Yuxiang Jia


pdf bib
FaiMA: Feature-aware In-context Learning for Multi-domain Aspect-based Sentiment Analysis
Songhua Yang | Xinke Jiang | Hanjie Zhao | Wenxuan Zeng | Hongde Liu | Yuxiang Jia
Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)

Multi-domain aspect-based sentiment analysis (ABSA) seeks to capture fine-grained sentiment across diverse domains. While existing research narrowly focuses on single-domain applications constrained by methodological limitations and data scarcity, the reality is that sentiment naturally traverses multiple domains. Although large language models (LLMs) offer a promising solution for ABSA, it is difficult to integrate effectively with established techniques, including graph-based models and linguistics, because modifying their internal architecture is not easy. To alleviate this problem, we propose a novel framework, Feature-aware In-context Learning for Multi-domain ABSA (FaiMA). The core insight of FaiMA is to utilize in-context learning (ICL) as a feature-aware mechanism that facilitates adaptive learning in multi-domain ABSA tasks. Specifically, we employ a multi-head graph attention network as a text encoder optimized by heuristic rules for linguistic, domain, and sentiment features. Through contrastive learning, we optimize sentence representations by focusing on these diverse features. Additionally, we construct an efficient indexing mechanism, allowing FaiMA to stably retrieve highly relevant examples across multiple dimensions for any given input. To evaluate the efficacy of FaiMA, we build the first multi-domain ABSA benchmark dataset. Extensive experimental results demonstrate that FaiMA achieves significant performance improvements in multiple domains compared to baselines, increasing F1 by 2.07% on average. Source code and data sets are available at https://github.com/SupritYoung/FaiMA.

pdf bib
MRC-based Nested Medical NER with Co-prediction and Adaptive Pre-training
Xiaojing Du | Hanjie Zhao | Danyan Xing | Yuxiang Jia | Hongying Zan
Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)

In medical information extraction, medical Named Entity Recognition (NER) is indispensable, playing a crucial role in developing medical knowledge graphs, enhancing medical question-answering systems, and analyzing electronic medical records. The challenge in medical NER arises from the complex nested structures and sophisticated medical terminologies, distinguishing it from its counterparts in traditional domains. In response to these complexities, we propose a medical NER model based on Machine Reading Comprehension (MRC), which uses a task-adaptive pre-training strategy to improve the model’s capability in the medical field. Meanwhile, our model introduces multiple word-pair embeddings and multi-granularity dilated convolution to enhance the model’s representation ability and uses a combined predictor of Biaffine and MLP to improve the model’s recognition performance. Experimental evaluations conducted on the CMeEE, a benchmark for Chinese nested medical NER, demonstrate that our proposed model outperforms the compared state-of-the-art (SOTA) models.


pdf bib
A Corpus for Named Entity Recognition in Chinese Novels with Multi-genres
Hanjie Zhao | Jinge Xie | Yuchen Yan | Yuxiang Jia | Yawen Ye | Hongying Zan
Proceedings of the 37th Pacific Asia Conference on Language, Information and Computation


pdf bib
MMDAG: Multimodal Directed Acyclic Graph Network for Emotion Recognition in Conversation
Shuo Xu | Yuxiang Jia | Changyong Niu | Hongying Zan
Proceedings of the Thirteenth Language Resources and Evaluation Conference

Emotion recognition in conversation is important for an empathetic dialogue system to understand the user’s emotion and then generate appropriate emotional responses. However, most previous researches focus on modeling conversational contexts primarily based on the textual modality or simply utilizing multimodal information through feature concatenation. In order to exploit multimodal information and contextual information more effectively, we propose a multimodal directed acyclic graph (MMDAG) network by injecting information flows inside modality and across modalities into the DAG architecture. Experiments on IEMOCAP and MELD show that our model outperforms other state-of-the-art models. Comparative studies validate the effectiveness of the proposed modality fusion method.


pdf bib
融入篇章信息的文学作品命名实体识别(Document-level Literary Named Entity Recognition)
Yuxiang Jia (贾玉祥) | Rui Chao (晁睿) | Hongying Zan (昝红英) | Huayi Dou (窦华溢) | Shuai Cao (曹帅) | Shuo Xu (徐硕)
Proceedings of the 20th Chinese National Conference on Computational Linguistics



pdf bib
A Comparison of Chinese Word Segmentation on News and Microblog Corpora with a Lexicon Based Method
Yuxiang Jia | Hongying Zan | Ming Fan | Zhimin Wang
Proceedings of the Second CIPS-SIGHAN Joint Conference on Chinese Language Processing


pdf bib
Chinese Word Sense Induction with Basic Clustering Algorithms
Yuxiang Jia | Shiwen Yu | Zhengyan Chen
CIPS-SIGHAN Joint Conference on Chinese Language Processing


pdf bib
Chinese Semantic Class Learning from Web Based on Concept-Level Characteristics
Wenbo Pang | Xiaozhong Fan | Jiangde Yu | Yuxiang Jia
Proceedings of the 23rd Pacific Asia Conference on Language, Information and Computation, Volume 1

pdf bib
A Noisy Channel Model for Grapheme-based Machine Transliteration
Yuxiang Jia | Danqing Zhu | Shiwen Yu
Proceedings of the 2009 Named Entities Workshop: Shared Task on Transliteration (NEWS 2009)


pdf bib
Unsupervised Chinese Verb Metaphor Recognition Based on Selectional Preferences
Yuxiang Jia | Shiwen Yu
Proceedings of the 22nd Pacific Asia Conference on Language, Information and Computation