• Publications
  • Influence
Open-Domain Targeted Sentiment Analysis via Span-Based Extraction and Classification
TLDR
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
TLDR
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
TLDR
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.
Reinforced Mnemonic Reader for Machine Comprehension
TLDR
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.
A Multi-Type Multi-Span Network for Reading Comprehension that Requires Discrete Reasoning
TLDR
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.
Fd-Mobilenet: Improved Mobilenet with a Fast Downsampling Strategy
TLDR
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.
Attention-Guided Answer Distillation for Machine Reading Comprehension
TLDR
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.
Mnemonic Reader for Machine Comprehension
TLDR
The Mnemonic Reader is introduced for machine comprehension tasks, which uses a self-alignment attention to model the long-distance dependency among context words, and obtains query-aware and selfaware contextual representation for each word in the context.
ThunderNet: Towards Real-Time Generic Object Detection on Mobile Devices
TLDR
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.
Retrieve, Read, Rerank: Towards End-to-End Multi-Document Reading Comprehension
TLDR
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.
...
...