Han Yu


2023

pdf bib
Ideology Takes Multiple Looks: A High-Quality Dataset for Multifaceted Ideology Detection
Songtao Liu | Ziling Luo | Minghua Xu | Lixiao Wei | Ziyao Wei | Han Yu | Wei Xiang | Bang Wang
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing

Ideology detection (ID) is important for gaining insights about peoples’ opinions and stances on our world and society, which can find many applications in politics, economics and social sciences. It is not uncommon that a piece of text can contain descriptions of various issues. It is also widely accepted that a person can take different ideological stances in different facets. However, existing datasets for the ID task only label a text as ideologically left- or right-leaning as a whole, regardless whether the text containing one or more different issues. Moreover, most prior work annotates texts from data resources with known ideological bias through distant supervision approaches, which may result in many false labels. With some theoretical help from social sciences, this work first designs an ideological schema containing five domains and twelve facets for a new multifaceted ideology detection (MID) task to provide a more complete and delicate description of ideology. We construct a MITweet dataset for the MID task, which contains 12,594 English Twitter posts, each annotated with a Relevance and an Ideology label for all twelve facets. We also design and test a few of strong baselines for the MID task under in-topic and cross-topic settings, which can serve as benchmarks for further research.

2022

pdf bib
Proceedings of the Second DialDoc Workshop on Document-grounded Dialogue and Conversational Question Answering
Song Feng | Hui Wan | Caixia Yuan | Han Yu
Proceedings of the Second DialDoc Workshop on Document-grounded Dialogue and Conversational Question Answering

pdf bib
Improving the Sample Efficiency of Prompt Tuning with Domain Adaptation
Xu Guo | Boyang Li | Han Yu
Findings of the Association for Computational Linguistics: EMNLP 2022

Prompt tuning, or the conditioning of a frozen pretrained language model (PLM) with soft prompts learned from data, has demonstrated impressive performance on a wide range of NLP tasks. However, prompt tuning requires a large training dataset to be effective and is outperformed by finetuning the entire PLM in data-scarce regimes. Previous work (Gu et al., 2022, Vu et al., 2022) proposed to transfer soft prompts pretrained on the source domain to the target domain. In this paper, we explore domain adaptation for prompt tuning, a problem setting where unlabeled data from the target domain are available during pretraining. We propose bOosting Prompt TunIng with doMain Adaptation (OPTIMA), which regularizes the decision boundary to be smooth around regions where source and target data distributions are similar. Extensive experiments demonstrate that OPTIMA significantly enhances the transferability and sample-efficiency of prompt tuning compared to strong baselines. Moreover, in few-shot settings, OPTIMA exceeds full-model tuning by a large margin.

2021

pdf bib
Latent-Optimized Adversarial Neural Transfer for Sarcasm Detection
Xu Guo | Boyang Li | Han Yu | Chunyan Miao
Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

The existence of multiple datasets for sarcasm detection prompts us to apply transfer learning to exploit their commonality. The adversarial neural transfer (ANT) framework utilizes multiple loss terms that encourage the source-domain and the target-domain feature distributions to be similar while optimizing for domain-specific performance. However, these objectives may be in conflict, which can lead to optimization difficulties and sometimes diminished transfer. We propose a generalized latent optimization strategy that allows different losses to accommodate each other and improves training dynamics. The proposed method outperforms transfer learning and meta-learning baselines. In particular, we achieve 10.02% absolute performance gain over the previous state of the art on the iSarcasm dataset.