1 code implementation • EMNLP (ACL) 2021 • Wenhao Yu, Meng Jiang, Zhiting Hu, Qingyun Wang, Heng Ji, Nazneen Rajani
Knowledge-enriched text generation poses unique challenges in modeling and learning, driving active research in several core directions, ranging from integrated modeling of neural representations and symbolic information in the sequential/hierarchical/graphical structures, learning without direct supervisions due to the cost of structured annotation, efficient optimization and inference with massive and global constraints, to language grounding on multiple modalities, and generative reasoning with implicit commonsense knowledge and background knowledge.
no code implementations • ACL 2022 • Chenguang Zhu, Yichong Xu, Xiang Ren, Bill Lin, Meng Jiang, Wenhao Yu
Knowledge in natural language processing (NLP) has been a rising trend especially after the advent of large scale pre-trained models.
no code implementations • 15 Sep 2023 • Marinka Zitnik, Michelle M. Li, Aydin Wells, Kimberly Glass, Deisy Morselli Gysi, Arjun Krishnan, T. M. Murali, Predrag Radivojac, Sushmita Roy, Anaïs Baudot, Serdar Bozdag, Danny Z. Chen, Lenore Cowen, Kapil Devkota, Anthony Gitter, Sara Gosline, Pengfei Gu, Pietro H. Guzzi, Heng Huang, Meng Jiang, Ziynet Nesibe Kesimoglu, Mehmet Koyuturk, Jian Ma, Alexander R. Pico, Nataša Pržulj, Teresa M. Przytycka, Benjamin J. Raphael, Anna Ritz, Roded Sharan, Yang shen, Mona Singh, Donna K. Slonim, Hanghang Tong, Xinan Holly Yang, Byung-Jun Yoon, Haiyuan Yu, Tijana Milenković
As such, it is expected to help shape short- and long-term vision for future computational and algorithmic research in network biology.
1 code implementation • 8 Sep 2023 • Eric Inae, Gang Liu, Meng Jiang
Attribute reconstruction is used to predict node or edge features in the pre-training of graph neural networks.
no code implementations • 8 Jul 2023 • Hy Dang, Bang Nguyen, Noah Ziems, Meng Jiang
Our paper investigates the use of discourse embedding techniques to develop a community recommendation system that focuses on mental health support groups on social media.
no code implementations • 27 Jun 2023 • Albert Lu, Meng Jiang
Review score prediction requires review text understanding, a critical real-world application of natural language processing.
no code implementations • 28 May 2023 • Meng Jiang, Hy Dang, Lingbo Tong
Language models (LMs) are being scaled and becoming powerful.
no code implementations • 23 May 2023 • Wenhao Yu, Zhihan Zhang, Zhenwen Liang, Meng Jiang, Ashish Sabharwal
ReFeed first generates initial outputs, then utilizes a retrieval model to acquire relevant information from large document collections, and finally incorporates the retrieved information into the in-context demonstration for output refinement, thereby addressing the limitations of LLMs in a more efficient and cost-effective manner.
no code implementations • 23 May 2023 • Wenhao Yu, Meng Jiang, Peter Clark, Ashish Sabharwal
Although counterfactual reasoning is a fundamental aspect of intelligence, the lack of large-scale counterfactual open-domain question-answering (QA) benchmarks makes it difficult to evaluate and improve models on this ability.
1 code implementation • 23 May 2023 • Zhihan Zhang, Wenhao Yu, Zheng Ning, Mingxuan Ju, Meng Jiang
Contrast consistency, the ability of a model to make consistently correct predictions in the presence of perturbations, is an essential aspect in NLP.
no code implementations • 23 May 2023 • Mengxia Yu, Zhihan Zhang, Wenhao Yu, Meng Jiang
In this paper, we propose a novel framework to pre-train language models for enhancing their abilities of comparative reasoning over texts.
1 code implementation • 20 May 2023 • Gang Liu, Tong Zhao, Eric Inae, Tengfei Luo, Meng Jiang
The training data balance is achieved by (1) pseudo-labeling more graphs for under-represented labels with a novel regression confidence measurement and (2) augmenting graph examples in latent space for remaining rare labels after data balancing with pseudo-labels.
