607 citations · 2.2k across the 78 of their papers we have counts for
52 papers · 1 filter
Metadata-Induced Contrastive Learning for Zero-Shot Multi-Label Text Classification
Yu Zhang, Zhihong Shen, Chieh-Han Wu +5
Large-scale multi-label text classification (LMTC) aims to associate a document with its relevant labels from a large candidate set. Most existing LMTC approaches rely on massive h…
MotifClass: Weakly Supervised Text Classification with Higher-order Metadata Information
Yu Zhang, Shweta Garg, Yu Meng +2
We study the problem of weakly supervised text classification, which aims to classify text documents into a set of pre-defined categories with category surface names only and witho…
Fine-Grained Opinion Summarization with Minimal Supervision
Suyu Ge, Jiaxin Huang, Yu Meng +2
Opinion summarization aims to profile a target by extracting opinions from multiple documents. Most existing work approaches the task in a semi-supervised manner due to the difficu…
Entity Linking Meets Deep Learning: Techniques and Solutions
Wei Shen, Yuhan Li, Yinan Liu +3
Entity linking (EL) is the process of linking entity mentions appearing in web text with their corresponding entities in a knowledge base. EL plays an important role in the fields…
Distantly-Supervised Named Entity Recognition with Noise-Robust Learning and Language Model Augmented Self-Training
Yu Meng, Yunyi Zhang, Jiaxin Huang +4
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…
SAIS: Supervising and Augmenting Intermediate Steps for Document-Level Relation Extraction
Yuxin Xiao, Zecheng Zhang, Yuning Mao +2
Stepping from sentence-level to document-level, the research on relation extraction (RE) confronts increasing text length and more complicated entity interactions. Consequently, it…
Corpus-based Open-Domain Event Type Induction
Jiaming Shen, Yunyi Zhang, Heng Ji +1
Traditional event extraction methods require predefined event types and their corresponding annotations to learn event extractors. These prerequisites are often hard to be satisfie…
Multi-head or Single-head? An Empirical Comparison for Transformer Training
Liyuan Liu, Jialu Liu, Jiawei Han
Multi-head attention plays a crucial role in the recent success of Transformer models, which leads to consistent performance improvements over conventional attention in various app…
Training ELECTRA Augmented with Multi-word Selection
Jiaming Shen, Jialu Liu, Tianqi Liu +2
Pre-trained text encoders such as BERT and its variants have recently achieved state-of-the-art performances on many NLP tasks. While being effective, these pre-training methods ty…
UCPhrase: Unsupervised Context-aware Quality Phrase Tagging
Xiaotao Gu, Zihan Wang, Zhenyu Bi +4
Identifying and understanding quality phrases from context is a fundamental task in text mining. The most challenging part of this task arguably lies in uncommon, emerging, and dom…
Document-Level Event Argument Extraction by Conditional Generation
Sha Li, Heng Ji, Jiawei Han
Event extraction has long been treated as a sentence-level task in the IE community. We argue that this setting does not match human information-seeking behavior and leads to incom…
Who Should Go First? A Self-Supervised Concept Sorting Model for Improving Taxonomy Expansion
Xiangchen Song, Jiaming Shen, Jieyu Zhang +1
Taxonomies have been widely used in various machine learning and text mining systems to organize knowledge and facilitate downstream tasks. One critical challenge is that, as data…
Extract, Denoise and Enforce: Evaluating and Improving Concept Preservation for Text-to-Text Generation
Yuning Mao, Wenchang Ma, Deren Lei +2
Prior studies on text-to-text generation typically assume that the model could figure out what to attend to in the input and what to include in the output via seq2seq learning, wit…
Minimally-Supervised Structure-Rich Text Categorization via Learning on Text-Rich Networks
Xinyang Zhang, Chenwei Zhang, Luna Xin Dong +2
Text categorization is an essential task in Web content analysis. Considering the ever-evolving Web data and new emerging categories, instead of the laborious supervised setting, i…
COCO-LM: Correcting and Contrasting Text Sequences for Language Model Pretraining
Yu Meng, Chenyan Xiong, Payal Bajaj +4
We present a self-supervised learning framework, COCO-LM, that pretrains Language Models by COrrecting and COntrasting corrupted text sequences. Following ELECTRA-style pretraining…
MATCH: Metadata-Aware Text Classification in A Large Hierarchy
Yu Zhang, Zhihong Shen, Yuxiao Dong +2
Multi-label text classification refers to the problem of assigning each given document its most relevant labels from the label set. Commonly, the metadata of the given documents an…
Rider: Reader-Guided Passage Reranking for Open-Domain Question Answering
Yuning Mao, Pengcheng He, Xiaodong Liu +4
Current open-domain question answering systems often follow a Retriever-Reader architecture, where the retriever first retrieves relevant passages and the reader then reads the ret…
Few-Shot Named Entity Recognition: A Comprehensive Study
Jiaxin Huang, Chunyuan Li, Krishan Subudhi +6
This paper presents a comprehensive study to efficiently build named entity recognition (NER) systems when a small number of in-domain labeled data is available. Based upon recent…
CoDA: Contrast-enhanced and Diversity-promoting Data Augmentation for Natural Language Understanding
Yanru Qu, Dinghan Shen, Yelong Shen +3
Data augmentation has been demonstrated as an effective strategy for improving model generalization and data efficiency. However, due to the discrete nature of natural language, de…
Text Classification Using Label Names Only: A Language Model Self-Training Approach
Yu Meng, Yunyi Zhang, Jiaxin Huang +4
Current text classification methods typically require a good number of human-labeled documents as training data, which can be costly and difficult to obtain in real applications. H…
CoRel: Seed-Guided Topical Taxonomy Construction by Concept Learning and Relation Transferring
Jiaxin Huang, Yiqing Xie, Yu Meng +2
Taxonomy is not only a fundamental form of knowledge representation, but also crucial to vast knowledge-rich applications, such as question answering and web search. Most existing…
Weakly-Supervised Aspect-Based Sentiment Analysis via Joint Aspect-Sentiment Topic Embedding
Jiaxin Huang, Yu Meng, Fang Guo +2
Aspect-based sentiment analysis of review texts is of great value for understanding user feedback in a fine-grained manner. It has in general two sub-tasks: (i) extracting aspects…
Hierarchical Metadata-Aware Document Categorization under Weak Supervision
Yu Zhang, Xiusi Chen, Yu Meng +1
Categorizing documents into a given label hierarchy is intuitively appealing due to the ubiquity of hierarchical topic structures in massive text corpora. Although related studies…
Constrained Abstractive Summarization: Preserving Factual Consistency with Constrained Generation
Yuning Mao, Xiang Ren, Heng Ji +1
Despite significant progress, state-of-the-art abstractive summarization methods are still prone to hallucinate content inconsistent with the source document. In this paper, we pro…