Supplying data augmentation to conversational question answering (CQA) can effectively improve model performance. However, there is less improvement from single-turn datasets in CQA due to the distribution gap between single-turn and multi-turn datasets. On the other hand, while numerous single-turn datasets are available, we have not utilized them effectively. To solve this problem, we propose a novel method to convert single-turn datasets to multi-turn datasets. The proposed method consists of three parts, namely, a QA pair Generator, a QA pair Reassembler, and a question Rewriter. Given a sample consisting of context and single-turn QA pairs, the Generator obtains candidate QA pairs and a knowledge graph based on the context. The Reassembler utilizes the knowledge graph to get sequential QA pairs, and the Rewriter rewrites questions from a conversational perspective to obtain a multi-turn dataset S2M. Our experiments show that our method can synthesize effective training resources for CQA. Notably, S2M ranks 1st place on the QuAC leaderboard (https://quac.ai/) at the time of submission (Aug 24th, 2022).

Knowledge-grounded dialogue (KGD) has become increasingly essential for online services, enabling individuals to obtain desired information. While KGD contains knowledge information, most knowledge points are fragmented and repeated in dialogues, making it difficult for users to quickly grasp complete and key information from a collection of sessions. In this paper, we propose a novel task of dialogue-grounded knowledge points generation (DialKPG) to condense a collection of sessions on a topic into succinct and complete knowledge points. To enable empirical study, we create TopicDial and OpenDial corpus based on two existing knowledge-grounded dialogue corpus FaithDial and OpenDialKG by a Three-Stage Annotation Framework, and establish a novel approach for DialKPG task, namely MSAM (Multi-Level Salience-Aware Mixture). MSAM explicitly incorporates salient information at the token-level, utterance-level, and session-level to better guide knowledge points generation. Extensive experiments have verified the effectiveness of our method over competitive baselines. Furthermore, our analysis shows that the proposed model is particularly effective at handling long inputs and multiple sessions due to its strong capability of duplicated elimination and knowledge integration.

The online performance of customer service bots is often less than satisfactory because of the gap between limited training data and real-world user questions. As a straightforward way to improve online performance, model iteration and re-deployment are time consuming and labor-intensive, and therefore difficult to sustain. To fix badcases and improve online performance of chatbots in a timely and continuous manner, we propose a data-centric solution consisting of three main modules: badcase detection, bad case correction, and answer extraction. By making full use of online model signals, implicit user feedback and artificial customer service log, the proposed solution can fix online badcases automatically. Our solution has been deployed and bringing consistently positive impacts for hundreds of customer service bots used by Alipay app.

BACKGROUND: The identification of genes responsible for human inherited diseases is one of the most challenging tasks in human genetics. Recent studies based on phenotype similarity and gene proximity have demonstrated great success in prioritizing candidate genes for human diseases. However, most of these methods rely on a single protein-protein interaction (PPI) network to calculate similarities between genes, and thus greatly restrict the scope of application of such methods. Meanwhile, independently constructed and maintained PPI networks are usually quite diverse in coverage and quality, making the selection of a suitable PPI network inevitable but difficult. METHODS: We adopt a linear model to explain similarities between disease phenotypes using gene proximities that are quantified by diffusion kernels of one or more PPI networks. We solve this model via a Bayesian approach, and we derive an analytic form for Bayes factor that naturally measures the strength of association between a query disease and a candidate gene and thus can be used as a score to prioritize candidate genes. This method is intrinsically capable of integrating multiple PPI networks. RESULTS: We show that gene proximities calculated from PPI networks imply phenotype similarities. We demonstrate the effectiveness of the Bayesian regression approach on five PPI networks via large scale leave-one-out cross-validation experiments and summarize the results in terms of the mean rank ratio of known disease genes and the area under the receiver operating characteristic curve (AUC). We further show the capability of our approach in integrating multiple PPI networks. CONCLUSIONS: The Bayesian regression approach can achieve much higher performance than the existing CIPHER approach and the ordinary linear regression method. The integration of multiple PPI networks can greatly improve the scope of application of the proposed method in the inference of disease genes.