…