HJHeng Ji

Heng Ji

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

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Heng Ji has a total of 105 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    A Large-Scale Study of Reranker Relevance Feedback at Inference

    by Revanth Gangi Reddy, Pradeep Dasigi, Arafat Sultan, Arman Cohan, Avirup Sil, Heng Ji, Hannaneh Hajishirzi


  • Open Access

    Making Pre-trained Language Models both Task-solvers and Self-calibrators

    by Yangyi Chen, Xingyao Wang, Heng Ji

    Yangyi Chen, Xingyao Wang, Heng Ji. Findings of the Association for Computational Linguistics: ACL 2023. 2023.

  • Modulation Recognition Based on Lightweight Residual Network via Binary Quantization

    by Heng Ji, Wangyang Xu, Lu Gan, Zhengwu Xu

    Signal modulation recognition is an important and complicated problem in spectrum monitoring. In recent years, many advanced deep learning methods have been proposed for this problem. However, the high computational cost of deep neural networks largely hinders practical deployment. In this paper, we consider the signal modulation recognition problem via the deep residual network and propose a binary quantization scheme to reduce the model size and memory cost. This is achieved by simultaneously increasing shortcuts and maintaining full-precision weights and outputs of key layers in binary residual network in a simple way. The results show that with competitive accuracy, 95% of multiply–accumulate operations of model are converted into binary operations under 0 dB snr. In summary, the proposed method can effectively reduce the parameters and complexity of recognition model.


  • 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.


  • Open Access

    HySPA: Hybrid Span Generation for Scalable Text-to-Graph Extraction

    by Liliang Ren, Chenkai Sun, Heng Ji, Julia Hockenmaier

    Liliang Ren, Chenkai Sun, Heng Ji, Julia Hockenmaier. Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021. 2021.


  • Expertise-Aware Truth Analysis and Task Allocation in Mobile Crowdsourcing

    by Xiaomei Zhang, Yibo Wu, Lifu Huang, Heng Ji, Guohong Cao

    In mobile crowdsourcing, the accuracy of the collected data is usually hard to ensure. Researchers have proposed techniques to identify truth from noisy data by inferring and utilizing the reliability of mobile users, and allocate tasks to users with higher reliability. However, they neglect the fact that a user may only have expertise on some problems (in some domains), but not others, and hence causing two problems: low estimation accuracy in truth analysis and ineffective task allocation. To address these problems, we propose Expertise-aware Truth Analysis and Task Allocation (ETA2), which can effectively infer user expertise, and then estimate truth and allocate tasks based on the inferred expertise. ETA2 relies on a novel semantic analysis method to identify the expertise, and an expertise-aware truth analysis method to find the truth. For expertise-aware task allocation in ETA2, we formalize and solve two problems based on the optimization objectives: max-quality task allocation which maximizes the probability for tasks to be allocated to users with high expertise and min-cost task allocation which minimizes the cost of task allocation while ensuring high-quality data are collected. Experimental results based on two real-world datasets and one synthetic dataset demonstrate that ETA2 significantly outperforms existing solutions.


  • Open Access

    Joint Entity and Event Extraction with Generative Adversarial Imitation Learning

    by Tongtao Zhang, Heng Ji, Avirup Sil

    We propose a new framework for entity and event extraction based on generative adversarial imitation learning—an inverse reinforcement learning method using a generative adversarial network (GAN). We assume that instances and labels yield to various extents of difficulty and the gains and penalties (rewards) are expected to be diverse. We utilize discriminators to estimate proper rewards according to the difference between the labels committed by the ground-truth (expert) and the extractor (agent). Our experiments demonstrate that the proposed framework outperforms state-of-the-art methods.


  • Open Access

    A Grounded Unsupervised Universal Part-of-Speech Tagger for Low-Resource Languages

    by Ronald Cardenas, Ying Lin, Heng Ji, Jonathan May

    Unsupervised part of speech (POS) tagging is often framed as a clustering problem, but practical taggers need to \textit{ground} their clusters as well. Grounding generally requires reference labeled data, a luxury a low-resource language might not have. In this work, we describe an approach for low-resource unsupervised POS tagging that yields fully grounded output and requires no labeled training data. We find the classic method of Brown et al. (1992) clusters well in our use case and employ a decipherment-based approach to grounding. This approach presumes a sequence of cluster IDs is a `ciphertext' and seeks a POS tag-to-cluster ID mapping that will reveal the POS sequence. We show intrinsically that, despite the difficulty of the task, we obtain reasonable performance across a variety of languages. We also show extrinsically that incorporating our POS tagger into a name tagger leads to state-of-the-art tagging performance in Sinhalese and Kinyarwanda, two languages with nearly no labeled POS data available. We further demonstrate our tagger's utility by incorporating it into a true `zero-resource' variant of the Malopa (Ammar et al., 2016) dependency parser model that removes the current reliance on multilingual resources and gold POS tags for new languages. Experiments show that including our tagger makes up much of the accuracy lost when gold POS tags are unavailable.

  • Open Access

    Describing a Knowledge Base

    by Qingyun Wang, Xiaoman Pan, Lifu Huang, Boliang Zhang, Zhiying Jiang, Heng Ji, Kevin Knight

    We aim to automatically generate natural language descriptions about an input structured knowledge base (KB). We build our generation framework based on a pointer network which can copy facts from the input KB, and add two attention mechanisms: (i) slot-aware attention to capture the association between a slot type and its corresponding slot value; and (ii) a new \emph{table position self-attention} to capture the inter-dependencies among related slots. For evaluation, besides standard metrics including BLEU, METEOR, and ROUGE, we propose a KB reconstruction based metric by extracting a KB from the generation output and comparing it with the input KB. We also create a new data set which includes 106,216 pairs of structured KBs and their corresponding natural language descriptions for two distinct entity types. Experiments show that our approach significantly outperforms state-of-the-art methods. The reconstructed KB achieves 68.8% - 72.6% F-score.

  • Open Access

    Paper Abstract Writing through Editing Mechanism

    by Qingyun Wang, Zhihao Zhou, Lifu Huang, Spencer Whitehead, Boliang Zhang, Heng Ji, Kevin Knight

    We present a paper abstract writing system based on an attentive neural sequence-to-sequence model that can take a title as input and automatically generate an abstract. We design a novel Writing-editing Network that can attend to both the title and the previously generated abstract drafts and then iteratively revise and polish the abstract. With two series of Turing tests, where the human judges are asked to distinguish the system-generated abstracts from human-written ones, our system passes Turing tests by junior domain experts at a rate up to 30% and by non-expert at a rate up to 80%.