MGRC: An End-to-End Multigranularity Reading Comprehension Model for Question Answering.

Deep neural network-based models have achieved great success in extractive question answering. Recently, many works have been proposed to model multistage matching for this task, which usually first retrieve relevant paragraphs or sentences and then extract an answer span from the retrieved results. However, such a pipeline-based approach suffers from the error propagation problem, especially for sentence-level retrieval that is usually difficult to achieve high accuracy due to the severe data imbalance problem. Furthermore, since the paragraph/sentence selector and the answer extractor are closely related, modeling them independently does not fully exploit the power of multistage matching. To solve these problems, we propose a novel end-to-end multigranularity reading comprehension model, which is a unified framework to explicitly model three matching granularities, including paragraph identification, sentence selection, and answer extraction. Our approach has two main advantages. First, the end-to-end approach alleviates the error propagation problem in both the training and inference phases. Second, the shared features in a unified model improve the learning of representations of different matching granularities. We conduct a comprehensive comparison on four large-scale datasets (SQuAD-open, NewsQA, SQuAD 2.0, and SQuAD Adversarial) and verify that the proposed approach outperforms both the vanilla BERT model and existing multistage matching approaches. We also conduct an ablation study and verify the effectiveness of the proposed components in our model structure.

Disentangled Retrieval and Reasoning for Implicit Question Answering.

To date, most of the existing open-domain question answering (QA) methods focus on explicit questions where the reasoning steps are mentioned explicitly in the question. In this article, we study implicit QA where the reasoning steps are not evident in the question. Implicit QA is challenging in two aspects. First, evidence retrieval is difficult since there is little overlap between a question and its required evidence. Second, answer inference is difficult since the reasoning strategy is latent in the question. To tackle implicit QA, we propose a systematic solution denoted as DisentangledQA, which disentangles topic, attribute, and reasoning strategy from the implicit question to guide the retrieval and reasoning. Specifically, we disentangle the topic and attribute information from the implicit question to guide evidence retrieval. For answer reasoning, we propose a disentangled reasoning model for answer prediction based on retrieved evidence as well as the latent representation of the reasoning strategy. The disentangled framework empowers each module to focus on a specific latent element in the question, and thus, leads to effective representation learning for them. Experiments on the StrategyQA dataset demonstrate the effectiveness of our method in answering implicit questions, improving performance in evidence retrieval and answering inference by 31.7% and 4.5%, respectively, and achieving the best performance on the official leaderboard. In addition, our method achieved the best performance on the challenging EntityQuestions dataset, indicating the effectiveness in improving general open-domain QA tasks.

Amplification-free library preparation with SAFE Hi-C uses ligation products for deep sequencing to improve traditional Hi-C analysis.

PCR amplification of Hi-C libraries introduces unusable duplicates and results in a biased representation of chromatin interactions. We present a simplified, fast, and economically efficient Hi-C library preparation procedure, SAFE Hi-C, which generates sufficient non-amplified ligation products for deep sequencing from 30 million Drosophila cells. Comprehensive analysis of the resulting data shows that amplification-free Hi-C preserves higher complexity of chromatin interaction and lowers sequencing depth for the same number of unique paired reads. For human cells which have a large genome, SAFE Hi-C recovers enough ligated fragments for direct high-throughput sequencing without amplification from as few as 250,000 cells. Comparison with published in situ Hi-C data from millions of human cells demonstrates that amplification introduces distance-dependent amplification bias, which results in an increased background noise level against genomic distance. With amplification bias avoided, SAFE Hi-C may produce a chromatin interaction network more faithfully reflecting the real three-dimensional genomic architecture.