Skip to search formSkip to main contentSkip to account menu

Open-Domain Targeted Sentiment Analysis via Span-Based Extraction and Classification

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.
View on ACL (opens in a new tab)

Reinforced Mnemonic Reader for Machine Reading Comprehension

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.
View via Publisher (opens in a new tab)

Read + Verify: Machine Reading Comprehension with Unanswerable Questions

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.
View PDF on arXiv (opens in a new tab)

A Multi-Type Multi-Span Network for Reading Comprehension that Requires Discrete Reasoning

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.
View on ACL (opens in a new tab)

Geometric Transformer for Fast and Robust Point Cloud Registration

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.
View on IEEE (opens in a new tab)

Reinforced Mnemonic Reader for Machine Comprehension

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.
View PDF on arXiv (opens in a new tab)

Fd-Mobilenet: Improved Mobilenet with a Fast Downsampling Strategy

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.
View on IEEE (opens in a new tab)

ThunderNet: Towards Real-Time Generic Object Detection on Mobile Devices

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.
View on IEEE (opens in a new tab)

Attention-Guided Answer Distillation for Machine Reading Comprehension

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.
View on ACL (opens in a new tab)

Retrieve, Read, Rerank: Towards End-to-End Multi-Document Reading Comprehension

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.
View on ACL (opens in a new tab)
By clicking accept or continuing to use the site, you agree to the terms outlined in our Privacy Policy (opens in a new tab), Terms of Service (opens in a new tab), and Dataset License (opens in a new tab)