Visualizing attention zones in machine reading comprehension models.

The attention mechanism plays an important role in the machine reading comprehension (MRC) model. Here, we describe a pipeline for building an MRC model with a pretrained language model and visualizing the effect of each attention zone in different layers, which can indicate the explainability of the model. With the presented protocol and accompanying code, researchers can easily visualize the relevance of each attention zone in the MRC model. This approach can be generalized to other pretrained language models. For complete details on the use and execution of this protocol, please refer to Cui et al. (2022).

Multilingual multi-aspect explainability analyses on machine reading comprehension models.

Achieving human-level performance on some of the machine reading comprehension (MRC) datasets is no longer challenging with the help of powerful pre-trained language models (PLMs). However, the internal mechanism of these artifacts remains unclear, placing an obstacle to further understand these models. This paper focuses on conducting a series of analytical experiments to examine the relations between the multi-head self-attention and the final MRC system performance, revealing the potential explainability in PLM-based MRC models. To ensure the robustness of the analyses, we perform our experiments in a multilingual way on top of various PLMs. We discover that passage-to-question and passage understanding attentions are the most important ones in the question answering process, showing strong correlations to the final performance than other parts. Through comprehensive visualizations and case studies, we also observe several general findings on the attention maps, which can be helpful to understand how these models solve the questions.

Laminaria japonica polysaccharide prevents high-fat-diet-induced insulin resistance in mice via regulating gut microbiota.

Insulin resistance has become a worldwide nutrition and metabolic health problem due to the lack of effective protective agents. Laminaria japonica is a well-known marine vegetable. Purified Laminaria japonica polysaccharide (LJP61A) can inhibit atherosclerosis in high-fat-diet (HFD)-fed mice via ameliorating insulin resistance. In this study, we aimed to clarify the mechanism by which LJP61A ameliorates HFD-induced insulin resistance. The results indicated that HFD-induced insulin resistance, obesity, systematic inflammation, metabolic endotoxemia, and gut permeability in mice could be reduced by LJP61A. Gut microbiota analysis showed that the gut microbiota dysbiosis of HFD-fed mice, especially the reduction in mucin-degrading Akkermansia, could be reversed by LJP61A. Additionally, the reduction in mucin-producing goblet cells in HFD-fed mice could also be reversed by LJP61A. Moreover, insulin resistance, obesity, systematic inflammation, metabolic endotoxemia, and gut microbiota dysbiosis in HFD-fed mice could also be alleviated by faecal transplant from LJP61A-treated mice. Overall, LJP61A might be used as a prebiotic to ameliorate HFD-induced insulin resistance and associated metabolic disorders via regulating gut microbiota, especially Akkermansia.

Alleviating VLDL overproduction is an important mechanism for Laminaria japonica polysaccharide to inhibit atherosclerosis in LDLr-/- mice with diet-induced insulin resistance.

SCOPE: The overproduction of very low density lipoprotein (VLDL) is an important cause for initiation and development of atherosclerosis, which is highly associated with insulin signaling. The aim of this work is to verify whether the inhibition of VLDL overproduction is an underlying mechanism for a Laminaria japonica polysaccharide (LJP61A (where LJP is L. japonica)) to resist atherosclerosis. METHODS AND RESULTS: LJP61A (50 and 200 mg/kg/day) was orally administered to a high-fat diet (HFD)-fed LDL receptor deficient mice for 14 weeks. LJP61A significantly attenuated insulin resistance, hepatic steatosis, atherosclerosis, and dyslipidemia. Meanwhile, LJP61A ameliorated the HFD-induced impairment of hepatic insulin signaling and reduced VLDL overproduction via regulating the expression of genes involved in the assembly and secretion of VLDL. To study the possibility that the inhibition of mammalian target of rapamycin complex 1 and stimulation of Forkhead box protein O1 (Foxo1) nuclear exclusion is a result of LJP61A via regulating insulin signaling, LJP61A was administrated to HepG2 cells in the presence or absence of mTOR inhibitor and Foxo1 inhibitor. Results showed that LJP61A alleviated VLDL overproduction via regulating insulin receptor substrate mediated phosphatidylinositide 3-kinase AKT mammalian target of rapamycin complex 1 and phosphatidylinositide 3-kinase AKT-Foxo1 signaling pathways. CONCLUSION: These results suggested that LJP61A ameliorated HFD-induced insulin resistance to attenuate VLDL overproduction possibly via regulating insulin signaling, leading to the inhibition of atherosclerosis.

A new kinetic model of ultrasound-assisted extraction of polysaccharides from Chinese chive.

