Leveraging hierarchical semantic‐emotional memory in emotional conversation generation

Handling emotions in human‐computer dialogues has emerged as a challenging task which requires artificial intelligence systems to generate emotional responses by jointly perceiving the emotion involved in the input posts and incorporating it into the gener-ation of semantically coherent and emotionally reasonable responses.However,most previous works generate emotional responses solely from input posts,which do not take full advantage of the training corpus and suffer from generating generic responses.In this study,we introduce a hierarchical semantic‐emotional memory module for emotional conversation generation(called HSEMEC),which can learn abstract semantic conver-sation patterns and emotional information from the large training corpus.The learnt semantic and emotional knowledge helps to enrich the post representation and assist the emotional conversation generation.Comprehensive experiments on a large real‐world conversation corpus show that HSEMEC can outperform the strong baselines on both automatic and manual evaluation.For reproducibility,we release the code and data publicly at:https://github.com/siat‐nlp/HSEMEC‐code‐data.

Incorporating multi-kernel function and Internet verification for Chinese person name disambiguation

The study on person name disambiguation aims to identify different entities with the same person name through document linking to different entities. The traditional disambiguation approach makes use of words in documents as features to distinguish different entities. Due to the lack of use of word order as a feature and the limited use of external knowledge, the traditional approach has performance limitations. This paper presents an approach for named entity disambiguation through entity linking based on a multi- kernel function and Internet verification to improve Chinese person name disambiguation. The proposed approach extends a linear kernel that uses in-document word features by adding a string kernel to construct a multi-kernel function. This multi-kernel can then calculate the similarities between an input document and the entity descriptions in a named per- son knowledge base to form a ranked list of candidates to different entities. Furthermore, Internet search results based on keywords extracted from the input document and entity descriptions in the knowledge base are used to train classifiers for verification. The evaluations on CIPS-SIGHAN 2012 person name disambiguation bakeoff dataset show that the use of word orders and Internet knowledge through a multi-kernel function can improve both precision and recall and our system has achieved state-of-the-art performance.

An Ensemble Approach for Emotion Cause Detection with Event Extraction and Multi-Kernel SVMs

In this paper, we present a new challenging task for emotion analysis, namely emotion cause extraction.In this task, we focus on the detection of emotion cause a.k.a the reason or the stimulant of an emotion, rather than the regular emotion classification or emotion component extraction. Since there is no open dataset for this task available, we first designed and annotated an emotion cause dataset which follows the scheme of W3 C Emotion Markup Language. We then present an emotion cause detection method by using event extraction framework,where a tree structure-based representation method is used to represent the events. Since the distribution of events is imbalanced in the training data, we propose an under-sampling-based bagging algorithm to solve this problem. Even with a limited training set, the proposed approach may still extract sufficient features for analysis by a bagging of multi-kernel based SVMs method. Evaluations show that our approach achieves an F-measure 7.04%higher than the state-of-the-art methods.

Insulin-resistance and depression cohort data mining to identify nutraceutical related DNA methylation biomarker for type 2 diabetes

Insulin-resistance(IR)is one of the most important precursors of type 2 diabetes(T2D).Recent evidence suggests an association of depression with the onset of T2D.Accumu-lating evidence shows that depression and T2D share common biological origins,and DNA methylation examination might reveal the link between lifestyle,disease risk,and potential therapeutic targets for T2D.Here we hypothesize that integrative mining of IR and depression cohort data will facilitate predictive biomarkers identification for T2D.We utilized a newly proposed method to extract gene-level information from probe level data on genome-wide DNA methylation array.We identified a set of genes associated with IR and depression in clin-ical cohorts.By overlapping the IR-related nutraceutical-gene network with depression net-works,we identified a common subnetwork centered with Vitamin D Receptor(VDR)gene.Preliminary clinical validation of gene methylation set in a small cohort of T2D patients and controls was established using the Sequenome matrix-assisted laser desorption ionization-time flight mass spectrometry.A set of sites in the promoter regions of VDR showed a signifi-cant difference between T2D patients and controls.Using a logistic regression model,the optimal prediction performance of these sites was AUC Z 0.902,and an odds ratio Z 19.76.Thus,monitoring the methylation status of specific VDR promoter region might help stratify the high-risk individuals who could potentially benefit from vitamin D dietary sup-plementation.Our results highlight the link between IR and depression,and the DNA methyl-ation analysis might facilitate the search for their shared mechanisms in the etiology of T2D.