Heui-Seok Lim

Also published as: Heuiseok Lim


2024

pdf
Hyper-BTS Dataset: Scalability and Enhanced Analysis of Back TranScription (BTS) for ASR Post-Processing
Chanjun Park | Jaehyung Seo | Seolhwa Lee | Junyoung Son | Hyeonseok Moon | Sugyeong Eo | Chanhee Lee | Heuiseok Lim
Findings of the Association for Computational Linguistics: EACL 2024

The recent advancements in the realm of Automatic Speech Recognition (ASR) post-processing have been primarily driven by sequence-to-sequence paradigms. Despite their effectiveness, these methods often demand substantial amounts of data, necessitating the expensive recruitment of phonetic transcription experts to rectify the erroneous outputs of ASR systems, thereby creating the desired training data. Back TranScription (BTS) alleviates this issue by generating ASR inputs from clean text via a Text-to-Speech (TTS) system. While initial studies on BTS exhibited promise, they were constrained by a limited dataset of just 200,000 sentence pairs, leaving the scalability of this method in question. In this study, we delve into the potential scalability of BTS. We introduce the “Hyper-BTS” dataset, a corpus approximately five times larger than that utilized in prior research. Additionally, we present innovative criteria for categorizing error types within ASR post-processing. This not only facilitates a more comprehensive qualitative analysis, which was absent in preceding studies, but also enhances the understanding of ASR error patterns. Our empirical results, both quantitative and qualitative, suggest that the enlarged scale of the Hyper-BTS dataset sufficiently addresses a vast majority of the ASR error categories. We make the Hyper-BTS dataset publicly available.

pdf
Generative Interpretation: Toward Human-Like Evaluation for Educational Question-Answer Pair Generation
Hyeonseok Moon | Jaewook Lee | Sugyeong Eo | Chanjun Park | Jaehyung Seo | Heuiseok Lim
Findings of the Association for Computational Linguistics: EACL 2024

Educational question-answer generation has been extensively researched owing to its practical applicability. However, we have identified a persistent challenge concerning the evaluation of such systems. Existing evaluation methods often fail to produce objective results and instead exhibit a bias towards favoring high similarity to the ground-truth question-answer pairs. In this study, we demonstrate that these evaluation methods yield low human alignment and propose an alternative approach called Generative Interpretation (GI) to achieve more objective evaluations. Through experimental analysis, we reveal that GI outperforms existing evaluation methods in terms of human alignment, and even shows comparable performance with GPT3.5, only with BART-large.

pdf
Ask, Assess, and Refine: Rectifying Factual Consistency and Hallucination in LLMs with Metric-Guided Feedback Learning
Dongyub Lee | Eunhwan Park | Hodong Lee | Heuiseok Lim
Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)

Recent advancements in Large Language Models (LLMs) have heralded unprecedented capabilities in information-seeking and text generation, as evidenced by applications like Bing Chat and perplexity.ai. Despite these strides, challenges on hallucination and factual inconsistency continue to impede their wider real-world adoption. Contemporary methods, including retrieval-augmented LLMs and feedback-based learning, serve as alternatives to mitigate these challenges. However, challenges remain, particularly regarding referencing erroneous evidence (citation errors) and generating information not present in the evidence (hallucination). In this paper, we introduce the 𝖠2𝖱 framework: Ask, Assess, and Refine. Our approach utilizes an explicit evaluation paradigm, incorporating metrics specifically tailored to assess citation errors and hallucination, aiming to address these prevalent challenges robustly. Capitalizing on these evaluations, we devise a strategy to formulate actionable natural language feedback, enabling iterative refinements that yield improved factual consistency and reduced hallucinations in responses. Our experiments on ASQA, ELI5, and QAMPARI datasets demonstrate our method’s superiority in enhancing correctness, fluency, and citation quality.

2023

pdf
Towards Diverse and Effective Question-Answer Pair Generation from Children Storybooks
Sugyeong Eo | Hyeonseok Moon | Jinsung Kim | Yuna Hur | Jeongwook Kim | SongEun Lee | Changwoo Chun | Sungsoo Park | Heuiseok Lim
Findings of the Association for Computational Linguistics: ACL 2023

Recent advances in QA pair generation (QAG) have raised interest in applying this technique to the educational field. However, the diversity of QA types remains a challenge despite its contributions to comprehensive learning and assessment of children. In this paper, we propose a QAG framework that enhances QA type diversity by producing different interrogative sentences and implicit/explicit answers. Our framework comprises a QFS-based answer generator, an iterative QA generator, and a relevancy-aware ranker. The two generators aim to expand the number of candidates while covering various types. The ranker trained on the in-context negative samples clarifies the top-N outputs based on the ranking score. Extensive evaluations and detailed analyses demonstrate that our approach outperforms previous state-of-the-art results by significant margins, achieving improved diversity and quality. Our task-oriented processes are consistent with real-world demand, which highlights our system’s high applicability.

