JHJiaxin Huang

Jiaxin Huang

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Jiaxin Huang has a total of 111 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Ontology Enrichment for Effective Fine-grained Entity Typing

    by Siru Ouyang, Jiaxin Huang, Pranav Pillai, Yunyi Zhang, Yu Zhang, Jiawei Han

    Fine-grained entity typing (FET) is the task of identifying specific entity types at a fine-grained level for entity mentions based on their contextual information. Conventional methods for FET require extensive human annotation, which is time-consuming and costly given the massive scale of data. Recent studies have been developing weakly supervised or zero-shot approaches. We study the setting of zero-shot FET where only an ontology is provided. However, most existing ontology structures lack rich supporting information and even contain ambiguous relations, making them ineffective in guiding FET. Recently developed language models, though promising in various few-shot and zero-shot NLP tasks, may face challenges in zero-shot FET due to their lack of interaction with task-specific ontology. In this study, we propose øurs, where we (1) enrich each node in the ontology structure with two categories of extra information:instance information for training sample augmentation andtopic information to relate types with contexts, and (2) develop a coarse-to-fine typing algorithm that exploits the enriched information by training an entailment model with contrasting topics and instance-based augmented training samples. Our experiments show that øurs achieves high-quality fine-grained entity typing without human annotation, outperforming existing zero-shot methods by a large margin and rivaling supervised methods. øurs also enjoys strong transferability to unseen and finer-grained types. We will open source this work upon acceptance.


  • Autoinducer‐2 produced by oral microbial flora and alveolar bone loss in periodontitis

    by Cheng Li, Hancheng Zhou, Huiqing Gou, Zixin Fan, Yifei Zhang, Pengzhou Tang, Jiaxin Huang, Yan Xu, Lu Li

    Objective: The aim of this study was to investigate the association between autoinducer‐2 (AI‐2) of oral microbial flora and the alveolar bone destruction in periodontitis to determine if AI‐2 may have the potential that monitor periodontitis and predict bone loss.Background: Plaque biofilm was the initiating factor of periodontitis and the essential factor of periodontal tissue destruction. The formation of biofilms depended on the complex regulation of the quorum sensing (QS) system, in which bacteria could sense changes in surrounding bacterial density by secreting the autoinducer (AI) to regulate the corresponding physiological function. Most oral bacteria also communicated with each other to form biofilms administrating the QS system, which implied that the QS system of periodontal pathogens was related to periodontitis, but the specific relationship was unknown.Method: We collected the gingival crevicular fluid (GCF) samples and measured the concentration of AI‐2 in samples using the Vibrio harveyi BB180 bioluminescent‐reporter system. To explore the interaction between AI‐2 and bone metabolism, we utilized AI‐2 purified from Fusobacterium nucleatum to investigate the impact of F. nucleatum AI‐2 on osteoclast differentiation. Moreover, we constructed murine periodontitis models and multi‐species biofilm models to study the association between AI‐2 and periodontal disease progression.Results: The AI‐2 concentration in GCF samples increased along with periodontal disease progression (p < .0001). F. nucleatum AI‐2 promoted osteoclast differentiation in a dose‐dependent manner. In the periodontitis mice model, the CEJ‐ABC distance in the F. nucleatum AI‐2 treatment group was higher than that in the simple ligation group (p < .01), and the maxilla of the mice in the group exhibited significantly lower BMD and BV/TV values (p < .05).Conclusions: We demonstrated that the AI‐2 concentration varied with the alveolar bone destruction in periodontitis, and it may have the potential for screening periodontitis. F. nucleatum AI‐2 promoted osteoclast differentiation in a dose‐dependent manner and aggravated bone loss.


