Papers by Kijong Han
An Evaluation Dataset and Strategy for Building Robust Multi-turn Response Selection Model (2021.emnlp-main)
Copied to clipboard
| Challenge: | Multi-turn response selection models have shown comparable performance to humans in several benchmark datasets, but in the real environment, they often have weaknesses, such as giving the highest score to the wrong response candidate containing several keywords related to the context. |
| Approach: | They propose to build a robust multi-turn response selection model in an adversarial environment and to use it to evaluate weaknesses. |
| Outcome: | The proposed model makes incorrect predictions based heavily on superficial patterns without a comprehensive understanding of the context. |
A Korean Knowledge Extraction System for Enriching a KBox (C18-2)
Copied to clipboard
| Challenge: | Existing systems for knowledge extraction from natural language sentences are lacking for all languages. |
| Approach: | They propose a Korean knowledge extraction system and web interface for enriching a KBox knowledge base based on the Korean DBpedia. |
| Outcome: | The proposed system can extract factual knowledge from natural language sentences . the endpoint can be used to add knowledge to a KBox knowledge base anytime and anywhere . |
Utilizing Graph Measure to Deduce Omitted Entities in Paragraphs (C18-2)
Copied to clipboard
| Challenge: | Existing studies on relation extraction only take into account intrasentence relationships that contain pairs of entities. |
| Approach: | They propose to capture omitted arguments in relation extraction given a proper knowledge base for entities of interest. |
| Outcome: | The proposed method improves relation extraction quality by capturing omitted arguments in sentences. |
Unsupervised Korean Word Sense Disambiguation using CoreNet (L18-1)
Copied to clipboard
| Challenge: | Unsupervised learning based Korean word sense disambiguation is needed to distinguish between sense candidates. |
| Approach: | They investigated unsupervised Korean word sense disambiguation using CoreNet, a Korean lexical semantic network. |
| Outcome: | The proposed method exhibited an 80.9% accuracy on the datasets constructed and proved to be effective for practical applications. |
Effective Crowdsourcing of Multiple Tasks for Comprehensive Knowledge Extraction (2020.lrec-1)
Copied to clipboard
Sangha Nam, Minho Lee, Donghwan Kim, Kijong Han, Kuntae Kim, Sooji Yoon, Eun-kyung Kim, Key-Sun Choi
| Challenge: | Existing studies on information extraction from unstructured texts lack a coherent evaluation of all tasks. |
| Approach: | They propose to use crowdsourcing data to develop a Korean information extraction initiative point . they propose to train and evaluate four Korean information extracting tasks using a state-of-the-art model . |
| Outcome: | The proposed model will be used to evaluate four Korean information extraction tasks using crowdsourcing data. |
LittleBird: Efficient Faster & Longer Transformer for Question Answering (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing models for BERT have a limitation dealing with long inputs due to its attention mechanism. |
| Approach: | They propose a model based on BigBird with improved speed and memory footprint . they propose 'pack and unpack attention' to replace global attention . |
| Outcome: | The proposed model can work on long inputs even after being pre-trained on short inputs. |