1 code implementation • 16 May 2023 • Noah Ziems, Wenhao Yu, Zhihan Zhang, Meng Jiang
To overcome this limitation, recent autoregressive search engines replace the dual-encoder architecture by directly generating identifiers for relevant documents in the candidate pool.
1 code implementation • 17 Mar 2023 • Gang Liu, Eric Inae, Tong Zhao, Jiaxin Xu, Tengfei Luo, Meng Jiang
A conventional approach is training a model with the unlabeled graphs on self-supervised tasks and then fine-tuning the model on the prediction tasks.
1 code implementation • 19 Dec 2022 • Meng Jiang
Text data mining is the process of deriving essential information from language text.
1 code implementation • 23 Oct 2022 • Wenhao Yu, Chenguang Zhu, Zhihan Zhang, Shuohang Wang, Zhuosheng Zhang, Yuwei Fang, Meng Jiang
However, applying such methods to commonsense reasoning tasks faces two unique challenges, i. e., the lack of a general large-scale corpus for retrieval and a corresponding effective commonsense retriever.
1 code implementation • 7 Oct 2022 • Zhihan Zhang, Wenhao Yu, Chenguang Zhu, Meng Jiang
The entity knowledge is stored in the memory as latent representations, and the memory is pre-trained on Wikipedia along with encoder-decoder parameters.
1 code implementation • 21 Sep 2022 • Wenhao Yu, Dan Iter, Shuohang Wang, Yichong Xu, Mingxuan Ju, Soumya Sanyal, Chenguang Zhu, Michael Zeng, Meng Jiang
We call our method generate-then-read (GenRead), which first prompts a large language model to generate contextutal documents based on a given question, and then reads the generated documents to produce the final answer.
no code implementations • 11 Aug 2022 • Zijian Hu, Meng Jiang
We originally planned to employ existing models but realized that they processed a math word problem as a sequence or a homogeneous graph of tokens.
no code implementations • 9 Jul 2022 • Gang Liu, Zhihan Zhang, Zheng Ning, Meng Jiang
To enable explainability, recent techniques such as ACCENT and FIA are looking for counterfactual explanations that are specific historical actions of a user, the removal of which leads to a change to the recommendation result.
1 code implementation • 21 Jun 2022 • Xiaojie Guo, Qingkai Zeng, Meng Jiang, Yun Xiao, Bo Long, Lingfei Wu
Automatic product description generation for e-commerce has witnessed significant advancement in the past decade.
1 code implementation • 6 Jun 2022 • Gang Liu, Tong Zhao, Jiaxin Xu, Tengfei Luo, Meng Jiang
Rationale is defined as a subset of input features that best explains or supports the prediction by machine learning models.
Ranked #1 on
Graph Regression
on GlassTemp
no code implementations • 29 Apr 2022 • Toby Jia-Jun Li, Yuwen Lu, Jaylexia Clark, Meng Chen, Victor Cox, Meng Jiang, Yang Yang, Tamara Kay, Danielle Wood, Jay Brockman
The AI inequality is caused by (1) the technology divide in who has access to AI technologies in gig work; and (2) the data divide in who owns the data in gig work leads to unfair working conditions, growing pay gap, neglect of workers' diverse preferences, and workers' lack of trust in the platforms.
no code implementations • 7 Apr 2022 • Zhihan Zhang, Wenhao Yu, Mengxia Yu, Zhichun Guo, Meng Jiang
Multi-task learning (MTL) has become increasingly popular in natural language processing (NLP) because it improves the performance of related tasks by exploiting their commonalities and differences.
1 code implementation • NAACL (DLG4NLP) 2022 • Wenhao Yu, Chenguang Zhu, Lianhui Qin, Zhihan Zhang, Tong Zhao, Meng Jiang
A set of knowledge experts seek diverse reasoning on KG to encourage various generation outputs.