pdf
Explore the Way: Exploring Reasoning Path by Bridging Entities for Effective Cross-Document Relation Extraction
Junyoung Son | Jinsung Kim | Jungwoo Lim | Yoonna Jang | Heuiseok Lim
Findings of the Association for Computational Linguistics: EMNLP 2023

Cross-document relation extraction (CodRED) task aims to infer the relation between two entities mentioned in different documents within a reasoning path. Previous studies have concentrated on merely capturing implicit relations between the entities. However, humans usually utilize explicit information chains such as hyperlinks or additional searches to find the relations between two entities. Inspired by this, we propose Path wIth expLOraTion (PILOT) that provides the enhanced reasoning path by exploring the explicit clue information within the documents. PILOT finds the bridging entities which directly guide the paths between the entities and then employs them as stepstones to navigate desirable paths. We show that models with PILOT outperform the baselines in the CodRED task. Furthermore, we offer a variety of analyses to verify the validity of the reasoning paths constructed through PILOT, including evaluations using large language models such as ChatGPT.

pdf
Beyond Candidates : Adaptive Dialogue Agent Utilizing Persona and Knowledge
Jungwoo Lim | Myunghoon Kang | Jinsung Kim | Jeongwook Kim | Yuna Hur | Heuiseok Lim
Findings of the Association for Computational Linguistics: EMNLP 2023

To build ultimate dialogue agents, previous studies suggest models that ground both persona and knowledge. However, applying the dialogue system directly to the usual conversation is still limited because the system requires a complete sentence-formed persona and knowledge candidate sets from the given dataset. In contrast to the dialogue setting in the dataset, humans utilize semantic concepts in their minds rather than a set of pre-defined candidate sentences. Following this manner of human dialogue, we suggest an adaptive dialogue system that is applicable to situations where complete sentence-formed candidates are not given. Our model generates consistent and relevant persona descriptions and identifies relevant knowledge for engaging and knowledgeable responses, even with fragmentary information. We show that our model outperforms previous baselines that utilize persona and knowledge candidate sentences and conduct the human evaluation on the machine-generated responses. In addition, we conduct ablation studies to demonstrate the effectiveness of each component of our model. Furthermore, we apply our model to other dialogue datasets that only ground knowledge or persona to showcase its adaptability. Our code is available at https://github.com/dlawjddn803/BeCand.

pdf
CReTIHC: Designing Causal Reasoning Tasks about Temporal Interventions and Hallucinated Confoundings
Changwoo Chun | SongEun Lee | Jaehyung Seo | Heuiseok Lim
Findings of the Association for Computational Linguistics: EMNLP 2023

Large language models (LLMs) have demonstrated impressive capabilities in natural language processing. However, their ability to establish causal relationships, particularly in the context of temporal interventions and language hallucinations, remains challenging. This paper presents CReTIHC, a novel dataset designed to test and enhance the causal reasoning abilities of LLMs. The dataset is constructed using a unique approach that incorporates elements of verbal hallucinations and temporal interventions through the reengineering of existing causal inference datasets. This transformation creates complex scenarios that push LLMs to critically evaluate the information presented and identify cause-and-effect relationships. The CReTIHC dataset serves as a pioneering tool for improving LLM’s causal inference capabilities, paving the way for a more nuanced understanding of causal relationships in natural language processing (NLP) tasks. The whole dataset is publicly accessible at: (https://github.com/ChangwooChun/CReTIHC)

pdf
KEBAP: Korean Error Explainable Benchmark Dataset for ASR and Post-processing
Seonmin Koo | Chanjun Park | Jinsung Kim | Jaehyung Seo | Sugyeong Eo | Hyeonseok Moon | Heuiseok Lim
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing

Automatic Speech Recognition (ASR) systems are instrumental across various applications, with their performance being critically tied to user satisfaction. Conventional evaluation metrics for ASR systems produce a singular aggregate score, which is insufficient for understanding specific system vulnerabilities. Therefore, we aim to address the limitations of the previous ASR evaluation methods by introducing the Korean Error Explainable Benchmark Dataset for ASR and Post-processing (KEBAP). KEBAP enables comprehensive analysis of ASR systems at both speech- and text levels, thereby facilitating a more balanced assessment encompassing speech recognition accuracy and user readability. KEBAP provides 37 newly defined speech-level resources incorporating diverse noise environments and speaker characteristics categories, also presenting 13 distinct text-level error types. This paper demonstrates detailed statistical analyses of colloquial noise categories and textual error types. Furthermore, we conduct extensive validation and analysis on commercially deployed ASR systems, providing valuable insights into their performance. As a more fine-grained and real-world-centric evaluation method, KEBAP contributes to identifying and mitigating potential weaknesses in ASR systems.

