Export Citations
Publications
Save this search
Please login to be able to save your searches and receive alerts for new content matching your search criteria.
- research-article
COCO-LM: correcting and contrasting text sequences for language model pretraining
NIPS '21: Proceedings of the 35th International Conference on Neural Information Processing Systems•December 2021, Article No.: 1769, pp 23102-23114We present a self-supervised learning framework, COCO-LM, that pretrains Language Models by COrrecting and COntrasting corrupted text sequences. Following ELECTRA-style pretraining, COCO-LM employs an auxiliary language model to corrupt text sequences, ...
- research-article
Large language model as attributed training data generator: a tale of diversity and bias
NIPS '23: Proceedings of the 37th International Conference on Neural Information Processing Systems•December 2023, Article No.: 2433, pp 55734-55784Large language models (LLMs) have been recently leveraged as training data generators for various natural language processing (NLP) tasks. While previous research has explored different approaches to training models using generated data, they generally ...
- research-article
Generating training data with language models: towards zero-shot language understanding
NIPS '22: Proceedings of the 36th International Conference on Neural Information Processing Systems•November 2022, Article No.: 34, pp 462-477Pretrained language models (PLMs) have demonstrated remarkable performance in various natural language processing tasks: Unidirectional PLMs (e.g., GPT) are well known for their superior text generation capabilities; bidirectional PLMs (e.g., BERT) have ...
- abstract
Pretrained Language Representations for Text Understanding: A Weakly-Supervised Perspective
KDD '23: Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining•August 2023, pp 5817-5818• https://doi.org/10.1145/3580305.3599569Language 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 ...
- research-article
Weakly Supervised Multi-Label Classification of Full-Text Scientific Papers
KDD '23: Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining•August 2023, pp 3458-3469• https://doi.org/10.1145/3580305.3599544Instead of relying on human-annotated training samples to build a classifier, weakly supervised scientific paper classification aims to classify papers only using category descriptions (e.g., category names, category-indicative keywords). Existing ...
- research-article
Tuning language models as training data generators for augmentation-enhanced few-shot learning
ICML'23: Proceedings of the 40th International Conference on Machine Learning•July 2023, Article No.: 1018, pp 24457-24477Recent studies have revealed the intriguing few-shot learning ability of pretrained language models (PLMs): They can quickly adapt to a new task when fine-tuned on a small amount of labeled data formulated as prompts, without requiring abundant task-...
- tutorial
Tutorials at The Web Conference 2023
- Valeria Fionda,
- Olaf Hartig,
- Reyhaneh Abdolazimi,
- Sihem Amer-Yahia,
- Hongzhi Chen,
- Xiao Chen,
- Peng Cui,
- Jeffrey Dalton,
- Xin Luna Dong,
- Lisette Espin-Noboa,
- Wenqi Fan,
- Manuela Fritz,
- Quan Gan,
- Jingtong Gao,
- Xiaojie Guo,
- Torsten Hahmann,
- Jiawei Han,
- Soyeon Han,
- Estevam Hruschka,
- Liang Hu,
- Jiaxin Huang,
- Utkarshani Jaimini,
- Olivier Jeunen,
- Yushan Jiang,
- Fariba Karimi,
- George Karypis,
- Krishnaram Kenthapadi,
- Himabindu Lakkaraju,
- Hady W. Lauw,
- Thai Le,
- Trung-Hoang Le,
- Dongwon Lee,
- Geon Lee,
- Liat Levontin,
- Cheng-Te Li,
- Haoyang Li,
- Ying Li,
- Jay Chiehen Liao,
- Qidong Liu,
- Usha Lokala,
- Ben London,
- Siqu Long,
- Hande Kücük Mcginty,
- Yu Meng,
- Seungwhan Moon,
- Usman Naseem,
- Pradeep Natarajan,
- Behrooz Omidvar-Tehrani,
- Zijie Pan,
- Devesh Parekh,
- Jian Pei,
- Tiago Peixoto,
- Steven Pemberton,
- Josiah Poon,
- Filip Radlinski,
- Federico Rossetto,
- Kaushik Roy,
- Aghiles Salah,
- Mehrnoosh Sameki,
- Amit Sheth,
- Cogan Shimizu,
- Kijung Shin,
- Dongjin Song,
- Julia Stoyanovich,
- Dacheng Tao,
- Johanne Trippas,
- Quoc Truong,
- Yu-Che Tsai,
- Adaku Uchendu,
- Bram Van Den Akker,
- Lin Wang,
- Minjie Wang,
- Shoujin Wang,
- Xin Wang,
- Ingmar Weber,
- Henry Weld,
- Lingfei Wu,
- Da Xu,
- Ethan Yifan Xu,
- Shuyuan Xu,
- Bo Yang,
- Ke Yang,
- Elad Yom-Tov,
- Jaemin Yoo,
- Zhou Yu,
- Reza Zafarani,
- Hamed Zamani,
- Meike Zehlike,
- Qi Zhang,
- Xikun Zhang,
- Yongfeng Zhang,
- Yu Zhang,
- Zheng Zhang,
- Liang Zhao,
- Xiangyu Zhao,
- Wenwu Zhu
WWW '23 Companion: Companion Proceedings of the ACM Web Conference 2023•April 2023, pp 648-658• https://doi.org/10.1145/3543873.3587713This paper summarizes the content of the 28 tutorials that have been given at The Web Conference 2023.
