Yo-Sub Han


2023

pdf bib
GDA: Grammar-based Data Augmentation for Text Classification using Slot Information
Joonghyuk Hahn | Hyunjoon Cheon | Elizabeth Orwig | Su-Hyeon Kim | Sang-Ki Ko | Yo-Sub Han
Findings of the Association for Computational Linguistics: EMNLP 2023

Recent studies propose various data augmentation approaches to resolve the low-resource problem in natural language processing tasks. Data augmentation is a successful solution to this problem and recent strategies give variation on sentence structures to boost performance. However, these approaches can potentially lead to semantic errors and produce semantically noisy data due to the unregulated variation of sentence structures. In an effort to combat these semantic errors, we leverage slot information, the representation of the context of keywords from a sentence, and form a data augmentation strategy which we propose, called GDA. Our strategy employs algorithms that construct and manipulate rules of context-aware grammar, utilizing this slot information. The algorithms extract recurrent patterns by distinguishing words with slots and form the “rules of grammar”—a set of injective relations between a sentence’s semantics and its syntactical structure—to augment the dataset. The augmentation is done in an automated manner with the constructed rules and thus, GDA is explainable and reliable without any human intervention. We evaluate GDA with state-of-the-art data augmentation techniques, including those using pre-trained language models, and the result illustrates that GDA outperforms all other data augmentation methods by 19.38%. Extensive experiments show that GDA is an effective data augmentation strategy that incorporates word semantics for more accurate and diverse data.

pdf bib
ConPrompt: Pre-training a Language Model with Machine-Generated Data for Implicit Hate Speech Detection
Youngwook Kim | Shinwoo Park | Youngsoo Namgoong | Yo-Sub Han
Findings of the Association for Computational Linguistics: EMNLP 2023

Implicit hate speech detection is a challenging task in text classification since no explicit cues (e.g., swear words) exist in the text. While some pre-trained language models have been developed for hate speech detection, they are not specialized in implicit hate speech. Recently, an implicit hate speech dataset with a massive number of samples has been proposed by controlling machine generation. We propose a pre-training approach, ConPrompt, to fully leverage such machine-generated data. Specifically, given a machine-generated statement, we use example statements of its origin prompt as positive samples for contrastive learning. Through pre-training with ConPrompt, we present ToxiGen-ConPrompt, a pre-trained language model for implicit hate speech detection. We conduct extensive experiments on several implicit hate speech datasets and show the superior generalization ability of ToxiGen-ConPrompt compared to other pre-trained models. Additionally, we empirically show that ConPrompt is effective in mitigating identity term bias, demonstrating that it not only makes a model more generalizable but also reduces unintended bias. We analyze the representation quality of ToxiGen-ConPrompt and show its ability to consider target group and toxicity, which are desirable features in terms of implicit hate speeches.

pdf bib
ATHENA: Mathematical Reasoning with Thought Expansion
Jb. Kim | Hazel Kim | Joonghyuk Hahn | Yo-Sub Han
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing

Solving math word problems depends on how to articulate the problems, the lens through which models view human linguistic expressions. Real-world settings count on such a method even more due to the diverse practices of the same mathematical operations. Earlier works constrain available thinking processes by limited prediction strategies without considering their significance in acquiring mathematical knowledge. We introduce Attention-based THought Expansion Network Architecture (ATHENA) to tackle the challenges of real-world practices by mimicking human thought expansion mechanisms in the form of neural network propagation. A thought expansion recurrently generates the candidates carrying the thoughts of possible math expressions driven from the previous step and yields reasonable thoughts by selecting the valid pathways to the goal. Our experiments show that ATHENA achieves a new state-of-the-art stage toward the ideal model that is compelling in variant questions even when the informativeness in training examples is restricted.

pdf bib
Contrastive Learning with Keyword-based Data Augmentation for Code Search and Code Question Answering
Shinwoo Park | Youngwook Kim | Yo-Sub Han
Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics

The semantic code search is to find code snippets from the collection of candidate code snippets with respect to a user query that describes functionality. Recent work on code search proposes data augmentation of queries for contrastive learning. This data augmentation approach modifies random words in queries. When a user web query for searching code snippet is too brief, the important word that represents the search intent of the query could be undesirably modified. A code snippet has informative components such as function name and documentation that describe its functionality. We propose to utilize these code components to identify important words and preserve them in the data augmentation step. We present KeyDAC (Keyword-based Data Augmentation for Contrastive learning) that identifies important words for code search from queries and code components based on term matching. KeyDAC augments query-code pairs while preserving keywords, and then leverages generated training instances for contrastive learning. We use KeyDAC to fine-tune various pre-trained language models and evaluate the performance of code search and code question answering via CoSQA and WebQueryTest. The experimental results confirm that KeyDAC substantially outperforms the current state-of-the-art performance, and achieves the new state-of-the-arts for both tasks.

