Author name cluster

Seung-won Hwang

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

24 papers

2 author rows

NeurIPS Conference 2025 Conference Paper

AcuRank: Uncertainty-Aware Adaptive Computation for Listwise Reranking

Soyoung Yoon
Gyuwan Kim
Gyu-Hwung Cho
Seung-won Hwang

Listwise reranking with large language models (LLMs) enhances top-ranked results in retrieval-based applications. Due to the limit in context size and high inference cost of long context, reranking is typically performed over a fixed size of small subsets, with the final ranking aggregated from these partial results. This fixed computation disregards query difficulty and document distribution, leading to inefficiencies. We propose AcuRank, an adaptive reranking framework that dynamically adjusts both the amount and target of computation based on uncertainty estimates over document relevance. Using a Bayesian TrueSkill model, we iteratively refine relevance estimates until reaching sufficient confidence levels, and our explicit modeling of ranking uncertainty enables principled control over reranking behavior and avoids unnecessary updates to confident predictions. Results on the TREC-DL and BEIR benchmarks show that our method consistently achieves a superior accuracy–efficiency trade-off and scales better with compute than fixed-computation baselines. These results highlight the effectiveness and generalizability of our method across diverse retrieval tasks and LLM-based reranking models.

ICLR Conference 2025 Conference Paper

ConvCodeWorld: Benchmarking Conversational Code Generation in Reproducible Feedback Environments

Hojae Han
Seung-won Hwang
Rajhans Samdani
Yuxiong He

Large language models (LLMs) have proven invaluable for code generation, particularly in interactive settings. However, existing code generation benchmarks fail to capture the diverse feedback encountered in multi-turn interactions, limiting our ability to evaluate LLMs in these contexts. To address this gap, we present a set of novel benchmarks that explicitly model the quality of feedback provided to code generation LLMs. Our contributions are threefold: **First**, we introduce CONVCODEWORLD, a novel and reproducible environment for benchmarking interactive code generation. CONVCODEWORLD simulates 9 distinct interactive code generation scenarios while systematically combining three types of feedback: (a) compilation feedback; (b) execution feedback with varying test coverage; (c) verbal feedback generated by GPT-4o with different levels of expertise. **Second**, we introduce CONVCODEBENCH, a fast, static version of benchmark that uses pre-generated feedback logs, eliminating the need for costly dynamic verbal feedback generation while maintaining strong Spearman’s rank correlations (0.82 to 0.99) with CONVCODEWORLD. **Third**, extensive evaluations of both closed-source and open-source LLMs including R1-Distill on CONVCODEWORLD reveal key insights: (a) LLM performance varies significantly based on the feedback provided; (b) Weaker LLMs, with sufficient feedback, can outperform single-turn results of state-of-the-art LLMs without feedback; (c) Training on a specific feedback combination can limit an LLM’s ability to utilize unseen combinations; (d) LLMs solve problems in fewer turns (high MRR) may not solve as many problems overall (high Recall), and vice versa. All implementations and benchmarks will be made publicly available at https://huggingface.co/spaces/ConvCodeWorld/ConvCodeWorld

AAAI Conference 2025 Conference Paper

HLMEA: Unsupervised Entity Alignment Based on Hybrid Language Models

Xiongnan Jin
Zhilin Wang
Jinpeng Chen
Liu Yang
Byungkook Oh
Seung-won Hwang
Jianqiang Li

Entity alignment (EA) is crucial for integrating knowledge graphs (KGs) constructed from diverse sources. Conventional unsupervised EA approaches attempt to eliminate human intervention but often suffer from accuracy limitations. With the rise of large language models (LLMs), leveraging their capabilities for EA presents a promising direction. However, it introduces new challenges: formulating the LLM-based EA problem and extracting the background knowledge in LLMs to realize EA without human intervention. This paper proposes HLMEA, a novel hybrid language model-based unsupervised EA method. HLMEA formulates the EA task into a filtering and single-choice problem and synergistically integrates small language models (SLMs) and LLMs. Specifically, SLMs filter candidate entities based on textual representations generated from KG triples. Then, LLMs refine this selection to identify the most semantically aligned entities. An iterative self-training mechanism allows SLMs to distill knowledge from LLM outputs, enhancing the EA ability of hybrid language models in subsequent rounds cooperatively. We also conducted extensive experiments on benchmark datasets to evaluate HLMEA's performance. The results demonstrate that HLMEA significantly outperforms unsupervised and even supervised EA baselines, proving its potential for scalable and effective EA across large KGs. The code and data are available at \url{https://github.com/xnjin-ai/HLMEA}.