- research-article
SCStory: Self-supervised and Continual Online Story Discovery
WWW '23: Proceedings of the ACM Web Conference 2023•April 2023, pp 1853-1864• https://doi.org/10.1145/3543507.3583507We present a framework SCStory for online story discovery, that helps people digest rapidly published news article streams in real-time without human annotations. To organize news article streams into stories, existing approaches directly encode the ...
- research-article
The Effect of Metadata on Scientific Literature Tagging: A Cross-Field Cross-Model Study
WWW '23: Proceedings of the ACM Web Conference 2023•April 2023, pp 1626-1637• https://doi.org/10.1145/3543507.3583354Due to the exponential growth of scientific publications on the Web, there is a pressing need to tag each paper with fine-grained topics so that researchers can track their interested fields of study rather than drowning in the whole literature. ...
- research-article
Effective Seed-Guided Topic Discovery by Integrating Multiple Types of Contexts
WSDM '23: Proceedings of the Sixteenth ACM International Conference on Web Search and Data Mining•February 2023, pp 429-437• https://doi.org/10.1145/3539597.3570475Instead of mining coherent topics from a given text corpus in a completely unsupervised manner, seed-guided topic discovery methods leverage user-provided seed words to extract distinctive and coherent topics so that the mined topics can better cater to ...
- research-article
FineSum: Target-Oriented, Fine-Grained Opinion Summarization
WSDM '23: Proceedings of the Sixteenth ACM International Conference on Web Search and Data Mining•February 2023, pp 1093-1101• https://doi.org/10.1145/3539597.3570397Target-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, ...
- abstract
Adapting Pretrained Representations for Text Mining
KDD '22: Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining•August 2022, pp 4806-4807• https://doi.org/10.1145/3534678.3542607Pretrained text representations, evolving from context-free word embeddings to contextualized language models, have brought text mining into a new era: By pretraining neural models on large-scale text corpora and then adapting them to task-specific data, ...
- research-article
Few-Shot Fine-Grained Entity Typing with Automatic Label Interpretation and Instance Generation
KDD '22: Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining•August 2022, pp 605-614• https://doi.org/10.1145/3534678.3539443We study the problem of few-shot Fine-grained Entity Typing (FET), where only a few annotated entity mentions with contexts are given for each entity type. Recently, prompt-based tuning has demonstrated superior performance to standard fine-tuning in few-...
- research-article
Topic Discovery via Latent Space Clustering of Pretrained Language Model Representations
WWW '22: Proceedings of the ACM Web Conference 2022•April 2022, pp 3143-3152• https://doi.org/10.1145/3485447.3512034Topic models have been the prominent tools for automatic topic discovery from text corpora. Despite their effectiveness, topic models suffer from several limitations including the inability of modeling word ordering information in documents, the ...
- research-article
Simulating online social response: a stimulus/response perspective
- Huajie Shao,
- Tarek Abdelzaher,
- Jiawei Han,
- Minhao Jiang,
- Yuning Mao,
- Yu Meng,
- Wenda Qiu,
- Dachun Sun,
- Ruijie Wang,
- Chaoqi Yang,
- Zhenzhou Yang,
- Xinyang Zhang,
- Yu Zhang,
- Sam Cohen,
- James Flamino,
- Gyorgy Korniss,
- Omar Malik,
- Aamir Mandviwalla,
- Boleslaw Szymanski,
- Lake Yin
The paper describes a methodology for simulating online social media activities that occur in response to external events. A large number of social media simulators model information diffusion on online social networks. However, information cascades do ...
- research-article
MotifClass: Weakly Supervised Text Classification with Higher-order Metadata Information
WSDM '22: Proceedings of the Fifteenth ACM International Conference on Web Search and Data Mining•February 2022, pp 1357-1367• https://doi.org/10.1145/3488560.3498384We 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 without any annotated training document provided. Most existing classifiers ...
- abstract
On the Power of Pre-Trained Text Representations: Models and Applications in Text Mining
KDD '21: Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining•August 2021, pp 4052-4053• https://doi.org/10.1145/3447548.3470810Recent years have witnessed the enormous success of text representation learning in a wide range of text mining tasks. Earlier word embedding learning approaches represent words as fixed low-dimensional vectors to capture their semantics. The word ...
- research-article
UCPhrase: Unsupervised Context-aware Quality Phrase Tagging
KDD '21: Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining•August 2021, pp 478-486• https://doi.org/10.1145/3447548.3467397Identifying 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 domain-specific phrases. The infrequent nature of these phrases ...
- research-article
Hierarchical Metadata-Aware Document Categorization under Weak Supervision
WSDM '21: Proceedings of the 14th ACM International Conference on Web Search and Data Mining•March 2021, pp 770-778• https://doi.org/10.1145/3437963.3441730Categorizing documents into a given label hierarchy is intuitively appealing due to the ubiquity of hierarchical topic structures in massive text corpora. Although related studies have achieved satisfying performance in fully supervised hierarchical ...
- tutorial
Embedding-Driven Multi-Dimensional Topic Mining and Text Analysis
KDD '20: Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining•August 2020, pp 3573-3574• https://doi.org/10.1145/3394486.3406483People nowadays are immersed in a wealth of text data, ranging from news articles, to social media, academic publications, advertisements, and economic reports. A grand challenge of data mining is to develop effective, scalable and weakly-supervised ...