pdf
Post-hoc Utterance Refining Method by Entity Mining for Faithful Knowledge Grounded Conversations
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

Despite the striking advances in recent language generation performance, model-generated responses have suffered from the chronic problem of hallucinations that are either untrue or unfaithful to a given source. Especially in the task of knowledge grounded conversation, the models are required to generate informative responses, but hallucinated utterances lead to miscommunication. In particular, entity-level hallucination that causes critical misinformation and undesirable conversation is one of the major concerns. To address this issue, we propose a post-hoc refinement method called REM. It aims to enhance the quality and faithfulness of hallucinated utterances by refining them based on the source knowledge. If the generated utterance has a low source-faithfulness score with the given knowledge, REM mines the key entities in the knowledge and implicitly uses them for refining the utterances. We verify that our method reduces entity hallucination in the utterance. Also, we show the adaptability and efficacy of REM with extensive experiments and generative results. Our code is available at https://github.com/YOONNAJANG/REM.

pdf
CHEF in the Language Kitchen: A Generative Data Augmentation Leveraging Korean Morpheme Ingredients
Jaehyung Seo | Hyeonseok Moon | Jaewook Lee | Sugyeong Eo | Chanjun Park | Heuiseok Lim
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing

Korean morphological variations present unique opportunities and challenges in natural language processing (NLP), necessitating an advanced understanding of morpheme-based sentence construction. The complexity of morphological variations allows for diverse sentence forms based on the syntactic-semantic integration of functional morphemes (i.e., affixes) to lexical morphemes (i.e., roots). With this in mind, we propose a method - CHEF, replicating the morphological transformations inherent in sentences based on lexical and functional morpheme combinations through generative data augmentation. CHEF operates using a morpheme blender and a label discriminator, thereby enhancing the diversity of Korean sentence forms by capturing the properties of agglutination while maintaining label consistency. We conduct experiments on Korean multiple classification datasets, improving model performance in full- and few-shot settings. Our proposed method boosts performance beyond the preceding data augmentation methods without incurring external data usage. We demonstrate that our approach achieves comparable results yielded by augmentation techniques that use large language models (LLMs).

pdf
Informative Evidence-guided Prompt-based Fine-tuning for English-Korean Critical Error Detection
DaHyun Jung | Sugyeong Eo | Chanjun Park | Hyeonseok Moon | Jaehyung Seo | Heuiseok Lim
Proceedings of the 13th International Joint Conference on Natural Language Processing and the 3rd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)

pdf
Analysis of Utterance Embeddings and Clustering Methods Related to Intent Induction for Task-Oriented Dialogue
Jeiyoon Park | Yoonna Jang | Chanhee Lee | Heuiseok Lim
Proceedings of The Eleventh Dialog System Technology Challenge

The focus of this work is to investigate unsupervised approaches to overcome quintessential challenges in designing task-oriented dialog schema: assigning intent labels to each dialog turn (intent clustering) and generating a set of intents based on the intent clustering methods (intent induction). We postulate there are two salient factors for automatic induction of intents: (1) clustering algorithm for intent labeling and (2) user utterance embedding space. We compare existing off-the-shelf clustering models and embeddings based on DSTC11 evaluation. Our extensive experiments demonstrate that the combined selection of utterance embedding and clustering method in the intent induction task should be carefully considered. We also present that pretrained MiniLM with Agglomerative clustering shows significant improvement in NMI, ARI, F1, accuracy and example coverage in intent induction tasks. The source codes are available at https://github.com/Jeiyoon/dstc11-track2.

pdf
Improving Formality-Sensitive Machine Translation Using Data-Centric Approaches and Prompt Engineering
Seungjun Lee | Hyeonseok Moon | Chanjun Park | Heuiseok Lim
Proceedings of the 20th International Conference on Spoken Language Translation (IWSLT 2023)

In this paper, we present the KU x Upstage team’s submission for the Special Task on Formality Control on Spoken Language Translation, which involves translating English into four languages with diverse grammatical formality markers. Our methodology comprises two primary components: 1) a language-specific data-driven approach, and 2) the generation of synthetic data through the employment of large-scale language models and empirically-grounded prompt engineering. By adapting methodologies and models to accommodate the unique linguistic properties of each language, we observe a notable enhancement in performance relative to the baseline, substantiating the heightened efficacy of data-driven approaches. Moreover, our devised prompt engineering strategy yields superior synthetic translation instances.