PDF Details DOI

AAAI Conference 2023 Conference Paper

Script, Language, and Labels: Overcoming Three Discrepancies for Low-Resource Language Specialization

Jaeseong Lee
Dohyeon Lee
Seung-won Hwang

Although multilingual pretrained models (mPLMs) enabled support of various natural language processing in diverse languages, its limited coverage of 100+ languages lets 6500+ languages remain ‘unseen’. One common approach for an unseen language is specializing the model for it as target, by performing additional masked language modeling (MLM) with the target language corpus. However, we argue that, due to the discrepancy from multilingual MLM pretraining, a naive specialization as such can be suboptimal. Specifically, we pose three discrepancies to overcome. Script and linguistic discrepancy of the target language from the related seen languages, hinder a positive transfer, for which we propose to maximize representation similarity, unlike existing approaches maximizing overlaps. In addition, label space for MLM prediction can vary across languages, for which we propose to reinitialize top layers for a more effective adaptation. Experiments over four different language families and three tasks shows that our method improves the task performance of unseen languages with statistical significance, while previous approach fails to.

PDF Details DOI

AAAI Conference 2022 Conference Paper

C2L: Causally Contrastive Learning for Robust Text Classification

Seungtaek Choi
Myeongho Jeong
Hojae Han
Seung-won Hwang

Despite the super-human accuracy of recent deep models in NLP tasks, their robustness is reportedly limited due to their reliance on spurious patterns. We thus aim to leverage contrastive learning and counterfactual augmentation for robustness. For augmentation, existing work either requires humans to add counterfactuals to the dataset or machines to automatically matches near-counterfactuals already in the dataset. Unlike existing augmentation is affected by spurious correlations, ours, by synthesizing “a set” of counterfactuals, and making a collective decision on the distribution of predictions on this set, can robustly supervise the causality of each term. Our empirical results show that our approach, by collective decisions, is less sensitive to task model bias of attribution-based synthesis, and thus achieves significant improvements, in diverse dimensions: 1) counterfactual robustness, 2) cross-domain generalization, and 3) generalization from scarce data.

AAAI Conference 2022 Conference Paper

Dual Task Framework for Improving Persona-Grounded Dialogue Dataset

Minju Kim
Beong-woo Kwak
Youngwook Kim
Hong-in Lee
Seung-won Hwang
Jinyoung Yeo

This paper introduces a simple yet effective data-centric approach for the task of improving persona-conditioned dialogue agents. Prior model-centric approaches unquestioningly depend on the raw crowdsourced benchmark datasets such as Persona-Chat. In contrast, we aim to fix annotation artifacts in benchmarking, which is orthogonally applicable to any dialogue model. Specifically, we augment relevant personas to improve dialogue dataset/agent, by leveraging the primal-dual structure of the two tasks, predicting dialogue responses and personas based on each other. Experiments on Persona-Chat show that our approach outperforms pretrained LMs by an 11. 7 point gain in terms of accuracy.

AAAI Conference 2022 Conference Paper

TrustAL: Trustworthy Active Learning Using Knowledge Distillation

Beong-woo Kwak
Youngwook Kim
Yu Jin Kim
Seung-won Hwang
Jinyoung Yeo

Active learning can be defined as iterations of data labeling, model training, and data acquisition, until sufficient labels are acquired. A traditional view of data acquisition is that, through iterations, knowledge from human labels and models is implicitly distilled to monotonically increase the accuracy and label consistency. Under this assumption, the most recently trained model is a good surrogate for the current labeled data, from which data acquisition is requested based on uncertainty/diversity. Our contribution is debunking this myth and proposing a new objective for distillation. First, we found example forgetting, which indicates the loss of knowledge learned across iterations. Second, for this reason, the last model is no longer the best teacher– For mitigating such forgotten knowledge, we select one of its predecessor models as a teacher, by our proposed notion of “consistency”. We show that this novel distillation is distinctive in the following three aspects; First, consistency ensures to avoid forgetting labels. Second, consistency improves both uncertainty/diversity of labeled data. Lastly, consistency redeems defective labels produced by human annotators.