Chinese chive, a famous green vegetable, is widely cultivated in the Asia. In the present study, we found that ultrasound caused the degradation of Chinese chive polysaccharides (CCP) in the process of extraction. Since lacking the consideration of polysaccharide degradation, the traditional kinetic models can not reflect the real extraction process of CCP. Therefore, a modified kinetic model was thus established by introducing a parameter of degradation coefficient based on the Fick's second law, suggesting the diffusion and degradation of CCP is highly dependent on the ultrasonic power, extraction temperature and solid-liquid ratio. According to this modified model, the maximum CCP yield was obtained under an optimal extraction condition including extraction temperature 37°C, ultrasonic power 458 w, extraction time 30min and solid-liquid ratio 1:32. The objective polysaccharides responding to ultrasound were shown to be four different fractions, contributing to the increased diffusion and degradation of CCP by ultrasound treatment.

Question popularity analysis and prediction in community question answering services.

With the blooming of online social media applications, Community Question Answering (CQA) services have become one of the most important online resources for information and knowledge seekers. A large number of high quality question and answer pairs have been accumulated, which allow users to not only share their knowledge with others, but also interact with each other. Accordingly, volumes of efforts have been taken to explore the questions and answers retrieval in CQA services so as to help users to finding the similar questions or the right answers. However, to our knowledge, less attention has been paid so far to question popularity in CQA. Question popularity can reflect the attention and interest of users. Hence, predicting question popularity can better capture the users' interest so as to improve the users' experience. Meanwhile, it can also promote the development of the community. In this paper, we investigate the problem of predicting question popularity in CQA. We first explore the factors that have impact on question popularity by employing statistical analysis. We then propose a supervised machine learning approach to model these factors for question popularity prediction. The experimental results show that our proposed approach can effectively distinguish the popular questions from unpopular ones in the Yahoo! Answers question and answer repository.

A topic clustering approach to finding similar questions from large question and answer archives.

With the blooming of Web 2.0, Community Question Answering (CQA) services such as Yahoo! Answers (http://answers.yahoo.com), WikiAnswer (http://wiki.answers.com), and Baidu Zhidao (http://zhidao.baidu.com), etc., have emerged as alternatives for knowledge and information acquisition. Over time, a large number of question and answer (Q&A) pairs with high quality devoted by human intelligence have been accumulated as a comprehensive knowledge base. Unlike the search engines, which return long lists of results, searching in the CQA services can obtain the correct answers to the question queries by automatically finding similar questions that have already been answered by other users. Hence, it greatly improves the efficiency of the online information retrieval. However, given a question query, finding the similar and well-answered questions is a non-trivial task. The main challenge is the word mismatch between question query (query) and candidate question for retrieval (question). To investigate this problem, in this study, we capture the word semantic similarity between query and question by introducing the topic modeling approach. We then propose an unsupervised machine-learning approach to finding similar questions on CQA Q&A archives. The experimental results show that our proposed approach significantly outperforms the state-of-the-art methods.

Phrasal Paraphrase Based Question Reformulation for Archived Question Retrieval.

Lexical gap in cQA search, resulted by the variability of languages, has been recognized as an important and widespread phenomenon. To address the problem, this paper presents a question reformulation scheme to enhance the question retrieval model by fully exploring the intelligence of paraphrase in phrase-level. It compensates for the existing paraphrasing research in a suitable granularity, which either falls into fine-grained lexical-level or coarse-grained sentence-level. Given a question in natural language, our scheme first detects the involved key-phrases by jointly integrating the corpus-dependent knowledge and question-aware cues. Next, it automatically extracts the paraphrases for each identified key-phrase utilizing multiple online translation engines, and then selects the most relevant reformulations from a large group of question rewrites, which is formed by full permutation and combination of the generated paraphrases. Extensive evaluations on a real world data set demonstrate that our model is able to characterize the complex questions and achieves promising performance as compared to the state-of-the-art methods.

Correction: Phrasal Paraphrase Based Question Reformulation for Archived Question Retrieval.

[This corrects the article DOI: 10.1371/journal.pone.0064601.].

[A comparative research on quality of Vitmin C Yinqiao tablets from different manufacturers].

OBJECTIVE: To study the different manufacturers Vitmin C (Vc) Yinqiao tablets, and the quality of the analysis of the problem, to provide a theoretical basis for the correct evaluation of the quality of medicines and improving the standard drugs. METHOD: 11 manufacturers of 18 batches of samples for determination of the weight of the core tablets, powder samples were observed with microscope, determination of Vc, and the establishment of the Vc Yinqiao tablets HPLC method for determination of chlorogenic acid and arctigenin, chlorogenic acid and arctigenin in the samples were measured and compared. RESULT: There is a big difference of microscope and various measured results in different manufacturers products. CONCLUSION: Because different manufacturers to produce the same, there are big differences in the quality of the products.