pdf
PEEP-Talk: A Situational Dialogue-based Chatbot for English Education
Seungjun Lee | Yoonna Jang | Chanjun Park | Jungseob Lee | Jaehyung Seo | Hyeonseok Moon | Sugyeong Eo | Seounghoon Lee | Bernardo Yahya | Heuiseok Lim
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations)

English is acknowledged worldwide as a mode of communication. However, due to the absence of realistic practicing scenarios, students learning English as a foreign language (EFL) typically have limited chances to converse and share feedback with others. In this paper, we propose PEEP-Talk, a real-world situational dialogue-based chatbot designed for English education. It also naturally switches to a new topic or situation in response to out-of-topic utterances, which are common among English beginners. Furthermore, PEEP-Talk provides feedback score on conversation and grammar error correction. We performed automatic and user evaluations to validate performance and education efficiency of our system. The results show that PEEP-Talk generates appropriate responses in various real-life situations while providing accurate feedback to learners. Moreover, we demonstrate a positive impact on English-speaking, grammar, and English learning anxiety, implying that PEEP-Talk can lower the barrier to learning natural conversation in effective ways.

2022

pdf
A Dog Is Passing Over The Jet? A Text-Generation Dataset for Korean Commonsense Reasoning and Evaluation
Jaehyung Seo | Seounghoon Lee | Chanjun Park | Yoonna Jang | Hyeonseok Moon | Sugyeong Eo | Seonmin Koo | Heuiseok Lim
Findings of the Association for Computational Linguistics: NAACL 2022

Recent natural language understanding (NLU) research on the Korean language has been vigorously maturing with the advancements of pretrained language models and datasets. However, Korean pretrained language models still struggle to generate a short sentence with a given condition based on compositionality and commonsense reasoning (i.e., generative commonsense reasoning). The two major challenges are inadequate data resources to develop generative commonsense reasoning regarding Korean linguistic features and to evaluate language models which are necessary for natural language generation (NLG). To solve these problems, we propose a text-generation dataset for Korean generative commonsense reasoning and language model evaluation. In this work, a semi-automatic dataset construction approach filters out contents inexplicable to commonsense, ascertains quality, and reduces the cost of building the dataset. We also present an in-depth analysis of the generation results of language models with various evaluation metrics along with human-annotated scores. The whole dataset is publicly available at (https://aihub.or.kr/opendata/korea-university).

pdf
You Truly Understand What I Need : Intellectual and Friendly Dialog Agents grounding Persona and Knowledge
Jungwoo Lim | Myunghoon Kang | Yuna Hur | Seung Won Jeong | Jinsung Kim | Yoonna Jang | Dongyub Lee | Hyesung Ji | DongHoon Shin | Seungryong Kim | Heuiseok Lim
Findings of the Association for Computational Linguistics: EMNLP 2022

To build a conversational agent that interacts fluently with humans, previous studies blend knowledge or personal profile into the pre-trained language model. However, the model that considers knowledge and persona at the same time is still limited, leading to hallucination and a passive way of using personas. We propose an effective dialogue agent that grounds external knowledge and persona simultaneously. The agent selects the proper knowledge and persona to use for generating the answers with our candidate scoring implemented with a poly-encoder. Then, our model generates the utterance with lesser hallucination and more engagingness utilizing retrieval augmented generation with knowledge-persona enhanced query. We conduct experiments on the persona-knowledge chat and achieve state-of-the-art performance in grounding and generation tasks on the automatic metrics. Moreover, we validate the answers from the models regarding hallucination and engagingness through human evaluation and qualitative results. We show our retriever’s effectiveness in extracting relevant documents compared to the other previous retrievers, along with the comparison of multiple candidate scoring methods. Code is available at https://github.com/dlawjddn803/INFO

pdf
PicTalky: Augmentative and Alternative Communication for Language Developmental Disabilities
Chanjun Park | Yoonna Jang | Seolhwa Lee | Jaehyung Seo | Kisu Yang | Heuiseok Lim
Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing: System Demonstrations