1 code implementation • 17 Feb 2022 • Tong Zhao, Wei Jin, Yozen Liu, Yingheng Wang, Gang Liu, Stephan Günnemann, Neil Shah, Meng Jiang
Overall, our work aims to clarify the landscape of existing literature in graph data augmentation and motivates additional work in this area, providing a helpful resource for researchers and practitioners in the broader graph machine learning domain.
1 code implementation • Findings (ACL) 2022 • Wenhao Yu, Chenguang Zhu, Yuwei Fang, Donghan Yu, Shuohang Wang, Yichong Xu, Michael Zeng, Meng Jiang
In addition to training with the masked language modeling objective, we propose two novel self-supervised pre-training tasks on word and sentence-level alignment between input text sequence and rare word definitions to enhance language modeling representation with dictionary.
no code implementations • 4 Aug 2021 • Joseph Kuebler, Lingbo Tong, Meng Jiang
Information extraction (IE) in scientific literature has facilitated many down-stream tasks.
2 code implementations • 5 Jun 2021 • Qingkai Zeng, Jinfeng Lin, Wenhao Yu, Jane Cleland-Huang, Meng Jiang
Automatic construction of a taxonomy supports many applications in e-commerce, web search, and question answering.
no code implementations • 3 Jun 2021 • Meng Jiang
Graph neural networks have been widely used for learning representations of nodes for many downstream tasks on graph data.
1 code implementation • NeurIPS 2021 • Tong Zhao, Gang Liu, Daheng Wang, Wenhao Yu, Meng Jiang
However, the causal relationship between the two variables was largely ignored for learning to predict links on a graph.
Ranked #1 on
Link Property Prediction
on ogbl-ddi
no code implementations • 25 May 2021 • Shawn Gu, Meng Jiang, Pietro Hiram Guzzi, Tijana Milenkovic
Prediction of node and graph labels are prominent network science tasks.
1 code implementation • EMNLP 2021 • Wenhao Yu, Chenguang Zhu, Tong Zhao, Zhichun Guo, Meng Jiang
Generating paragraphs of diverse contents is important in many applications.
1 code implementation • 17 Feb 2021 • Daheng Wang, Prashant Shiralkar, Colin Lockard, Binxuan Huang, Xin Luna Dong, Meng Jiang
Existing work linearize table cells and heavily rely on modifying deep language models such as BERT which only captures related cells information in the same table.
1 code implementation • 16 Feb 2021 • Zhichun Guo, Chuxu Zhang, Wenhao Yu, John Herr, Olaf Wiest, Meng Jiang, Nitesh V. Chawla
The recent success of graph neural networks has significantly boosted molecular property prediction, advancing activities such as drug discovery.
Ranked #1 on
Molecular Property Prediction (1-shot))
on Tox21
1 code implementation • 8 Feb 2021 • Jinfeng Lin, Yalin Liu, Qingkai Zeng, Meng Jiang, Jane Cleland-Huang
In this study, we propose a novel framework called Trace BERT (T-BERT) to generate trace links between source code and natural language artifacts.
Transfer Learning
Software Engineering
no code implementations • EMNLP (Eval4NLP) 2021 • Qingkai Zeng, Mengxia Yu, Wenhao Yu, Tianwen Jiang, Meng Jiang
It can be used to validate the label consistency (or catches the inconsistency) in multiple sets of NER data annotation.
no code implementations • 1 Jan 2021 • Qing Lu, Weiwen Jiang, Meng Jiang, Jingtong Hu, Sakyasingha Dasgupta, Yiyu Shi
The success of gragh neural networks (GNNs) in the past years has aroused grow-ing interest and effort in designing best models to handle graph-structured data.
no code implementations • Findings of the Association for Computational Linguistics 2020 • Qingkai Zeng, Wenhao Yu, Mengxia Yu, Tianwen Jiang, Tim Weninger, Meng Jiang
The training process of scientific NER models is commonly performed in two steps: i) Pre-training a language model by self-supervised tasks on huge data and ii) fine-tune training with small labelled data.
no code implementations • Findings of the Association for Computational Linguistics 2020 • Chuxu Zhang, Lu Yu, Mandana Saebi, Meng Jiang, Nitesh Chawla
Multi-hop relation reasoning over knowledge base is to generate effective and interpretable relation prediction through reasoning paths.