AAAI Conference 2020 Conference Paper

Segment-Then-Rank: Non-Factoid Question Answering on Instructional Videos

Kyungjae Lee
Nan Duan
Lei Ji
Jason Li
Seung-won Hwang

We study the problem of non-factoid QA on instructional videos. Existing work focuses either on visual or textual modality of video content, to ﬁnd matching answers to the question. However, neither is ﬂexible enough for our problem setting of non-factoid answers with varying lengths. Motivated by this, we propose a two-stage model: (a) multimodal segmentation of video into span candidates and (b) lengthadaptive ranking of the candidates to the question. First, for segmentation, we propose Segmenter for generating span candidates of diverse length, considering both textual and visual modality. Second, for ranking, we propose Ranker to score the candidates, dynamically combining the two models with complementary strength for both short and long spans respectively. Experimental result demonstrates that our model achieves state-of-the-art performance.

AAAI Conference 2019 Conference Paper

AutoSense Model for Word Sense Induction

Reinald Kim Amplayo
Seung-won Hwang
Min Song

Word sense induction (WSI), or the task of automatically discovering multiple senses or meanings of a word, has three main challenges: domain adaptability, novel sense detection, and sense granularity flexibility. While current latent variable models are known to solve the first two challenges, they are not flexible to different word sense granularities, which differ very much among words, from aardvark with one sense, to play with over 50 senses. Current models either require hyperparameter tuning or nonparametric induction of the number of senses, which we find both to be ineffective. Thus, we aim to eliminate these requirements and solve the sense granularity problem by proposing AutoSense, a latent variable model based on two observations: (1) senses are represented as a distribution over topics, and (2) senses generate pairings between the target word and its neighboring word. These observations alleviate the problem by (a) throwing garbage senses and (b) additionally inducing fine-grained word senses. Results show great improvements over the stateof-the-art models on popular WSI datasets. We also show that AutoSense is able to learn the appropriate sense granularity of a word. Finally, we apply AutoSense to the unsupervised author name disambiguation task where the sense granularity problem is more evident and show that AutoSense is evidently better than competing models. We share our data and code here: https: //github. com/rktamplayo/AutoSense.

AAAI Conference 2019 Conference Paper

Paraphrase Diversification Using Counterfactual Debiasing

Sunghyun Park
Seung-won Hwang
Fuxiang Chen
Jaegul Choo
Jung-Woo Ha
Sunghun Kim
Jinyeong Yim

The problem of generating a set of diverse paraphrase sentences while (1) not compromising the original meaning of the original sentence, and (2) imposing diversity in various semantic aspects, such as a lexical or syntactic structure, is examined. Existing work on paraphrase generation has focused more on the former, and the latter was trained as a fixed style transfer, such as transferring from positive to negative sentiments, even at the cost of losing semantics. In this work, we consider style transfer as a means of imposing diversity, with a paraphrasing correctness constraint that the target sentence must remain a paraphrase of the original sentence. However, our goal is to maximize the diversity for a set of k generated paraphrases, denoted as the diversified paraphrase (DP) problem. Our key contribution is deciding the style guidance at generation towards the direction of increasing the diversity of output with respect to those generated previously. As pre-materializing training data for all style decisions is impractical, we train with biased data, but with debiasing guidance. Compared to state-of-the-art methods, our proposed model can generate more diverse and yet semantically consistent paraphrase sentences. That is, our model, trained with the MSCOCO dataset, achieves the highest embedding scores, .94/. 95/. 86, similar to state-of-the-art results, but with a lower mBLEU score (more diverse) by 8. 73%.

AAAI Conference 2019 System Paper

QADiver: Interactive Framework for Diagnosing QA Models

Gyeongbok Lee
Sungdong Kim
Seung-won Hwang

Question answering (QA) extracting answers from text to the given question in natural language, has been actively studied and existing models have shown a promise of outperforming human performance when trained and evaluated with SQuAD dataset. However, such performance may not be replicated in the actual setting, for which we need to diagnose the cause, which is non-trivial due to the complexity of model. We thus propose a web-based UI that provides how each model contributes to QA performances, by integrating visualization and analysis tools for model explanation. We expect this framework can help QA model researchers to refine and improve their models.