2022

pdf bib
Boosting Code Summarization by Embedding Code Structures
Jikyoeng Son | Joonghyuk Hahn | HyeonTae Seo | Yo-Sub Han
Proceedings of the 29th International Conference on Computational Linguistics

Recent research on code summarization relies on the structural information from the abstract syntax tree (AST) of source codes. It is, however, questionable whether it is the most effective to use AST for expressing the structural information. We find that a program dependency graph (PDG) can represent the structure of a code more effectively. We propose PDG Boosting Module (PBM) that encodes PDG into graph embedding and the framework to implement the proposed PBM with the existing models. PBM achieves improvements of 6.67% (BLEU) and 7.47% (ROUGE) on average. We then analyze the experimental results, and examine how PBM helps the training of baseline models and its performance robustness. For the validation of robustness, we measure the performance of an out-of-domain benchmark dataset, and confirm its robustness. In addition, we apply a new evaluation measure, SBERT score, to evaluate the semantic performance. The models implemented with PBM improve the performance of SBERT score. This implies that they generate summaries that are semantically more similar to the reference summary.

pdf bib
Generalizable Implicit Hate Speech Detection Using Contrastive Learning
Youngwook Kim | Shinwoo Park | Yo-Sub Han
Proceedings of the 29th International Conference on Computational Linguistics

Hate speech detection has gained increasing attention with the growing prevalence of hateful contents. When a text contains an obvious hate word or expression, it is fairly easy to detect it. However, it is challenging to identify implicit hate speech in nuance or context when there are insufficient lexical cues. Recently, there are several attempts to detect implicit hate speech leveraging pre-trained language models such as BERT and HateBERT. Fine-tuning on an implicit hate speech dataset shows satisfactory performance when evaluated on the test set of the dataset used for training. However, we empirically confirm that the performance drops at least 12.5%p in F1 score when tested on the dataset that is different from the one used for training. We tackle this cross-dataset underperforming problem using contrastive learning. Based on our observation of common underlying implications in various forms of hate posts, we propose a novel contrastive learning method, ImpCon, that pulls an implication and its corresponding posts close in representation space. We evaluate the effectiveness of ImpCon by running cross-dataset evaluation on three implicit hate speech benchmarks. The experimental results on cross-dataset show that ImpCon improves at most 9.10% on BERT, and 8.71% on HateBERT.

2021

pdf bib
Self-Training using Rules of Grammar for Few-Shot NLU
Joonghyuk Hahn | Hyunjoon Cheon | Kyuyeol Han | Cheongjae Lee | Junseok Kim | Yo-Sub Han
Findings of the Association for Computational Linguistics: EMNLP 2021

We tackle the problem of self-training networks for NLU in low-resource environment—few labeled data and lots of unlabeled data. The effectiveness of self-training is a result of increasing the amount of training data while training. Yet it becomes less effective in low-resource settings due to unreliable labels predicted by the teacher model on unlabeled data. Rules of grammar, which describe the grammatical structure of data, have been used in NLU for better explainability. We propose to use rules of grammar in self-training as a more reliable pseudo-labeling mechanism, especially when there are few labeled data. We design an effective algorithm that constructs and expands rules of grammar without human involvement. Then we integrate the constructed rules as a pseudo-labeling mechanism into self-training. There are two possible scenarios regarding data distribution: it is unknown or known in prior to training. We empirically demonstrate that our approach substantially outperforms the state-of-the-art methods in three benchmark datasets for both scenarios.

pdf bib
MultiFix: Learning to Repair Multiple Errors by Optimal Alignment Learning
HyeonTae Seo | Yo-Sub Han | Sang-Ki Ko
Findings of the Association for Computational Linguistics: EMNLP 2021

We consider the problem of learning to repair erroneous C programs by learning optimal alignments with correct programs. Since the previous approaches fix a single error in a line, it is inevitable to iterate the fixing process until no errors remain. In this work, we propose a novel sequence-to-sequence learning framework for fixing multiple program errors at a time. We introduce the edit-distance-based data labeling approach for program error correction. Instead of labeling a program repair example by pairing an erroneous program with a line fix, we label the example by paring an erroneous program with an optimal alignment to the corresponding correct program produced by the edit-distance computation. We evaluate our proposed approach on a publicly available dataset (DeepFix dataset) that consists of erroneous C programs submitted by novice programming students. On a set of 6,975 erroneous C programs from the DeepFix dataset, our approach achieves the state-of-the-art result in terms of full repair rate on the DeepFix dataset (without extra data such as compiler error message or additional source codes for pre-training).

