Open-Domain Targeted Sentiment Analysis via Span-Based Extraction and Classification
- Minghao Hu, Yuxing Peng, Zhen Huang, Dongsheng Li, Yiwei Lv
- Computer ScienceAnnual Meeting of the Association for…
- 1 June 2019
This work proposes a span-based extract-then-classify framework, where multiple opinion targets are directly extracted from the sentence under the supervision of target span boundaries, and corresponding polarities are then classified using their span representations.
Reinforced Mnemonic Reader for Machine Reading Comprehension
- Minghao Hu, Yuxing Peng, Zhen Huang, Xipeng Qiu, Furu Wei, M. Zhou
- Computer ScienceInternational Joint Conference on Artificial…
- 8 May 2017
The Reinforced Mnemonic Reader for machine reading comprehension tasks, which enhances previous attentive readers in two aspects: a reattention mechanism is proposed to refine current attentions by directly accessing to past attentions that are temporally memorized in a multi-round alignment architecture.
Read + Verify: Machine Reading Comprehension with Unanswerable Questions
- Minghao Hu, Furu Wei, Yuxing Peng, Zhen Huang, Nan Yang, Ming Zhou
- Computer ScienceAAAI Conference on Artificial Intelligence
- 17 August 2018
This work proposes a novel read-then-verify system, which not only utilizes a neural reader to extract candidate answers and produce no-answer probabilities, but also leverages an answer verifier to decide whether the predicted answer is entailed by the input snippets.
A Multi-Type Multi-Span Network for Reading Comprehension that Requires Discrete Reasoning
- Minghao Hu, Yuxing Peng, Zhen Huang, Dongsheng Li
- Computer ScienceConference on Empirical Methods in Natural…
- 1 August 2019
The Multi-Type Multi-Span Network (MTMSN) is introduced, a neural reading comprehension model that combines a multi-type answer predictor designed to support various answer types with amulti-span extraction method for dynamically producing one or multiple text spans.
Geometric Transformer for Fast and Robust Point Cloud Registration
- Zheng Qin, Hao Yu, Changjian Wang, Yulan Guo, Yuxing Peng, Kaiping Xu
- Computer ScienceComputer Vision and Pattern Recognition
- 14 February 2022
This work proposes Geometric Transformer, a simplistic design that attains surprisingly high matching accuracy such that no RANSAC is required in the estimation of alignment transformation, leading to 100 times acceleration.
Reinforced Mnemonic Reader for Machine Comprehension
- Minghao Hu, Yuxing Peng, Xipeng Qiu
- Computer Science
- 8 May 2017
The Reinforced Mnemonic Reader for machine comprehension (MC) task, which aims to answer a query about a given context document, is introduced and several novel mechanisms that address critical problems in MC that are not adequately solved by previous works are proposed.
Fd-Mobilenet: Improved Mobilenet with a Fast Downsampling Strategy
- Zheng Qin, Zhaoning Zhang, Xiaotao Chen, Yuxing Peng
- Computer ScienceInternational Conference on Information Photonics
- 11 February 2018
Fast-Downsampling MobileNet is presented, an efficient and accurate network for very limited computational budgets (e.g., 10–140 MFLOPs) that consistently outperforms MobileNet and achieves comparable results with ShufflieNet under different computational budgets.
ThunderNet: Towards Real-Time Generic Object Detection on Mobile Devices
- Zheng Qin, Zeming Li, Jian Sun
- Computer ScienceIEEE International Conference on Computer Vision
- 1 October 2019
benefit from the highly efficient backbone and detection part design, ThunderNet surpasses previous lightweight one-stage detectors with only 40% of the computational cost on PASCAL VOC and COCO benchmarks.
Attention-Guided Answer Distillation for Machine Reading Comprehension
- Minghao Hu, Yuxing Peng, M. Zhou
- Computer ScienceConference on Empirical Methods in Natural…
- 23 August 2018
This paper demonstrates that vanilla knowledge distillation applied to answer span prediction is effective for reading comprehension systems and proposes two novel approaches that not only penalize the prediction on confusing answers but also guide the training with alignment information distilled from the ensemble.
Retrieve, Read, Rerank: Towards End-to-End Multi-Document Reading Comprehension
- Minghao Hu, Yuxing Peng, Zhen Huang, Dongsheng Li
- Computer ScienceAnnual Meeting of the Association for…
- 11 June 2019
RE^3QA is presented, a unified question answering model that combines context retrieving, reading comprehension, and answer reranking to predict the final answer and outperforms the pipelined baseline and achieves state-of-the-art results on two versions of TriviaQA and two variants of SQuAD.
...
...