Jiaoyan Chen


pdf bib
DET: A Dual-Encoding Transformer for Relational Graph Embedding
Lingbing Guo | Zhuo Chen | Jiaoyan Chen | Qiang Zhang | Huajun Chen
Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)

Despite recent successes in natural language processing and computer vision, Transformer faces scalability issues when processing graphs, e.g., computing the full node-to-node attention on knowledge graphs (KGs) with million of entities is still infeasible. The existing methods mitigate this problem by considering only the local neighbors, sacrificing the Transformer’s ability to attend to elements at any distance. This paper proposes a new Transformer architecture called Dual-Encoding Transformer (DET). DET comprises a structural encoder to aggregate information from nearby neighbors, and a semantic encoder to seek for semantically relevant nodes. We adopt a semantic neighbor search approach inspired by multiple sequence alignment (MSA) algorithms used in biological sciences. By stacking the two encoders alternately, similar to the MSA Transformer for protein representation, our method achieves superior performance compared to state-of-the-art attention-based methods on complex relational graphs like KGs and citation networks. Additionally, DET remains competitive for smaller graphs such as molecules.

pdf bib
TacoERE: Cluster-aware Compression for Event Relation Extraction
Yong Guan | Xiaozhi Wang | Lei Hou | Juanzi Li | Jeff Z. Pan | Jiaoyan Chen | Freddy Lecue
Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)

Event relation extraction (ERE) is a critical and fundamental challenge for natural language processing. Existing work mainly focuses on directly modeling the entire document, which cannot effectively handle long-range dependencies and information redundancy. To address these issues, we propose a cluster-aware compression method for improving event relation extraction (TacoERE), which explores a compression-then-extraction paradigm. Specifically, we first introduce document clustering for modeling event dependencies. It splits the document into intra- and inter-clusters, where intra-clusters aim to enhance the relations within the same cluster, while inter-clusters attempt to model the related events at arbitrary distances. Secondly, we utilize cluster summarization to simplify and highlight important text content of clusters for mitigating information redundancy and event distance. We have conducted extensive experiments on both pre-trained language models, such as RoBERTa, and large language models, such as ChatGPT and GPT-4, on three ERE datasets, i.e., MAVEN-ERE, EventStoryLine and HiEve. Experimental results demonstrate that TacoERE is an effective method for ERE.

pdf bib
Exploring the Impact of Table-to-Text Methods on Augmenting LLM-based Question Answering with Domain Hybrid Data
Dehai Min | Nan Hu | Rihui Jin | Nuo Lin | Jiaoyan Chen | Yongrui Chen | Yu Li | Guilin Qi | Yun Li | Nijun Li | Qianren Wang
Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 6: Industry Track)

Augmenting Large Language Models (LLMs) for Question Answering (QA) with domain specific data has attracted wide attention. However, domain data often exists in a hybrid format, including text and semi-structured tables, posing challenges for the seamless integration of information. Table-to-Text Generation is a promising solution by facilitating the transformation of hybrid data into a uniformly text-formatted corpus. Although this technique has been widely studied by the NLP community, there is currently no comparative analysis on how corpora generated by different table-to-text methods affect the performance of QA systems.In this paper, we address this research gap in two steps. First, we innovatively integrate table-to-text generation into the framework of enhancing LLM-based QA systems with domain hybrid data. Then, we utilize this framework in real-world industrial data to conduct extensive experiments on two types of QA systems (DSFT and RAG frameworks) with four representative methods: Markdown format, Template serialization, TPLM-based method, and LLM-based method. Based on the experimental results, we draw some empirical findings and explore the underlying reasons behind the success of some methods. We hope the findings of this work will provide a valuable reference for the academic and industrial communities in developing robust QA systems.


pdf bib
Class Lifelong Learning for Intent Detection via Structure Consolidation Networks
Qingbin Liu | Yanchao Hao | Xiaolong Liu | Bo Li | Dianbo Sui | Shizhu He | Kang Liu | Jun Zhao | Xi Chen | Ningyu Zhang | Jiaoyan Chen
Findings of the Association for Computational Linguistics: ACL 2023

Intent detection, which estimates diverse intents behind user utterances, is an essential component of task-oriented dialogue systems. Previous intent detection models are usually trained offline, which can only handle predefined intent classes. In the real world, new intents may keep challenging deployed models. For example, with the prevalence of the COVID-19 pandemic, users may pose various issues related to the pandemic to conversational systems, which brings many new intents. A general intent detection model should be intelligent enough to continually learn new data and recognize new arriving intent classes. Therefore, this work explores Class Lifelong Learning for Intent Detection (CLL-ID), where the model continually learns new intent classes from new data while avoiding catastrophic performance degradation on old data. To this end, we propose a novel lifelong learning method, called Structure Consolidation Networks (SCN), which consists of structure-based retrospection and contrastive knowledge distillation to handle the problems of expression diversity and class imbalance in the CLL-ID task. In addition to formulating the new task, we construct 3 benchmarks based on 8 intent detection datasets. Experimental results demonstrate the effectiveness of SCN, which significantly outperforms previous lifelong learning methods on the three benchmarks.

pdf bib
Language Model Analysis for Ontology Subsumption Inference
Yuan He | Jiaoyan Chen | Ernesto Jimenez-Ruiz | Hang Dong | Ian Horrocks
Findings of the Association for Computational Linguistics: ACL 2023

