Sung-Min Lee


2024

pdf bib
RADCoT: Retrieval-Augmented Distillation to Specialization Models for Generating Chain-of-Thoughts in Query Expansion
Sung-Min Lee | Eunhwan Park | DongHyeon Jeon | Inho Kang | Seung-Hoon Na
Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)

Large language models (LLMs) have demonstrated superior performance to that of small language models (SLM) in information retrieval for various subtasks including dense retrieval, reranking, query expansion, and pseudo-document generation. However, the parameter sizes of LLMs are extremely large, making it expensive to operate LLMs stably for providing LLM-based retrieval services. Recently, retrieval-augmented language models have been widely employed to significantly reduce the parameter size by retrieving relevant knowledge from large-scale corpora and exploiting the resulting “in-context” knowledge as additional model input, thereby substantially reducing the burden of internalizing and retaining world knowledge in model parameters. Armed by the retrieval-augmented language models, we present a retrieval-augmented model specialization that distills the capability of LLMs to generate the chain-of-thoughts (CoT) for query expansion – that is, injects the LLM’s capability to generate CoT into a retrieval-augmented SLM – referred to as RADCoT. Experimental results on the MS-MARCO, TREC DL 19, 20 datasets show that RADCoT yields consistent improvements over distillation without retrieval, achieving comparable performance to that of the query expansion method using LLM-based CoTs. Our code is publicly available at https://github.com/ZIZUN/RADCoT.

2023

pdf bib
MAFiD: Moving Average Equipped Fusion-in-Decoder for Question Answering over Tabular and Textual Data
Sung-Min Lee | Eunhwan Park | Daeryong Seo | Donghyeon Jeon | Inho Kang | Seung-Hoon Na
Findings of the Association for Computational Linguistics: EACL 2023

Transformer-based models for question answering (QA) over tables and texts confront a “long” hybrid sequence over tabular and textual elements, causing long-range reasoning problems. To handle long-range reasoning, we extensively employ a fusion-in-decoder (FiD) and exponential moving average (EMA), proposing a Moving Average Equipped Fusion-in-Decoder (MAFiD). With FiD as the backbone architecture, MAFiD combines various levels of reasoning: independent encoding of homogeneous data and single-row and multi-row heterogeneous reasoning, using a gated cross attention layer to effectively aggregate the three types of representations resulting from various reasonings. Experimental results on HybridQA indicate that MAFiD achieves state-of-the-art performance by increasing exact matching (EM) and F1 by 1.1 and 1.7, respectively, on the blind test set.

2022

pdf bib
JBNU-CCLab at SemEval-2022 Task 7: DeBERTa for Identifying Plausible Clarifications in Instructional Texts
Daewook Kang | Sung-Min Lee | Eunhwan Park | Seung-Hoon Na
Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022)

In this study, we examine the ability of contextualized representations of pretrained language model to distinguish whether sequences from instructional articles are plausible or implausible. Towards this end, we compare the BERT, RoBERTa, and DeBERTa models using simple classifiers based on the sentence representations of the [CLS] tokens and perform a detailed analysis by visualizing the representations of the [CLS] tokens of the models. In the experimental results of Subtask A: Multi-Class Classification, DeBERTa exhibits the best performance and produces a more distinguishable representation across different labels. Submitting an ensemble of 10 DeBERTa-based models, our final system achieves an accuracy of 61.4% and is ranked fifth out of models submitted by eight teams. Further in-depth results suggest that the abilities of pretrained language models for the plausibility detection task are more strongly affected by their model structures or attention designs than by their model sizes.

pdf bib
JBNU-CCLab at SemEval-2022 Task 12: Machine Reading Comprehension and Span Pair Classification for Linking Mathematical Symbols to Their Descriptions
Sung-Min Lee | Seung-Hoon Na
Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022)

This paper describes our system in the SemEval-2022 Task 12: ‘linking mathematical symbols to their descriptions’, achieving first on the leaderboard for all the subtasks comprising named entity extraction (NER) and relation extraction (RE). Our system is a two-stage pipeline model based on SciBERT that detects symbols, descriptions, and their relationships in scientific documents. The system consists of 1) machine reading comprehension(MRC)-based NER model, where each entity type is represented as a question and its entity mention span is extracted as an answer using an MRC model, and 2) span pair classification for RE, where two entity mentions and their type markers are encoded into span representations that are then fed to a Softmax classifier. In addition, we deploy a rule-based symbol tokenizer to improve the detection of the exact boundary of symbol entities. Regularization and ensemble methods are further explored to improve the RE model.