AAAI Conference 2018 Conference Paper

Machine-Translated Knowledge Transfer for Commonsense Causal Reasoning

Jinyoung Yeo
Geungyu Wang
Hyunsouk Cho
Seungtaek Choi
Seung-won Hwang

This paper studies the problem of multilingual causal reasoning in resource-poor languages. Existing approaches, translating into the most probable resource-rich language such as English, suffer in the presence of translation and language gaps between different cultural area, which leads to the loss of causality. To overcome these challenges, our goal is thus to identify key techniques to construct a new causality network of cause-effect terms, targeted for the machinetranslated English, but without any language-speciﬁc knowledge of resource-poor languages. In our evaluations with three languages, Korean, Chinese, and French, our proposed method consistently outperforms all baselines, achieving upto 69. 0% reasoning accuracy, which is close to the state-ofthe-art accuracy 70. 2% achieved on English.

IJCAI Conference 2018 Conference Paper

Translations as Additional Contexts for Sentence Classification

Reinald Kim Amplayo
Kyungjae Lee
Jinyoung Yeo
Seung-won Hwang

In sentence classification tasks, additional contexts, such as the neighboring sentences, may improve the accuracy of the classifier. However, such contexts are domain-dependent and thus cannot be used for another classification task with an inappropriate domain. In contrast, we propose the use of translated sentences as domain-free context that is always available regardless of the domain. We find that naive feature expansion of translations gains only marginal improvements and may decrease the performance of the classifier, due to possible inaccurate translations thus producing noisy sentence vectors. To this end, we present multiple context fixing attachment (MCFA), a series of modules attached to multiple sentence vectors to fix the noise in the vectors using the other sentence vectors as context. We show that our method performs competitively compared to previous models, achieving best classification performance on multiple data sets. We are the first to use translations as domain-free contexts for sentence classification.

IJCAI Conference 2017 Conference Paper

Entity Suggestion with Conceptual Expanation

Yi Zhang
Yanghua Xiao
Seung-won Hwang
Haixun Wang
X. Sean Wang
Wei Wang

Entity Suggestion with Conceptual Explanation (ESC) refers to a type of entity acquisition query in which a user provides a set of example entities as the query and obtains in return not only some related entities but also concepts which can best explain the query and the result. ESC is useful in many applications such as related-entity recommendation and query expansion. Many example based entity suggestion solutions are available in existing literatures. However, they are generally not aware of the concepts of query entities thus cannot be used for conceptual explanation. In this paper, we propose two probabilistic entity suggestion models and their computation solutions. Our models and solutions fully take advantage of the large scale taxonomies which consist of isA relations between entities and concepts. With our models and solutions, we can not only find the best entities to suggest but also derive the best concepts to explain the suggestion. Extensive evaluations on real data sets justify the accuracy of our models and the efficiency of our solutions.

AAAI Conference 2017 Conference Paper

Graph-Based Wrong IsA Relation Detection in a Large-Scale Lexical Taxonomy

Jiaqing Liang
Yanghua Xiao
Yi Zhang
Seung-won Hwang
Haixun Wang

Knowledge base(KB) plays an important role in artiﬁcial intelligence. Much effort has been taken to both manually and automatically construct web-scale knowledge bases. Comparing with manually constructed KBs, automatically constructed KB is broader but with more noises. In this paper, we study the problem of improving the quality for automatically constructed web-scale knowledge bases, in particular, lexical taxonomies of isA relationships. We ﬁnd that these taxonomies usually contain cycles, which are often introduced by incorrect isA relations. Inspired by this observation, we introduce two kinds of models to detect incorrect isA relations from cycles. The ﬁrst one eliminates cycles by extracting directed acyclic graphs, and the other one eliminates cycles by grouping nodes into different levels. We implement our models on Probase, a state-of-the-art, automatically constructed, web-scale taxonomy. After processing tens of millions of relations, our models eliminate 74 thousand wrong relations with 91% accuracy.