1 code implementation • 20 Oct 2020 • Tong Zhao, Bo Ni, Wenhao Yu, Zhichun Guo, Neil Shah, Meng Jiang
With Eland, anomaly detection performance at an earlier stage is better than non-augmented methods that need significantly more observed data by up to 15% on the Area under the ROC curve.
1 code implementation • NAACL 2021 • Wenhao Yu, Lingfei Wu, Yu Deng, Qingkai Zeng, Ruchi Mahindru, Sinem Guven, Meng Jiang
In this paper, we propose a novel framework of deep transfer learning to effectively address technical QA across tasks and domains.
3 code implementations • 9 Oct 2020 • Wenhao Yu, Chenguang Zhu, Zaitang Li, Zhiting Hu, Qingyun Wang, Heng Ji, Meng Jiang
To address this issue, researchers have considered incorporating various forms of knowledge beyond the input text into the generation models.
1 code implementation • EMNLP 2020 • Wenhao Yu, Lingfei Wu, Yu Deng, Ruchi Mahindru, Qingkai Zeng, Sinem Guven, Meng Jiang
In recent years, the need for community technical question-answering sites has increased significantly.
2 code implementations • EMNLP 2021 • Xiangyu Dong, Wenhao Yu, Chenguang Zhu, Meng Jiang
Our model has a multi-step decoder that injects the entity types into the process of entity mention generation.
no code implementations • 15 Sep 2020 • Meng Jiang, Taeho Jung, Ryan Karl, Tong Zhao
Given video data from multiple personal devices or street cameras, can we exploit the structural and dynamic information to learn dynamic representation of objects for applications such as distributed surveillance, without storing data at a central server that leads to a violation of user privacy?
1 code implementation • 25 Jul 2020 • Daheng Wang, Zhihan Zhang, Yihong Ma, Tong Zhao, Tianwen Jiang, Nitesh V. Chawla, Meng Jiang
In this work, we present a novel framework called CoEvoGNN for modeling dynamic attributed graph sequence.
no code implementations • 16 Jul 2020 • Zhiyu Liu, Meng Jiang, Hai Lin
For knowledge representation, we use a graph-based spatial temporal logic (GSTL) to capture spatial and temporal information of related skills demonstrated by demo videos.
no code implementations • 17 Jun 2020 • Tianwen Jiang, Tong Zhao, Bing Qin, Ting Liu, Nitesh V. Chawla, Meng Jiang
Noun phrases and relational phrases in Open Knowledge Bases are often not canonical, leading to redundant and ambiguous facts.
2 code implementations • 11 Jun 2020 • Tong Zhao, Yozen Liu, Leonardo Neves, Oliver Woodford, Meng Jiang, Neil Shah
Our work shows that neural edge predictors can effectively encode class-homophilic structure to promote intra-class edges and demote inter-class edges in given graph structure, and our main contribution introduces the GAug graph data augmentation framework, which leverages these insights to improve performance in GNN-based node classification via edge prediction.
Ranked #1 on
Node Classification
on Eximtradedata
1 code implementation • 11 Jun 2020 • Daheng Wang, Meng Jiang, Munira Syed, Oliver Conway, Vishal Juneja, Sriram Subramanian, Nitesh V. Chawla
The user embeddings preserve spatial patterns and temporal patterns of a variety of periodicity (e. g., hourly, weekly, and weekday patterns).
no code implementations • WS 2020 • Yang Zhou, Tong Zhao, Meng Jiang
Textual patterns (e. g., Country's president Person) are specified and/or generated for extracting factual information from unstructured data.
no code implementations • ACL 2020 • Wenhao Yu, Lingfei Wu, Qingkai Zeng, Shu Tao, Yu Deng, Meng Jiang
Existing methods learned semantic representations with dual encoders or dual variational auto-encoders.
no code implementations • NAACL 2021 • Chenguang Zhu, William Hinthorn, Ruochen Xu, Qingkai Zeng, Michael Zeng, Xuedong Huang, Meng Jiang
Automatic abstractive summaries are found to often distort or fabricate facts in the article.
no code implementations • 12 Mar 2020 • Mandana Saebi, Steven Krieg, Chuxu Zhang, Meng Jiang, Nitesh Chawla
Path-based relational reasoning over knowledge graphs has become increasingly popular due to a variety of downstream applications such as question answering in dialogue systems, fact prediction, and recommender systems.
