Recently, language models have accelerated the improvement in natural language processing. However, recent studies have highlighted a significant issue: social biases inherent in training data can lead models to learn and propagate these biases. In this study, we propose a contrastive learning method for bias mitigation, utilizing anchor points to push further negatives and pull closer positives within the representation space. This approach employs stereotypical data as negatives and stereotype-free data as positives, enhancing debiasing performance. Our model attained state-of-the-art performance in the ICAT score on the StereoSet, a benchmark for measuring bias in models. In addition, we observed that effective debiasing is achieved through an awareness of biases, as evidenced by improved hate speech detection scores. The implementation code and trained models are available at https://github.com/HUFS-NLP/CL_Polarizer.git.

Despite the recent advancements in abstractive summarization systems leveraged from large-scale datasets and pre-trained language models, the factual correctness of the summary is still insufficient. One line of trials to mitigate this problem is to include a post-editing process that can detect and correct factual errors in the summary. In building such a system, it is strongly required that 1) the process has a high success rate and interpretability and 2) it has a fast running time. Previous approaches focus on the regeneration of the summary, resulting in low interpretability and high computing resources. In this paper, we propose an efficient factual error correction system RFEC based on entity retrieval. RFEC first retrieves the evidence sentences from the original document by comparing the sentences with the target summary to reduce the length of the text to analyze. Next, RFEC detects entity-level errors in the summaries using the evidence sentences and substitutes the wrong entities with the accurate entities from the evidence sentences. Experimental results show that our proposed error correction system shows more competitive performance than baseline methods in correcting factual errors with a much faster speed.

This paper describes our system, Joint Encoders for Stable Suggestion Inference (JESSI), for the SemEval 2019 Task 9: Suggestion Mining from Online Reviews and Forums. JESSI is a combination of two sentence encoders: (a) one using multiple pre-trained word embeddings learned from log-bilinear regression (GloVe) and translation (CoVe) models, and (b) one on top of word encodings from a pre-trained deep bidirectional transformer (BERT). We include a domain adversarial training module when training for out-of-domain samples. Our experiments show that while BERT performs exceptionally well for in-domain samples, several runs of the model show that it is unstable for out-of-domain samples. The problem is mitigated tremendously by (1) combining BERT with a non-BERT encoder, and (2) using an RNN-based classifier on top of BERT. Our final models obtained second place with 77.78% F-Score on Subtask A (i.e. in-domain) and achieved an F-Score of 79.59% on Subtask B (i.e. out-of-domain), even without using any additional external data.

Biomedical Named Entity (NE) recognition is a core technique for various works in the biomedical domain. In previous studies, using machine learning algorithm shows better performance than dictionary-based and rule-based approaches because there are too many terminological variations of biomedical NEs and new biomedical NEs are constantly generated. To achieve the high performance with a machine-learning algorithm, good-quality corpora are required. However, it is difficult to obtain the good-quality corpora because an-notating a biomedical corpus for ma-chine-learning is extremely time-consuming and costly. In addition, most previous corpora are insufficient for high-level tasks because they cannot cover various domains. Therefore, we propose a method for generating a large amount of machine-labeled data that covers various domains. To generate a large amount of machine-labeled data, firstly we generate an initial machine-labeled data by using a chunker and MetaMap. The chunker is developed to extract only biomedical NEs with manually annotated data. MetaMap is used to annotate the category of bio-medical NE. Then we apply the self-training approach to bootstrap the performance of initial machine-labeled data. In our experiments, the biomedical NE recognition system that is trained with our proposed machine-labeled data achieves much high performance. As a result, our system outperforms biomedical NE recognition system that using MetaMap only with 26.03%p improvements on F1-score.