KR Conference 2016 Conference Paper

Commonsense Causal Reasoning between Short Texts

Zhiyi Luo
Yuchen Sha
Kenny Zhu
Seung-won Hwang
Zhongyuan Wang

Commonsense causal reasoning is the process of capturing and understanding the causal dependencies amongst events and actions. Such events and actions can be expressed in terms, phrases or sentences in natural language text. Therefore, one possible way of obtaining causal knowledge is by extracting causal relations between terms or phrases from a large text corpus. However, causal relations in text are sparse, ambiguous, and sometimes implicit, and thus difﬁcult to obtain. This paper attacks the problem of commonsense causality reasoning between short texts (phrases and sentences) using a data driven approach. We propose a framework that automatically harvests a network of causal-effect terms from a large web corpus. Backed by this network, we propose a novel and effective metric to properly model the causality strength between terms. We show these signals can be aggregated for causality reasonings between short texts, including sentences and phrases. In particular, our approach outperforms all previously reported results in the standard SEMEVAL COPA task by substantial margins.

AAAI Conference 2016 Conference Paper

Fine-Grained Semantic Conceptualization of FrameNet

Jin-woo Park
Seung-won Hwang
Haixun Wang

Understanding verbs is essential for many natural language tasks. To this end, large-scale lexical resources such as FrameNet have been manually constructed to annotate the semantics of verbs (frames) and their arguments (frame elements or FEs) in example sentences. Our goal is to “semantically conceptualize” example sentences by connecting FEs to knowledge base (KB) concepts. For example, connecting Employer FE to company concept in the KB enables the understanding that any (unseen) company can also be FE examples. However, a naive adoption of existing KB conceptualization technique, focusing on scenarios of conceptualizing a few terms, cannot 1) scale to many FE instances (average of 29. 7 instances for all FEs) and 2) leverage interdependence between instances and concepts. We thus propose a scalable k-truss clustering and a Markov Random Field (MRF) model leveraging interdependence between conceptinstance, concept-concept, and instance-instance pairs. Our extensive analysis with real-life data validates that our approach improves not only the quality of the identiﬁed concepts for FrameNet, but also that of applications such as selectional preference.

AAAI Conference 2016 Conference Paper

Understanding Emerging Spatial Entities

Jinyoung Yeo
Jin-woo Park
Seung-won Hwang

In Foursquare or Google+ Local, emerging spatial entities, such as new business or venue, are reported to grow by 1% every day. As information on such spatial entities is initially limited (e. g. , only name), we need to quickly harvest related information from social media such as Flickr photos. Especially, achieving high-recall in photo population is essential for emerging spatial entities, which suffer from data sparseness (e. g. , 71% restaurants of TripAdvisor in Seattle do not have any photo, as of Sep 03, 2015). Our goal is thus to address this limitation by identifying effective linking techniques for emerging spatial entities and photos. Compared with state-of-the-art baselines, our proposed approach improves recall and F1 score by up to 24% and 18%, respectively. To show the effectiveness and robustness of our approach, we have conducted extensive experiments in three different cities, Seattle, Washington D. C. , and Taipei, of varying characteristics such as geographical density and language.

AAAI Conference 2016 Conference Paper

Verb Pattern: A Probabilistic Semantic Representation on Verbs

Wanyun Cui
Xiyou Zhou
Hangyu Lin
Yanghua Xiao
Haixun Wang
Seung-won Hwang
Wei Wang

Verbs are important in semantic understanding of natural language. Traditional verb representations, such as FrameNet, PropBank, VerbNet, focus on verbs’ roles. These roles are too coarse to represent verbs’ semantics. In this paper, we introduce verb patterns to represent verbs’ semantics, such that each pattern corresponds to a single semantic of the verb. First we analyze the principles for verb patterns: generality and speciﬁcity. Then we propose a nonparametric model based on description length. Experimental results prove the high effectiveness of verb patterns. We further apply verb patterns to context-aware conceptualization, to show that verb patterns are helpful in semantic-related tasks.