1 code implementation • 28 Jan 2020 • Bo Ni, Zhichun Guo, Jianing Li, Meng Jiang
Recently, due to the booming influence of online social networks, detecting fake news is drawing significant attention from both academic communities and general public.
1 code implementation • 26 Nov 2019 • Chuxu Zhang, Huaxiu Yao, Chao Huang, Meng Jiang, Zhenhui Li, Nitesh V. Chawla
Knowledge graphs (KGs) serve as useful resources for various natural language processing applications.
no code implementations • WS 2019 • Qingkai Zeng, Mengxia Yu, Wenhao Yu, JinJun Xiong, Yiyu Shi, Meng Jiang
On a scientific concept hierarchy, a parent concept may have a few attributes, each of which has multiple values being a group of child concepts.
no code implementations • IJCNLP 2019 • Tianwen Jiang, Tong Zhao, Bing Qin, Ting Liu, Nitesh Chawla, Meng Jiang
In this work, we propose a new sequence labeling framework (as well as a new tag schema) to jointly extract the fact and condition tuples from statement sentences.
1 code implementation • 7 Oct 2019 • Huaxiu Yao, Chuxu Zhang, Ying WEI, Meng Jiang, Suhang Wang, Junzhou Huang, Nitesh V. Chawla, Zhenhui Li
Towards the challenging problem of semi-supervised node classification, there have been extensive studies.
no code implementations • 15 Sep 2019 • Tianchen Wang, JinJun Xiong, Xiaowei Xu, Meng Jiang, Yiyu Shi, Haiyun Yuan, Meiping Huang, Jian Zhuang
Cardiac magnetic resonance imaging (MRI) is an essential tool for MRI-guided surgery and real-time intervention.
no code implementations • 26 Jun 2019 • Tianwen Jiang, Tong Zhao, Bing Qin, Ting Liu, Nitesh V. Chawla, Meng Jiang
Conditions are essential in the statements of biological literature.
2 code implementations • 22 Dec 2018 • Chao Zhang, Fangbo Tao, Xiusi Chen, Jiaming Shen, Meng Jiang, Brian Sadler, Michelle Vanni, Jiawei Han
Our method, TaxoGen, uses term embeddings and hierarchical clustering to construct a topic taxonomy in a recursive fashion.
Databases
no code implementations • 26 Feb 2018 • Jinglan Liu, Jiaxin Zhang, Yukun Ding, Xiaowei Xu, Meng Jiang, Yiyu Shi
This work explores the binarization of the deconvolution-based generator in a GAN for memory saving and speedup of image construction.
no code implementations • 13 Mar 2017 • Meng Jiang, Jingbo Shang, Taylor Cassidy, Xiang Ren, Lance M. Kaplan, Timothy P. Hanratty, Jiawei Han
We propose an efficient framework, called MetaPAD, which discovers meta patterns from massive corpora with three techniques: (1) it develops a context-aware segmentation method to carefully determine the boundaries of patterns with a learnt pattern quality assessment function, which avoids costly dependency parsing and generates high-quality patterns; (2) it identifies and groups synonymous meta patterns from multiple facets---their types, contexts, and extractions; and (3) it examines type distributions of entities in the instances extracted by each group of patterns, and looks for appropriate type levels to make discovered patterns precise.
4 code implementations • 15 Feb 2017 • Jingbo Shang, Jialu Liu, Meng Jiang, Xiang Ren, Clare R. Voss, Jiawei Han
As one of the fundamental tasks in text analysis, phrase mining aims at extracting quality phrases from a text corpus.
no code implementations • 31 Oct 2016 • Jingbo Shang, Meng Jiang, Wenzhu Tong, Jinfeng Xiao, Jian Peng, Jiawei Han
In the literature, two series of models have been proposed to address prediction problems including classification and regression.