Query auto-completion(QAC)facilitates query formulation by predicting completions for given query prefix inputs.Most web search engines use behavioral signals to customize query completion lists for users.To be effect...Query auto-completion(QAC)facilitates query formulation by predicting completions for given query prefix inputs.Most web search engines use behavioral signals to customize query completion lists for users.To be effective,such personalized QAC models rely on the access to suffcient context about each user’s interest and intentions.Hence,they often suffer from data sparseness problems.For this reason,we propose the construction and application of cohorts to address context sparsity and to enhance QAC personalization.We build an individual’s interest profile by learning his/her topic preferences through topic models and then aggregate users who share similar profiles.As conventional topic models are unable to automatically learn cohorts,we propose two cohort topic models that handle topic modeling and cohort discovery in the same framework.We present four cohortbased personalized QAC models that employ four different cohort discovery strategies.Our proposals use cohorts’contextual information together with query frequency to rank completions.We perform extensive experiments on the publicly available AOL query log and compare the ranking effectiveness with that of models that discard cohort contexts.Experimental results suggest that our cohort-based personalized QAC models can solve the sparseness problem and yield significant relevance improvement over competitive baselines.展开更多
BACKGROUND The impact of psychiatric disorder,especially depression,on the prognosis of sarcopenic patients is gaining prominence.Yet,there have been very few studies focusing on this issue,let alone the related targe...BACKGROUND The impact of psychiatric disorder,especially depression,on the prognosis of sarcopenic patients is gaining prominence.Yet,there have been very few studies focusing on this issue,let alone the related targeted mental health prevention.This cohort-based nested case-control study is geared to compare risk of depression and the depression-related ambulatory care utilization for sarcopenia persons with and without receiving add-on Chinese herbal medicines(CHMs)treatment.AIM To compare risk of depression and the depression-related ambulatory care utili-zation for sarcopenia persons with and without receiving add-on CHMs treat-ment.METHODS In the beginning,we recruited those aged 20-70 years with newly diagnosed sarcopenia and free of depression between 2002 and 2010 from a nationwide insurance database.From them,we identified cases with depression onset occurring after sarcopenia until December 31,2013.To cautiously isolate the effect of CHMs,we established the matched sets of treated and untreated subjects with CHMs use by randomly frequency matching.A conditional logistic regression was executed to explore the association of CHMs to depression risk,and the frequency and costs of depression-related ambulatory care were compared using Mann-Whitney U test.RESULTS Addition of CHMs to routine care of sarcopenia notably correlated with a lower risk of depression.A remarkable effect of CHMs in reducing depression was detected when sarcopenia subjects received CHMs for more than three years,lowering depression risk by as much as 65%.As compared to CHMs users,the non-CHMs users indeed incurred higher frequency and costs of depression-related ambulatory care after depression attack(P<0.05).Notably,the costs for per depression-related ambulatory care profoundly increased with the years after depression attack.CONCLUSION Sarcopenic patients can greatly benefit from add-on CHMs treatment,underscoring the urgent need for interdisciplinary collaboration and proactive treatment planning.展开更多
基金the National Natural Science Foundation of China(No.61702526)the Defense Industrial Technology Development Program of China(No.JCKY2017204B064)the National Advanced Research Project of China(No.6141B0801010b)。
文摘Query auto-completion(QAC)facilitates query formulation by predicting completions for given query prefix inputs.Most web search engines use behavioral signals to customize query completion lists for users.To be effective,such personalized QAC models rely on the access to suffcient context about each user’s interest and intentions.Hence,they often suffer from data sparseness problems.For this reason,we propose the construction and application of cohorts to address context sparsity and to enhance QAC personalization.We build an individual’s interest profile by learning his/her topic preferences through topic models and then aggregate users who share similar profiles.As conventional topic models are unable to automatically learn cohorts,we propose two cohort topic models that handle topic modeling and cohort discovery in the same framework.We present four cohortbased personalized QAC models that employ four different cohort discovery strategies.Our proposals use cohorts’contextual information together with query frequency to rank completions.We perform extensive experiments on the publicly available AOL query log and compare the ranking effectiveness with that of models that discard cohort contexts.Experimental results suggest that our cohort-based personalized QAC models can solve the sparseness problem and yield significant relevance improvement over competitive baselines.
文摘BACKGROUND The impact of psychiatric disorder,especially depression,on the prognosis of sarcopenic patients is gaining prominence.Yet,there have been very few studies focusing on this issue,let alone the related targeted mental health prevention.This cohort-based nested case-control study is geared to compare risk of depression and the depression-related ambulatory care utilization for sarcopenia persons with and without receiving add-on Chinese herbal medicines(CHMs)treatment.AIM To compare risk of depression and the depression-related ambulatory care utili-zation for sarcopenia persons with and without receiving add-on CHMs treat-ment.METHODS In the beginning,we recruited those aged 20-70 years with newly diagnosed sarcopenia and free of depression between 2002 and 2010 from a nationwide insurance database.From them,we identified cases with depression onset occurring after sarcopenia until December 31,2013.To cautiously isolate the effect of CHMs,we established the matched sets of treated and untreated subjects with CHMs use by randomly frequency matching.A conditional logistic regression was executed to explore the association of CHMs to depression risk,and the frequency and costs of depression-related ambulatory care were compared using Mann-Whitney U test.RESULTS Addition of CHMs to routine care of sarcopenia notably correlated with a lower risk of depression.A remarkable effect of CHMs in reducing depression was detected when sarcopenia subjects received CHMs for more than three years,lowering depression risk by as much as 65%.As compared to CHMs users,the non-CHMs users indeed incurred higher frequency and costs of depression-related ambulatory care after depression attack(P<0.05).Notably,the costs for per depression-related ambulatory care profoundly increased with the years after depression attack.CONCLUSION Sarcopenic patients can greatly benefit from add-on CHMs treatment,underscoring the urgent need for interdisciplinary collaboration and proactive treatment planning.