Investigating whether pre-trained language models (LMs) can function as knowledge bases (KBs) has raised wide research interests recently. However, existing works focus on simple, triple-based, relational KBs, but omit more sophisticated, logic-based, conceptualised KBs such as OWL ontologies. To investigate an LM’s knowledge of ontologies, we propose OntoLAMA, a set of inference-based probing tasks and datasets from ontology subsumption axioms involving both atomic and complex concepts. We conduct extensive experiments on ontologies of different domains and scales, and our results demonstrate that LMs encode relatively less background knowledge of Subsumption Inference (SI) than traditional Natural Language Inference (NLI) but can improve on SI significantly when a small number of samples are given. We will open-source our code and datasets.

pdf bib
Trigger-Argument based Explanation for Event Detection
Yong Guan | Jiaoyan Chen | Freddy Lecue | Jeff Pan | Juanzi Li | Ru Li
Findings of the Association for Computational Linguistics: ACL 2023

Event Detection (ED) is a critical task that aims to identify events of certain types in plain text. Neural models have achieved great success on ED, thus coming with a desire for higher interpretability. Existing works mainly exploit words or phrases of the input text to explain models’ inner mechanisms. However, for ED, the event structure, comprising of an event trigger and a set of arguments, are more enlightening clues to explain model behaviors. To this end, we propose a Trigger-Argument based Explanation method (TAE), which can utilize event structure knowledge to uncover a faithful interpretation for the existing ED models at neuron level. Specifically, we design group, sparsity, support mechanisms to construct the event structure from structuralization, compactness, and faithfulness perspectives. We evaluate our model on the large-scale MAVEN and the widely-used ACE 2005 datasets, and observe that TAE is able to reveal the process by which the model predicts. Experimental results also demonstrate that TAE can not only improve the interpretability on standard evaluation metrics, but also effectively facilitate the human understanding.

pdf bib
Novel Relation Detection: Discovering Unknown Relation Types via Multi-Strategy Self-Supervised Learning
Qingbin Liu | Yin Kung | Yanchao Hao | Dianbo Sui | Siyuan Cheng | Xi Chen | Ningyu Zhang | Jiaoyan Chen
Findings of the Association for Computational Linguistics: EMNLP 2023

Conventional approaches to relation extraction can only recognize predefined relation types. In the real world, new or out-of-scope relation types may keep challenging the deployed models. In this paper, we formalize such a challenging problem as Novel Relation Detection (NRD), which aims to discover potential new relation types based on training samples of known relations. To this end, we construct two NRD datasets and exhaustively investigate a variety of out-of-scope detection methods. We further propose an effective NRD method that utilizes multi-strategy self-supervised learning to handle the problem of shallow semantic similarity in the NRD task. Experimental results demonstrate the effectiveness of our method, which significantly outperforms previous state-of-the-art methods on both datasets.


pdf bib
UoR-NCL at SemEval-2022 Task 3: Fine-Tuning the BERT-Based Models for Validating Taxonomic Relations
Thanet Markchom | Huizhi Liang | Jiaoyan Chen
Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022)

In human languages, there are many presuppositional constructions that impose a constrain on the taxonomic relations between two nouns depending on their order. These constructions create a challenge in validating taxonomic relations in real-world contexts. In SemEval2022-Task3 Presupposed Taxonomies: Evaluating Neural Network Semantics (PreTENS), the organizers introduced a task regarding validating the taxonomic relations within a variety of presuppositional constructions. This task is divided into two subtasks: classification and regression. Each subtask contains three datasets in multiple languages, i.e., English, Italian and French. To tackle this task, this work proposes to fine-tune different BERT-based models pre-trained on different languages. According to the experimental results, the fine-tuned BERT-based models are effective compared to the baselines in classification. For regression, the fine-tuned models show promising performance with the possibility of improvement.


pdf bib
OntoEA: Ontology-guided Entity Alignment via Joint Knowledge Graph Embedding
Yuejia Xiang | Ziheng Zhang | Jiaoyan Chen | Xi Chen | Zhenxi Lin | Yefeng Zheng
Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021


pdf bib
Zero-shot Text Classification via Reinforced Self-training
Zhiquan Ye | Yuxia Geng | Jiaoyan Chen | Jingmin Chen | Xiaoxiao Xu | SuHang Zheng | Feng Wang | Jun Zhang | Huajun Chen
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

Zero-shot learning has been a tough problem since no labeled data is available for unseen classes during training, especially for classes with low similarity. In this situation, transferring from seen classes to unseen classes is extremely hard. To tackle this problem, in this paper we propose a self-training based method to efficiently leverage unlabeled data. Traditional self-training methods use fixed heuristics to select instances from unlabeled data, whose performance varies among different datasets. We propose a reinforcement learning framework to learn data selection strategy automatically and provide more reliable selection. Experimental results on both benchmarks and a real-world e-commerce dataset show that our approach significantly outperforms previous methods in zero-shot text classification

pdf bib
An Industry Evaluation of Embedding-based Entity Alignment
Ziheng Zhang | Hualuo Liu | Jiaoyan Chen | Xi Chen | Bo Liu | YueJia Xiang | Yefeng Zheng
Proceedings of the 28th International Conference on Computational Linguistics: Industry Track

Embedding-based entity alignment has been widely investigated in recent years, but most proposed methods still rely on an ideal supervised learning setting with a large number of unbiased seed mappings for training and validation, which significantly limits their usage. In this study, we evaluate those state-of-the-art methods in an industrial context, where the impact of seed mappings with different sizes and different biases is explored. Besides the popular benchmarks from DBpedia and Wikidata, we contribute and evaluate a new industrial benchmark that is extracted from two heterogeneous knowledge graphs (KGs) under deployment for medical applications. The experimental results enable the analysis of the advantages and disadvantages of these alignment methods and the further discussion of suitable strategies for their industrial deployment.