Sangkeun Jung

Also published as: SangKeun Jung


Learning to Embed Semantic Correspondence for Natural Language Understanding
Sangkeun Jung | Jinsik Lee | Jiwon Kim
Proceedings of the 22nd Conference on Computational Natural Language Learning

While learning embedding models has yielded fruitful results in several NLP subfields, most notably Word2Vec, embedding correspondence has relatively not been well explored especially in the context of natural language understanding (NLU), a task that typically extracts structured semantic knowledge from a text. A NLU embedding model can facilitate analyzing and understanding relationships between unstructured texts and their corresponding structured semantic knowledge, essential for both researchers and practitioners of NLU. Toward this end, we propose a framework that learns to embed semantic correspondence between text and its extracted semantic knowledge, called semantic frame. One key contributed technique is semantic frame reconstruction used to derive a one-to-one mapping between embedded vectors and their corresponding semantic frames. Embedding into semantically meaningful vectors and computing their distances in vector space provides a simple, but effective way to measure semantic similarities. With the proposed framework, we demonstrate three key areas where the embedding model can be effective: visualization, semantic search and re-ranking.


Concept Equalization to Guide Correct Training of Neural Machine Translation
Kangil Kim | Jong-Hun Shin | Seung-Hoon Na | SangKeun Jung
Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 2: Short Papers)

Neural machine translation decoders are usually conditional language models to sequentially generate words for target sentences. This approach is limited to find the best word composition and requires help of explicit methods as beam search. To help learning correct compositional mechanisms in NMTs, we propose concept equalization using direct mapping distributed representations of source and target sentences. In a translation experiment from English to French, the concept equalization significantly improved translation quality by 3.00 BLEU points compared to a state-of-the-art NMT model.


Automatic Agenda Graph Construction from Human-Human Dialogs using Clustering Method
Cheongjae Lee | Sangkeun Jung | Kyungduk Kim | Gary Geunbae Lee
Proceedings of Human Language Technologies: The 2009 Annual Conference of the North American Chapter of the Association for Computational Linguistics, Companion Volume: Short Papers

Hybrid Approach to User Intention Modeling for Dialog Simulation
Sangkeun Jung | Cheongjae Lee | Kyungduk Kim | Gary Geunbae Lee
Proceedings of the ACL-IJCNLP 2009 Conference Short Papers


Robust Dialog Management with N-Best Hypotheses Using Dialog Examples and Agenda
Cheongjae Lee | Sangkeun Jung | Gary Geunbae Lee
Proceedings of ACL-08: HLT

A Frame-Based Probabilistic Framework for Spoken Dialog Management Using Dialog Examples
Kyungduk Kim | Cheongjae Lee | Sangkeun Jung | Gary Geunbae Lee
Proceedings of the 9th SIGdial Workshop on Discourse and Dialogue

An Integrated Dialog Simulation Technique for Evaluating Spoken Dialog Systems
Sangkeun Jung | Cheongjae Lee | Kyungduk Kim | Gary Geunbae Lee
Coling 2008: Proceedings of the workshop on Speech Processing for Safety Critical Translation and Pervasive Applications