AAAI Conference 2015 Conference Paper

An Association Network for Computing Semantic Relatedness

Keyang Zhang
Kenny Zhu
Seung-won Hwang

To judge how much a pair of words (or texts) are semantically related is a cognitive process. However, previous algorithms for computing semantic relatedness are largely based on co-occurrences within textual windows, and do not actively leverage cognitive human perceptions of relatedness. To bridge this perceptional gap, we propose to utilize free association as signals to capture such human perceptions. However, free association, being manually evaluated, has limited lexical coverage and is inherently sparse. We propose to expand lexical coverage and overcome sparseness by constructing an association network of terms and concepts that combines signals from free association norms and five types of cooccurrences extracted from the rich structures of Wikipedia. Our evaluation results validate that simple algorithms on this network give competitive results in computing semantic relatedness between words and between short texts.

AAAI Conference 2014 Conference Paper

ARIA: Asymmetry Resistant Instance Alignment

Sanghoon Lee
Seung-won Hwang

We study the problem of instance alignment between knowledge bases (KBs). Existing approaches, exploiting the “symmetry” of structure and information across KBs, suffer in the presence of asymmetry, which is frequent as KBs are independently built. Specifically, we observe three types of asymmetries (in concepts, in features, and in structures). Our goal is to identify key techniques to reduce accuracy loss caused by each type of asymmetry, then design Asymmetry-Resistant Instance Alignment framework (ARIA). ARIA uses twophased blocking methods considering concept and feature asymmetries, with a novel similarity measure overcoming structure asymmetry. Compared to a state-ofthe-art method, ARIA increased precision by 19% and recall by 2%, and decreased processing time by more than 80% in matching large-scale real-life KBs.

AAAI Conference 2012 Conference Paper

Predictive Mining of Comparable Entities from the Web

Myungha Jang
Jin-woo Park
Seung-won Hwang

Comparing entities is an important part of decision making. Several approaches have been reported for mining comparable entities from Web sources to improve user experience in comparing entities online. However, these efforts extract only entities explicitly compared in the corpora, and may exclude entities that occur less-frequently but potentially comparable. To build a more complete comparison machine that can infer such missing relations, here we develop a solution to predict transitivity of known comparable relations. Named CLIQUE- GROW, our approach predicts missing links given a comparable entity graph obtained from versus query logs. Our approach achieved the highest F1-score among five link prediction approaches and a commercial comparison engine provided by Yahoo! .

AAAI Conference 2011 Conference Paper

CosTriage: A Cost-Aware Triage Algorithm for Bug Reporting Systems

Jin-woo Park
Mu-Woong Lee
Jinhan Kim
Seung-won Hwang
Sunghun Kim

‘Who can ﬁx this bug? ’ is an important question in bug triage to “accurately” assign developers to bug reports. To address this question, recent research treats it as a optimizing recommendation accuracy problem and proposes a solution that is essentially an instance of content-based recommendation (CBR). However, CBR is well-known to cause over-specialization, recommending only the types of bugs that each developer has solved before. This problem is critical in practice, as some experienced developers could be overloaded, and this would slow the bug ﬁxing process. In this paper, we take two directions to address this problem: First, we reformulate the problem as an optimization problem of both accuracy and cost. Second, we adopt a content-boosted collaborative ﬁltering (CBCF), combining an existing CBR with a collaborative ﬁltering recommender (CF), which enhances the recommendation quality of either approach alone. However, unlike general recommendation scenarios, bug ﬁx history is extremely sparse. Due to the nature of bug ﬁxes, one bug is ﬁxed by only one developer, which makes it challenging to pursue the above two directions. To address this challenge, we develop a topic-model to reduce the sparseness and enhance the quality of CBCF. Our experimental evaluation shows that our solution reduces the cost efﬁciently by 30% without seriously compromising accuracy.

AAAI Conference 2010 Conference Paper

Towards an Intelligent Code Search Engine

Jinhan Kim
Sanghoon Lee
Seung-won Hwang
Sunghun Kim

Software developers increasingly rely on information from the Web, such as documents or code examples on Application Programming Interfaces (APIs), to facilitate their development processes. However, API documents often do not include enough information for developers to fully understand the API usages, while searching for good code examples requires non-trivial effort. To address this problem, we propose a novel code search engine, combining the strength of browsing documents and searching for code examples, by returning documents embedded with high-quality code example summaries mined from the Web. Our evaluation results show that our approach provides code examples with high precision and boosts programmer productivity.