1.2k citations · 3k across the 72 of their papers we have counts for
14 papers · 2 filters
Debiasing Stance Detection Models with Counterfactual Reasoning and Adversarial Bias Learning
Jianhua Yuan, Yanyan Zhao, Bing Qin
Stance detection models may tend to rely on dataset bias in the text part as a shortcut and thus fail to sufficiently learn the interaction between the targets and texts. Recent de…
Knowledge-Bridged Causal Interaction Network for Causal Emotion Entailment
Weixiang Zhao, Yanyan Zhao, Zhuojun Li +1
Causal Emotion Entailment aims to identify causal utterances that are responsible for the target utterance with a non-neutral emotion in conversations. Previous works are limited i…
Controllable Text Generation via Probability Density Estimation in the Latent Space
Yuxuan Gu, Xiaocheng Feng, Sicheng Ma +4
Previous work on controllable text generation has explored the idea of control from the latent space, such as optimizing a representation with attribute-related classifiers or samp…
A Distributional Lens for Multi-Aspect Controllable Text Generation
Yuxuan Gu, Xiaocheng Feng, Sicheng Ma +3
Multi-aspect controllable text generation is a more challenging and practical task than single-aspect control. Existing methods achieve complex multi-aspect control by fusing multi…
Don't Lose Yourself! Empathetic Response Generation via Explicit Self-Other Awareness
Weixiang Zhao, Yanyan Zhao, Xin Lu +1
As a critical step to achieve human-like chatbots, empathetic response generation has attained increasing interests. Previous attempts are incomplete and not sufficient enough to e…
An Efficient End-to-End Transformer with Progressive Tri-modal Attention for Multi-modal Emotion Recognition
Yang Wu, Pai Peng, Zhenyu Zhang +2
Recent works on multi-modal emotion recognition move towards end-to-end models, which can extract the task-specific features supervised by the target task compared with the two-pha…
Prompt Combines Paraphrase: Teaching Pre-trained Models to Understand Rare Biomedical Words
Haochun Wang, Chi Liu, Nuwa Xi +7
Prompt-based fine-tuning for pre-trained models has proven effective for many natural language processing tasks under few-shot settings in general domain. However, tuning with prom…
Zero-shot Aspect-level Sentiment Classification via Explicit Utilization of Aspect-to-Document Sentiment Composition
Pengfei Deng, Jianhua Yuan, Yanyan Zhao +1
As aspect-level sentiment labels are expensive and labor-intensive to acquire, zero-shot aspect-level sentiment classification is proposed to learn classifiers applicable to new do…
Hansel: A Chinese Few-Shot and Zero-Shot Entity Linking Benchmark
Zhenran Xu, Zifei Shan, Yuxin Li +2
Modern Entity Linking (EL) systems entrench a popularity bias, yet there is no dataset focusing on tail and emerging entities in languages other than English. We present Hansel, a…
MACSA: A Multimodal Aspect-Category Sentiment Analysis Dataset with Multimodal Fine-grained Aligned Annotations
Hao Yang, Yanyan Zhao, Jianwei Liu +2
Multimodal fine-grained sentiment analysis has recently attracted increasing attention due to its broad applications. However, the existing multimodal fine-grained sentiment datase…
A Graph Enhanced BERT Model for Event Prediction
Li Du, Xiao Ding, Yue Zhang +3
Predicting the subsequent event for an existing event context is an important but challenging task, as it requires understanding the underlying relationship between events. Previou…
Unifying the Convergences in Multilingual Neural Machine Translation
Yichong Huang, Xiaocheng Feng, Xinwei Geng +1
Although all-in-one-model multilingual neural machine translation (multilingual NMT) has achieved remarkable progress, the convergence inconsistency in the joint training is ignore…
Sentiment Word Aware Multimodal Refinement for Multimodal Sentiment Analysis with ASR Errors
Yang Wu, Yanyan Zhao, Hao Yang +4
Multimodal sentiment analysis has attracted increasing attention and lots of models have been proposed. However, the performance of the state-of-the-art models decreases sharply wh…
Pretraining without Wordpieces: Learning Over a Vocabulary of Millions of Words
Zhangyin Feng, Duyu Tang, Cong Zhou +6
The standard BERT adopts subword-based tokenization, which may break a word into two or more wordpieces (e.g., converting "lossless" to "loss" and "less"). This will bring inconven…