Although Large Language Models (LLMs) can generate coherent text, they often struggle to recognise user intent behind queries. In contrast, Natural Language Understanding (NLU) models interpret the purpose and key information of user input for responsive interactions. Existing NLU models typically map utterances to a dual-level semantic frame, involving sentence-level intent (SI) and word-level slot (WS) labels. However, real-life conversations primarily consist of multi-turn dialogues, requiring the interpretation of complex and extended exchanges. Researchers encounter challenges in addressing all facets of multi-turn dialogue using a unified NLU model. This paper introduces MIDAS, a novel approach leveraging multi-level intent, domain, and slot knowledge distillation for multi-turn NLU. We construct distinct teachers for SI detection, WS filling, and conversation-level domain (CD) classification, each fine-tuned for specific knowledge. A multi-teacher loss is proposed to facilitate the integration of these teachers, guiding a student model in multi-turn dialogue tasks. Results demonstrate the efficacy of our model in improving multi-turn conversation understanding, showcasing the potential for advancements in NLU through multi-level dialogue knowledge distillation. Our implementation is open-sourced on GitHub (https://github.com/adlnlp/Midas).

The pre-trained language models such as KoBART often fail in generating perfect interrogative sentences when they are applied to Korean question generation. This is mainly due to the fact that the language models are much experienced with declarative sentences, but not with interrogative sentences. Therefore, this paper proposes a novel post-training of KoBART to enhance it for Korean question generation. The enhancement of KoBART is accomplished in three ways: (i) introduction of question infilling objective to KoBART to enforce it to focus more on the structure of interrogative sentences, (ii) augmentation of training data for question generation with another data set to cope with the lack of training instances for post-training, (iii) introduction of Korean spacing objective to make KoBART understand the linguistic features of Korean. Since there is no standard data set for Korean question generation, this paper also proposes KorQuAD-QG, a new data set for this task, to verify the performance of the proposed post-training. Our code are publicly available at https://github.com/gminipark/post_training_qg

Korean morphological analysis has been considered as a sequence of morpheme processing and POS tagging. Thus, a pipeline model of the tasks has been adopted widely by previous studies. However, the model has a problem that it cannot utilize interactions among the tasks. This paper formulates Korean morphological analysis as a combination of the tasks and presents a tied sequence-to-sequence multi-task model for training the two tasks simultaneously without any explicit regularization. The experiments prove the proposed model achieves the state-of-the-art performance.

We demonstrate a report generation system called WiseReporter. The WiseReporter generates a text report of a specific topic which is usually given as a keyword by verbalizing knowledge base facts involving the topic. This demonstration does not demonstate only the report itself, but also the processes how the sentences for the report are generated. We are planning to enhance WiseReporter in the future by adding data analysis based on deep learning architecture and text summarization.

We present four kinds of machine translation system in this description: E-K (English to Korean), K-E (Korean to English), J-K (Japanese to Korean), K-J (Korean to Japanese). Among these, E-K and K-J translation systems are published commercially, and the other systems have finished their development. This paper describes the structure and function of each system with figures and translation results.