Children with language disabilities face communication difficulties in daily life. They are often deprived of the opportunity to participate in social activities due to their difficulty in understanding or using natural language. In this regard, Augmentative and Alternative Communication (AAC) can be a practical means of communication for children with language disabilities. In this study, we propose PicTalky, which is an AI-based AAC system that helps children with language developmental disabilities to improve their communication skills and language comprehension abilities. PicTalky can process both text and pictograms more accurately by connecting a series of neural-based NLP modules. Additionally, we perform quantitative and qualitative analyses on the modules of PicTalky. By using this service, it is expected that those suffering from language problems will be able to express their intentions or desires more easily and improve their quality of life. We have made the models freely available alongside a demonstration of the web interface. Furthermore, we implemented robotics AAC for the first time by applying PicTalky to the NAO robot.

pdf
KU X Upstage’s Submission for the WMT22 Quality Estimation: Critical Error Detection Shared Task
Sugyeong Eo | Chanjun Park | Hyeonseok Moon | Jaehyung Seo | Heuiseok Lim
Proceedings of the Seventh Conference on Machine Translation (WMT)

This paper presents KU X Upstage’s submission to the quality estimation (QE): critical error detection (CED) shared task in WMT22. We leverage the XLM-RoBERTa large model without utilizing any additional parallel data. To the best of our knowledge, we apply prompt-based fine-tuning to the QE task for the first time. To maximize the model’s language understanding capability, we reformulate the CED task to be similar to the masked language model objective, which is a pre-training strategy of the language model. We design intuitive templates and label words, and include auxiliary descriptions such as demonstration or Google Translate results in the input sequence. We further improve the performance through the template ensemble, and as a result of the shared task, our approach achieve the best performance for both English-German and Portuguese-English language pairs in an unconstrained setting.

pdf
Priming Ancient Korean Neural Machine Translation
Chanjun Park | Seolhwa Lee | Jaehyung Seo | Hyeonseok Moon | Sugyeong Eo | Heuiseok Lim
Proceedings of the Thirteenth Language Resources and Evaluation Conference

In recent years, there has been an increasing need for the restoration and translation of historical languages. In this study, we attempt to translate historical records in ancient Korean language based on neural machine translation (NMT). Inspired by priming, a cognitive science theory that two different stimuli influence each other, we propose novel priming ancient-Korean NMT (AKNMT) using bilingual subword embedding initialization with structural property awareness in the ancient documents. Finally, we obtain state-of-the-art results in the AKNMT task. To the best of our knowledge, we confirm the possibility of developing a human-centric model that incorporates the concepts of cognitive science and analyzes the result from the perspective of interference and cognitive dissonance theory for the first time.

pdf
Empirical Analysis of Noising Scheme based Synthetic Data Generation for Automatic Post-editing
Hyeonseok Moon | Chanjun Park | Seolhwa Lee | Jaehyung Seo | Jungseob Lee | Sugyeong Eo | Heuiseok Lim
Proceedings of the Thirteenth Language Resources and Evaluation Conference

Automatic post-editing (APE) refers to a research field that aims to automatically correct errors included in the translation sentences derived by the machine translation system. This study has several limitations, considering the data acquisition, because there is no official dataset for most language pairs. Moreover, the amount of data is restricted even for language pairs in which official data has been released, such as WMT. To solve this problem and promote universal APE research regardless of APE data existence, this study proposes a method for automatically generating APE data based on a noising scheme from a parallel corpus. Particularly, we propose a human mimicking errors-based noising scheme that considers a practical correction process at the human level. We propose a precise inspection to attain high performance, and we derived the optimal noising schemes that show substantial effectiveness. Through these, we also demonstrate that depending on the type of noise, the noising scheme-based APE data generation may lead to inferior performance. In addition, we propose a dynamic noise injection strategy that enables the acquisition of a robust error correction capability and demonstrated its effectiveness by comparative analysis. This study enables obtaining a high performance APE model without human-generated data and can promote universal APE research for all language pairs targeting English.

pdf
FreeTalky: Don’t Be Afraid! Conversations Made Easier by a Humanoid Robot using Persona-based Dialogue
Chanjun Park | Yoonna Jang | Seolhwa Lee | Sungjin Park | Heuiseok Lim
Proceedings of the Thirteenth Language Resources and Evaluation Conference

We propose a deep learning-based foreign language learning platform, named FreeTalky, for people who experience anxiety dealing with foreign languages, by employing a humanoid robot NAO and various deep learning models. A persona-based dialogue system that is embedded in NAO provides an interesting and consistent multi-turn dialogue for users. Also, an grammar error correction system promotes improvement in grammar skills of the users. Thus, our system enables personalized learning based on persona dialogue and facilitates grammar learning of a user using grammar error feedback. Furthermore, we verified whether FreeTalky provides practical help in alleviating xenoglossophobia by replacing the real human in the conversation with a NAO robot, through human evaluation.