2019

pdf bib
Online Infix Probability Computation for Probabilistic Finite Automata
Marco Cognetta | Yo-Sub Han | Soon Chan Kwon
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

Probabilistic finite automata (PFAs) are com- mon statistical language model in natural lan- guage and speech processing. A typical task for PFAs is to compute the probability of all strings that match a query pattern. An impor- tant special case of this problem is computing the probability of a string appearing as a pre- fix, suffix, or infix. These problems find use in many natural language processing tasks such word prediction and text error correction. Recently, we gave the first incremental algorithm to efficiently compute the infix probabilities of each prefix of a string (Cognetta et al., 2018). We develop an asymptotic improvement of that algorithm and solve the open problem of computing the infix probabilities of PFAs from streaming data, which is crucial when process- ing queries online and is the ultimate goal of the incremental approach.

pdf bib
SoftRegex: Generating Regex from Natural Language Descriptions using Softened Regex Equivalence
Jun-U Park | Sang-Ki Ko | Marco Cognetta | Yo-Sub Han
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)

We continue the study of generating se-mantically correct regular expressions from natural language descriptions (NL). The current state-of-the-art model SemRegex produces regular expressions from NLs by rewarding the reinforced learning based on the semantic (rather than syntactic) equivalence between two regular expressions. Since the regular expression equivalence problem is PSPACE-complete, we introduce the EQ_Reg model for computing the simi-larity of two regular expressions using deep neural networks. Our EQ_Reg mod-el essentially softens the equivalence of two regular expressions when used as a reward function. We then propose a new regex generation model, SoftRegex, us-ing the EQ_Reg model, and empirically demonstrate that SoftRegex substantially reduces the training time (by a factor of at least 3.6) and produces state-of-the-art results on three benchmark datasets.

pdf bib
Detecting context abusiveness using hierarchical deep learning
Ju-Hyoung Lee | Jun-U Park | Jeong-Won Cha | Yo-Sub Han
Proceedings of the Second Workshop on Natural Language Processing for Internet Freedom: Censorship, Disinformation, and Propaganda

Abusive text is a serious problem in social media and causes many issues among users as the number of users and the content volume increase. There are several attempts for detecting or preventing abusive text effectively. One simple yet effective approach is to use an abusive lexicon and determine the existence of an abusive word in text. This approach works well even when an abusive word is obfuscated. On the other hand, it is still a challenging problem to determine abusiveness in a text having no explicit abusive words. Especially, it is hard to identify sarcasm or offensiveness in context without any abusive words. We tackle this problem using an ensemble deep learning model. Our model consists of two parts of extracting local features and global features, which are crucial for identifying implicit abusiveness in context level. We evaluate our model using three benchmark data. Our model outperforms all the previous models for detecting abusiveness in a text data without abusive words. Furthermore, we combine our model and an abusive lexicon method. The experimental results show that our model has at least 4% better performance compared with the previous approaches for identifying text abusiveness in case of with/without abusive words.

2018

pdf bib
Incremental Computation of Infix Probabilities for Probabilistic Finite Automata
Marco Cognetta | Yo-Sub Han | Soon Chan Kwon
Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing

In natural language processing, a common task is to compute the probability of a phrase appearing in a document or to calculate the probability of all phrases matching a given pattern. For instance, one computes affix (prefix, suffix, infix, etc.) probabilities of a string or a set of strings with respect to a probability distribution of patterns. The problem of computing infix probabilities of strings when the pattern distribution is given by a probabilistic context-free grammar or by a probabilistic finite automaton is already solved, yet it was open to compute the infix probabilities in an incremental manner. The incremental computation is crucial when a new query is built from a previous query. We tackle this problem and suggest a method that computes infix probabilities incrementally for probabilistic finite automata by representing all the probabilities of matching strings as a series of transition matrix calculations. We show that the proposed approach is theoretically faster than the previous method and, using real world data, demonstrate that our approach has vastly better performance in practice.