Recent machine translation (MT) systems have overcome language barriers for a wide range of users, yet they still carry the risk of critical meaning deviation. Critical error detection (CED) is a task that identifies an inherent risk of catastrophic meaning distortions in the machine translation output. With the importance of reflecting cultural elements in detecting critical errors, we introduce the culture-aware “Politeness” type in detecting English-Korean critical translation errors. Besides, we facilitate two tasks by providing multiclass labels: critical error detection and critical error type classification (CETC). Empirical evaluations reveal that our introduced data augmentation approach using a newly presented perturber significantly outperforms existing baselines in both tasks. Further analysis highlights the significance of multiclass labeling by demonstrating its superior effectiveness compared to binary labels.

Abstract Document-level relation extraction (RE) aims to predict the relational facts between two given entities from a document. Unlike widespread research on document-level RE in English, Korean document-level RE research is still at the very beginning due to the absence of a dataset. To accelerate the studies, we present (Toward Document-Level Relation Extraction in Korean) dataset constructed from Korean encyclopedia documents written by the domain experts. We provide detailed statistical analyses for our large-scale dataset and human evaluation results suggest the assured quality of . Also, we introduce the document-level RE model that considers the named entity-type while considering the Korean language’s properties. In the experiments, we demonstrate that our proposed model outperforms the baselines and conduct qualitative analysis.

The main objective of the task-oriented dialogue system is to identify the intent and needs of human dialogue. Many existing studies are conducted under the setting of written dialogue, but there always exists a difficulty in coping with real-world spoken dialogues. To this end, DSTC10 challenge organizers propose the task of building robust dialogue state tracking (DST) models on spoken dialogues. With the powerful existing DST model (i.e., MinTL), this article suggests integral components for building a dialogue state tracker; 1) Data augmentation effectively enhances the capability of the model to catch the entities that exist in the evaluation dataset. 2) Levenshtein post-processing aims to prevent the distortion in model prediction caused by automatic speech recognition errors. To validate the effectiveness of our methods, we evaluate our model on DSTC10 datasets and conduct qualitative analysis by ablating each component of the model. Experimental results show that our model significantly outperforms baselines in all evaluation metrics and took 3rd place in the challenge.

Yoonna Jang, Suhyune Son, Jeongwoo Lee, Junyoung Son, Yuna Hur, Jungwoo Lim, Hyeonseok Moon, Kisu Yang, Heuiseok Lim. Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing. 2023.

We present an energy-efficient, scalable neural stim-ulation IC with adaptive dynamic voltage switching, which can be applied to cochlear implant (CI) systems. The stimulation IC generates three different voltage outputs by operating a single-inductor multiple-output (SIMO) boost converter, while an adaptive dynamic voltage switching (ADVS) block selects an appropriate supply voltage for each stimulation channel among those SIMO outputs. The SIMO boost converter is designed to operate over a wide range of its input, which is the rectifier output of the wirelessly powered CI system. The ADVS control as well as the stimulation amplitude control are performed remotely by an external sound processor (SP) of the CI system in real time. For the ADVS operation, the compliance voltage of each stimulation channel is monitored to be used as an input signal for switching to the appropriate supply voltage for the corresponding stimulation channel. The dynamic voltage switching operation is carried out in sub-us, The stimulation IC with ADVS is implemented using a 180-nm BCD process, and its operation and performance are verified through post-layout simulations. When applying a real audio input using decoded data from a prototype SP, the proposed stimulation IC with ADVS demonstrates 36.6% energy saving compared to the conventional stimulation IC.

Humans usually have conversations by making use of prior knowledge about a topic and background information of the people whom they are talking to. However, existing conversational agents and datasets do not consider such comprehensive information, and thus they have a limitation in generating the utterances where the knowledge and persona are fused properly. To address this issue, we introduce a call For Customized conversation (FoCus) dataset where the customized answers are built with the user's persona and Wikipedia knowledge. To evaluate the abilities to make informative and customized utterances of pre-trained language models, we utilize BART and GPT-2 as well as transformer-based models. We assess their generation abilities with automatic scores and conduct human evaluations for qualitative results. We examine whether the model reflects adequate persona and knowledge with our proposed two sub-tasks, persona grounding (PG) and knowledge grounding (KG). Moreover, we show that the utterances of our data are constructed with the proper knowledge and persona through grounding quality assessment.

The dialogue-based relation extraction (DialogRE) task aims to predict the relations between argument pairs that appear in dialogue. Most previous studies utilize fine-tuning pre-trained language models (PLMs) only with extensive features to supplement the low information density of the dialogue by multiple speakers. To effectively exploit inherent knowledge of PLMs without extra layers and consider scattered semantic cues on the relation between the arguments, we propose a Guiding model with RelAtional Semantics using Prompt (GRASP). We adopt a prompt-based fine-tuning approach and capture relational semantic clues of a given dialogue with 1) an argument-aware prompt marker strategy and 2) the relational clue detection task. In the experiments, GRASP achieves state-of-the-art performance in terms of both F1 and F1c scores on a DialogRE dataset even though our method only leverages PLMs without adding any extra layers.

CommonsenseQA is a task in which a correct answer is predicted through commonsense reasoning with pre-defined knowledge.Most previous works have aimed to improve the performance with distributed representation without considering the process of predicting the answer from the semantic representation of the question.To shed light upon the semantic interpretation of the question, we propose an AMR-ConceptNet-Pruned (ACP) graph.The ACP graph is pruned from a full integrated graph encompassing Abstract Meaning Representation (AMR) graph generated from input questions and an external commonsense knowledge graph, ConceptNet (CN).Then the ACP graph is exploited to interpret the reasoning path as well as to predict the correct answer on the CommonsenseQA task.This paper presents the manner in which the commonsense reasoning process can be interpreted with the relations and concepts provided by the ACP graph.Moreover, ACP-based models are shown to outperform the baselines.