pdf bib
Proceedings of the 1st Workshop on Customized Chat Grounding Persona and Knowledge
Heuiseok Lim | Seungryong Kim | Yeonsoo Lee | Steve Lin | Paul Hongsuck Seo | Yumin Suh | Yoonna Jang | Jungwoo Lim | Yuna Hur | Suhyune Son
Proceedings of the 1st Workshop on Customized Chat Grounding Persona and Knowledge

pdf bib
Focus on FoCus: Is FoCus focused on Context, Knowledge and Persona?
SeungYoon Lee | Jungseob Lee | Chanjun Park | Sugyeong Eo | Hyeonseok Moon | Jaehyung Seo | Jeongbae Park | Heuiseok Lim
Proceedings of the 1st Workshop on Customized Chat Grounding Persona and Knowledge

Rather than continuing the conversation based on personalized or implicit information, the existing conversation system generates dialogue by focusing only on the superficial content. To solve this problem, FoCus was recently released. FoCus is a persona-knowledge grounded dialogue generation dataset that leverages Wikipedia’s knowledge and personal persona, focusing on the landmarks provided by Google, enabling user-centered conversation. However, a closer empirical study is needed since research in the field is still in its early stages. Therefore, we fling two research questions about FoCus. “Is the FoCus whether for conversation or question answering?” to identify the structural problems of the dataset. “Does the FoCus model do real knowledge blending?” to closely demonstrate that the model acquires actual knowledge. As a result of the experiment, we present that the FoCus model could not correctly blend the knowledge according to the input dialogue and that the dataset design is unsuitable for the multi-turn conversation.

pdf
GRASP: Guiding Model with RelAtional Semantics Using Prompt for Dialogue Relation Extraction
Junyoung Son | Jinsung Kim | Jungwoo Lim | Heuiseok Lim
Proceedings of the 29th International Conference on Computational Linguistics

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.

pdf
KoCHET: A Korean Cultural Heritage Corpus for Entity-related Tasks
Gyeongmin Kim | Jinsung Kim | Junyoung Son | Heuiseok Lim
Proceedings of the 29th International Conference on Computational Linguistics

As digitized traditional cultural heritage documents have rapidly increased, resulting in an increased need for preservation and management, practical recognition of entities and typification of their classes has become essential. To achieve this, we propose KoCHET - a Korean cultural heritage corpus for the typical entity-related tasks, i.e., named entity recognition (NER), relation extraction (RE), and entity typing (ET). Advised by cultural heritage experts based on the data construction guidelines of government-affiliated organizations, KoCHET consists of respectively 112,362, 38,765, 113,198 examples for NER, RE, and ET tasks, covering all entity types related to Korean cultural heritage. Moreover, unlike the existing public corpora, modified redistribution can be allowed both domestic and foreign researchers. Our experimental results make the practical usability of KoCHET more valuable in terms of cultural heritage. We also provide practical insights of KoCHET in terms of statistical and linguistic analysis. Our corpus is freely available at https://github.com/Gyeongmin47/KoCHET.

pdf
Don’t Judge a Language Model by Its Last Layer: Contrastive Learning with Layer-Wise Attention Pooling
Dongsuk Oh | Yejin Kim | Hodong Lee | H. Howie Huang | Heuiseok Lim
Proceedings of the 29th International Conference on Computational Linguistics

Recent pre-trained language models (PLMs) achieved great success on many natural language processing tasks through learning linguistic features and contextualized sentence representation. Since attributes captured in stacked layers of PLMs are not clearly identified, straightforward approaches such as embedding the last layer are commonly preferred to derive sentence representations from PLMs. This paper introduces the attention-based pooling strategy, which enables the model to preserve layer-wise signals captured in each layer and learn digested linguistic features for downstream tasks. The contrastive learning objective can adapt the layer-wise attention pooling to both unsupervised and supervised manners. It results in regularizing the anisotropic space of pre-trained embeddings and being more uniform. We evaluate our model on standard semantic textual similarity (STS) and semantic search tasks. As a result, our method improved the performance of the base contrastive learned BERTbase and variants.

pdf
QUAK: A Synthetic Quality Estimation Dataset for Korean-English Neural Machine Translation
Sugyeong Eo | Chanjun Park | Hyeonseok Moon | Jaehyung Seo | Gyeongmin Kim | Jungseob Lee | Heuiseok Lim
Proceedings of the 29th International Conference on Computational Linguistics

