BERT has shown a lot of sucess in a wide variety of NLP tasks. But it has a limitation dealing with long inputs due to its attention mechanism. Longformer, ETC and BigBird addressed this issue and effectively solved the quadratic dependency problem.However we find that these models are not sufficient, and propose LittleBird, a novel model based on BigBird with improved speed and memory footprint while maintaining accuracy.In particular, we devise a more flexible and efficient position representation method based on Attention with Linear Biases(ALiBi). We also show that replacing the method of global information represented in the BigBird with pack and unpack attention is more effective.The proposed model can work on long inputs even after being pre-trained on short inputs, and can be trained efficiently reusing existing pre-trained language model for short inputs. This is a significant benefit for low-resource languages where large amounts of long text data are difficult to obtain.As a result, our experiments show that LittleBird works very well in a variety of languages, achieving high performance in question answering tasks, particularly in KorQuAD2.0, Korean Question Answering Dataset for long paragraphs.

Multi-turn response selection models have recently shown comparable performance to humans in several benchmark datasets. However, in the real environment, these models often have weaknesses, such as making incorrect predictions based heavily on superficial patterns without a comprehensive understanding of the context. For example, these models often give a high score to the wrong response candidate containing several keywords related to the context but using the inconsistent tense. In this study, we analyze the weaknesses of the open-domain Korean Multi-turn response selection models and publish an adversarial dataset to evaluate these weaknesses. We also suggest a strategy to build a robust model in this adversarial environment.

Information extraction from unstructured texts plays a vital role in the field of natural language processing. Although there has been extensive research into each information extraction task (i.e., entity linking, coreference resolution, and relation extraction), data are not available for a continuous and coherent evaluation of all information extraction tasks in a comprehensive framework. Given that each task is performed and evaluated with a different dataset, analyzing the effect of the previous task on the next task with a single dataset throughout the information extraction process is impossible. This paper aims to propose a Korean information extraction initiative point and promote research in this field by presenting crowdsourcing data collected for four information extraction tasks from the same corpus and the training and evaluation results for each task of a state-of-the-art model. These machine learning data for Korean information extraction are the first of their kind, and there are plans to continuously increase the data volume. The test results will serve as an initiative result for each Korean information extraction task and are expected to serve as a comparison target for various studies on Korean information extraction using the data collected in this study.

Distant supervision can automatically generate labeled data between a large-scale corpus and a knowledge base without utilizing human efforts. Therefore, many studies have used the distant supervision approach in relation extraction tasks. However, existing studies have a disadvantage in that they do not reflect the homograph in the word embedding used as an input of the relation extraction model. Thus, it can be seen that the relation extraction model learns without grasping the meaning of the word accurately. In this paper, we propose a relation extraction model with multi-sense word embedding. We learn multi-sense word embedding using a word sense disambiguation module. In addition, we use convolutional neural network and piecewise max pooling convolutional neural network relation extraction models that efficiently grasp key features in sentences. To evaluate the performance of the proposed model, two additional methods of word embedding were learned and compared. Accordingly, our method showed the highest performance among them.

The increased demand for structured knowledge has created considerable interest in knowledge extraction from natural language sentences. This study presents a new Korean knowledge extraction system and web interface for enriching a KBox knowledge base that expands based on the Korean DBpedia. The aim is to create an endpoint where knowledge can be extracted and added to KBox anytime and anywhere.

This demo deals with the problem of capturing omitted arguments in relation extraction given a proper knowledge base for entities of interest. This paper introduces the concept of a salient entity and use this information to deduce omitted entities in the paragraph which allows improving the relation extraction quality. The main idea to compute salient entities is to construct a graph on the given information (by identifying the entities but without parsing it), rank it with standard graph measures and embed it in the context of the sentences.