  • Open Access

    Pretrained Language Representations for Text Understanding: A Weakly-Supervised Perspective

    by Yu Meng, Jiaxin Huang, Yu Zhang, Yunyi Zhang, Jiawei Han

    Language representations pretrained on general-domain corpora and adapted to downstream task data have achieved enormous success in building natural language understanding (NLU) systems. While the standard supervised fine-tuning of pretrained language models (PLMs) has proven an effective approach for superior NLU performance, it often necessitates a large quantity of costly human-annotated training data. For example, the enormous success of ChatGPT and GPT-4 can be largely credited to their supervised fine-tuning with massive manually-labeled prompt-response training pairs. Unfortunately, obtaining large-scale human annotations is in general infeasible for most practitioners. To broaden the applicability of PLMs to various tasks and settings, weakly-supervised learning offers a promising direction to minimize the annotation requirements for PLM adaptions. In this tutorial, we cover the recent advancements in pretraining language models and adaptation methods for a wide range of NLU tasks. Our tutorial has a particular focus on weakly-supervised approaches that do not require massive human annotations. We will introduce the following topics in this tutorial: (1) pretraining language representation models that serve as the fundamentals for various NLU tasks, (2) extracting entities and hierarchical relations from unlabeled texts, (3) discovering topical structures from massive text corpora for text organization, and (4) understanding documents and sentences with weakly-supervised techniques.

  • Open Access

    Tutorials at The Web Conference 2023

    by Valeria Fionda, Olaf Hartig, Reyhaneh Abdolazimi, Sihem Amer-Yahia, Hongzhi Chen, Xiao Chen, Peng Cui, Jeffrey Dalton, Xin Luna Dong, Lisette Espin-Noboa, et al.

    This paper summarizes the content of the 28 tutorials that have been given at The Web Conference 2023.


  • Open Access

    FineSum: Target-Oriented, Fine-Grained Opinion Summarization

    by Suyu Ge, Jiaxin Huang, Yu Meng, Jiawei Han

    Target-oriented opinion summarization is to profile a target by extracting user opinions from multiple related documents. Instead of simply mining opinion ratings on a target (e.g., a restaurant) or on multiple aspects (e.g., food, service) of a target, it is desirable to go deeper, to mine opinion on fine-grained sub-aspects (e.g., fish). However, it is expensive to obtain high-quality annotations at such fine-grained scale. This leads to our proposal of a new framework, FineSum, which advances the frontier of opinion analysis in three aspects: (1) minimal supervision, where no document-summary pairs are provided, only aspect names and a few aspect/sentiment keywords are available; (2) fine-grained opinion analysis, where sentiment analysis drills down to a specific subject or characteristic within each general aspect; and (3) phrase-based summarization, where short phrases are taken as basic units for summarization, and semantically coherent phrases are gathered to improve the consistency and comprehensiveness of summary. Given a large corpus with no annotation, FineSum first automatically identifies potential spans of opinion phrases, and further reduces the noise in identification results using aspect and sentiment classifiers. It then constructs multiple fine-grained opinion clusters under each aspect and sentiment. Each cluster expresses uniform opinions towards certain sub-aspects (e.g., "fish" in "food" aspect) or characteristics (e.g., "Mexican" in "food" aspect). To accomplish this, we train a spherical word embedding space to explicitly represent different aspects and sentiments. We then distill the knowledge from embedding to a contextualized phrase classifier, and perform clustering using the contextualized opinion-aware phrase embedding. Both automatic evaluations on the benchmark and quantitative human evaluation validate the effectiveness of our approach.


  • Open Access

    Distantly-Supervised Named Entity Recognition with Noise-Robust Learning and Language Model Augmented Self-Training

    by Yu Meng, Yunyi Zhang, Jiaxin Huang, Xuan Wang, Yu Zhang, Heng Ji, Jiawei Han

    We study the problem of training named entity recognition (NER) models using only distantly-labeled data, which can be automatically obtained by matching entity mentions in the raw text with entity types in a knowledge base. The biggest challenge of distantly-supervised NER is that the distant supervision may induce incomplete and noisy labels, rendering the straightforward application of supervised learning ineffective. In this paper, we propose (1) a noise-robust learning scheme comprised of a new loss function and a noisy label removal step, for training NER models on distantly-labeled data, and (2) a self-training method that uses contextualized augmentations created by pre-trained language models to improve the generalization ability of the NER model. On three benchmark datasets, our method achieves superior performance, outperforming existing distantly-supervised NER models by significant margins.