With the recent advance in neural machine translation demonstrating its importance, research on quality estimation (QE) has been steadily progressing. QE aims to automatically predict the quality of machine translation (MT) output without reference sentences. Despite its high utility in the real world, there remain several limitations concerning manual QE data creation: inevitably incurred non-trivial costs due to the need for translation experts, and issues with data scaling and language expansion. To tackle these limitations, we present QUAK, a Korean-English synthetic QE dataset generated in a fully automatic manner. This consists of three sub-QUAK datasets QUAK-M, QUAK-P, and QUAK-H, produced through three strategies that are relatively free from language constraints. Since each strategy requires no human effort, which facilitates scalability, we scale our data up to 1.58M for QUAK-P, H and 6.58M for QUAK-M. As an experiment, we quantitatively analyze word-level QE results in various ways while performing statistical analysis. Moreover, we show that datasets scaled in an efficient way also contribute to performance improvements by observing meaningful performance gains in QUAK-M, P when adding data up to 1.58M.

2021

pdf
Two Heads are Better than One? Verification of Ensemble Effect in Neural Machine Translation
Chanjun Park | Sungjin Park | Seolhwa Lee | Taesun Whang | Heuiseok Lim
Proceedings of the Second Workshop on Insights from Negative Results in NLP

In the field of natural language processing, ensembles are broadly known to be effective in improving performance. This paper analyzes how ensemble of neural machine translation (NMT) models affect performance improvement by designing various experimental setups (i.e., intra-, inter-ensemble, and non-convergence ensemble). To an in-depth examination, we analyze each ensemble method with respect to several aspects such as different attention models and vocab strategies. Experimental results show that ensembling is not always resulting in performance increases and give noteworthy negative findings.

pdf
Should we find another model?: Improving Neural Machine Translation Performance with ONE-Piece Tokenization Method without Model Modification
Chanjun Park | Sugyeong Eo | Hyeonseok Moon | Heuiseok Lim
Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Industry Papers

Most of the recent Natural Language Processing(NLP) studies are based on the Pretrain-Finetuning Approach (PFA), but in small and medium-sized enterprises or companies with insufficient hardware there are many limitations to servicing NLP application software using such technology due to slow speed and insufficient memory. The latest PFA technologies require large amounts of data, especially for low-resource languages, making them much more difficult to work with. We propose a new tokenization method, ONE-Piece, to address this limitation that combines the morphology-considered subword tokenization method and the vocabulary method used after probing for an existing method that has not been carefully considered before. Our proposed method can also be used without modifying the model structure. We experiment by applying ONE-Piece to Korean, a morphologically-rich and low-resource language. We derive an optimal subword tokenization result for Korean-English machine translation by conducting a case study that combines the subword tokenization method, morphological segmentation, and vocabulary method. Through comparative experiments with all the tokenization methods currently used in NLP research, ONE-Piece achieves performance comparable to the current Korean-English machine translation state-of-the-art model.

pdf bib
Dealing with the Paradox of Quality Estimation
Sugyeong Eo | Chanjun Park | Hyeonseok Moon | Jaehyung Seo | Heuiseok Lim
Proceedings of the 4th Workshop on Technologies for MT of Low Resource Languages (LoResMT2021)

In quality estimation (QE), the quality of translation can be predicted by referencing the source sentence and the machine translation (MT) output without access to the reference sentence. However, there exists a paradox in that constructing a dataset for creating a QE model requires non-trivial human labor and time, and it may even requires additional effort compared to the cost of constructing a parallel corpus. In this study, to address this paradox and utilize the various applications of QE, even in low-resource languages (LRLs), we propose a method for automatically constructing a pseudo-QE dataset without using human labor. We perform a comparative analysis on the pseudo-QE dataset using multilingual pre-trained language models. As we generate the pseudo dataset, we conduct experiments using various external machine translators as test sets to verify the accuracy of the results objectively. Also, the experimental results show that multilingual BART demonstrates the best performance, and we confirm the applicability of QE in LRLs using pseudo-QE dataset construction methods.

pdf
Capturing Speaker Incorrectness: Speaker-Focused Post-Correction for Abstractive Dialogue Summarization
Dongyub Lee | Jungwoo Lim | Taesun Whang | Chanhee Lee | Seungwoo Cho | Mingun Park | Heuiseok Lim
Proceedings of the Third Workshop on New Frontiers in Summarization

In this paper, we focus on improving the quality of the summary generated by neural abstractive dialogue summarization systems. Even though pre-trained language models generate well-constructed and promising results, it is still challenging to summarize the conversation of multiple participants since the summary should include a description of the overall situation and the actions of each speaker. This paper proposes self-supervised strategies for speaker-focused post-correction in abstractive dialogue summarization. Specifically, our model first discriminates which type of speaker correction is required in a draft summary and then generates a revised summary according to the required type. Experimental results show that our proposed method adequately corrects the draft summaries, and the revised summaries are significantly improved in both quantitative and qualitative evaluations.

pdf
BTS: Back TranScription for Speech-to-Text Post-Processor using Text-to-Speech-to-Text
Chanjun Park | Jaehyung Seo | Seolhwa Lee | Chanhee Lee | Hyeonseok Moon | Sugyeong Eo | Heuiseok Lim
Proceedings of the 8th Workshop on Asian Translation (WAT2021)

With the growing popularity of smart speakers, such as Amazon Alexa, speech is becoming one of the most important modes of human-computer interaction. Automatic speech recognition (ASR) is arguably the most critical component of such systems, as errors in speech recognition propagate to the downstream components and drastically degrade the user experience. A simple and effective way to improve the speech recognition accuracy is to apply automatic post-processor to the recognition result. However, training a post-processor requires parallel corpora created by human annotators, which are expensive and not scalable. To alleviate this problem, we propose Back TranScription (BTS), a denoising-based method that can create such corpora without human labor. Using a raw corpus, BTS corrupts the text using Text-to-Speech (TTS) and Speech-to-Text (STT) systems. Then, a post-processing model can be trained to reconstruct the original text given the corrupted input. Quantitative and qualitative evaluations show that a post-processor trained using our approach is highly effective in fixing non-trivial speech recognition errors such as mishandling foreign words. We present the generated parallel corpus and post-processing platform to make our results publicly available.

2020

pdf
I Know What You Asked: Graph Path Learning using AMR for Commonsense Reasoning
Jungwoo Lim | Dongsuk Oh | Yoonna Jang | Kisu Yang | Heuiseok Lim
Proceedings of the 28th International Conference on Computational Linguistics

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.

2018

pdf
Rich Character-Level Information for Korean Morphological Analysis and Part-of-Speech Tagging
Andrew Matteson | Chanhee Lee | Youngbum Kim | Heuiseok Lim
Proceedings of the 27th International Conference on Computational Linguistics

Due to the fact that Korean is a highly agglutinative, character-rich language, previous work on Korean morphological analysis typically employs the use of sub-character features known as graphemes or otherwise utilizes comprehensive prior linguistic knowledge (i.e., a dictionary of known morphological transformation forms, or actions). These models have been created with the assumption that character-level, dictionary-less morphological analysis was intractable due to the number of actions required. We present, in this study, a multi-stage action-based model that can perform morphological transformation and part-of-speech tagging using arbitrary units of input and apply it to the case of character-level Korean morphological analysis. Among models that do not employ prior linguistic knowledge, we achieve state-of-the-art word and sentence-level tagging accuracy with the Sejong Korean corpus using our proposed data-driven Bi-LSTM model.

pdf
Character-Level Feature Extraction with Densely Connected Networks
Chanhee Lee | Young-Bum Kim | Dongyub Lee | Heuiseok Lim
Proceedings of the 27th International Conference on Computational Linguistics

Generating character-level features is an important step for achieving good results in various natural language processing tasks. To alleviate the need for human labor in generating hand-crafted features, methods that utilize neural architectures such as Convolutional Neural Network (CNN) or Recurrent Neural Network (RNN) to automatically extract such features have been proposed and have shown great results. However, CNN generates position-independent features, and RNN is slow since it needs to process the characters sequentially. In this paper, we propose a novel method of using a densely connected network to automatically extract character-level features. The proposed method does not require any language or task specific assumptions, and shows robustness and effectiveness while being faster than CNN- or RNN-based methods. Evaluating this method on three sequence labeling tasks - slot tagging, Part-of-Speech (POS) tagging, and Named-Entity Recognition (NER) - we obtain state-of-the-art performance with a 96.62 F1-score and 97.73% accuracy on slot tagging and POS tagging, respectively, and comparable performance to the state-of-the-art 91.13 F1-score on NER.

2003

pdf
A Syllable Based Word Recognition Model for Korean Noun Extraction
Do-Gil Lee | Hae-Chang Rim | Heui-Seok Lim
Proceedings of the 41st Annual Meeting of the Association for Computational Linguistics

2002

pdf
Automatic Word Spacing Using Hidden Markov Model for Refining Korean Text Corpora
Do-Gil Lee | Sang-Zoo Lee | Hae-Chang Rim | Heui-Seok Lim
COLING-02: The 3rd Workshop on Asian Language Resources and International Standardization

2000

pdf
KCAT: A Korean Corpus Annotating Tool Minimizing Human Intervention
Won-He Ryu | Jin-Dong Kim | Hae-Chang Rim | Heui-Seok Lim
COLING 2000 Volume 2: The 18th International Conference on Computational Linguistics