Large Language Model (LLM)-based Task-Oriented Dialogue (TOD) systems show promising performance in helping users achieve specific goals in a zero-shot setting. However, existing systems engage with users in a reactive manner, relying on a basic single-query mechanism with the knowledge base and employing passive policy planning. The proactive TOD systems, which can provide potentially helpful information and plan cross-domain multi-task dialogue policies, have not been well studied. In addition, effective evaluation methods are also lacking. To address these issues, we propose ProTOD, a novel LLM-based proactive TOD framework designed to improve system proactivity and goal completion. First, we design an adaptive exploratory retrieval mechanism to dynamically navigate domain knowledge. Second, we introduce a two-stage passive-to-proactive policy planner that effectively organizes knowledge and actions relationship. Finally, we develop two distinct user simulators with different personalities to simulate real-world interactions and propose a new error measure called Human-targeted Policy Edit Rate (HPER) for evaluation. Experimental results show that ProTOD achieves state-of-the-art (SOTA) performance, improving goal completion rates by 10% while significantly enhancing the proactive engagement.

Knowledge base (KB) embeddings have been shown to contain gender biases (Fisher et al., 2020b).In this paper, we study two questions regarding these biases: how to quantify them, and how to trace their origins in KB? Specifically, first, we develop two novel bias measures respectively for a group of person entities and an individual person entity.Evidence of their validity is observed by comparison with real-world census data.Second, we use influence function to inspect the contribution of each triple in KB to the overall group bias.To exemplify the potential applications of our study, we also present two strategies (by adding and removing KB triples) to mitigate gender biases in KB embeddings.

Medical Named Entity Recognition (NER) is a fundamental but challenging task due to the lack of specialized entity datasets like tumor entities, which are often overlapped and discontinuous. In this paper, we propose a novel Prompt Enhanced Generative Machine Reading Comprehension Framework (PGMRC) to improve the overlapped and discontinuous NER performance. Specifically, we formulate NER as a Machine Reading Comprehension (MRC) task and employ a pre-trained encoder-decoder module to generate entity span sequences according to their entity query. In this way, we adopt query to guide the model to focus on answer entities in context, which can naturally solve entity overlap and alleviate the exposure bias of the generative model. Then, we introduce continuous prompts to the self-attention mechanism in Transformer to reduce the dependence on manually constructed queries. In addition, we annotate 875 pathological documents of pancreatic cancer and construct a Chinese pathological NER dataset (PAN) containing overlapped and discontinuous entities. Finally, we conduct our experiments on three widely used benchmarks (GENIA, ACE04, ACE05) and our dataset PAN. Experiments have demonstrated its effectiveness and better performance than state-of-the-art methods.

Dialogue state tracker is responsible for inferring user intentions through dialogue history.Previous methods have difficulties in handling dialogues with long interaction context, due to the excessive information.We propose a Dialogue State Tracker with Slot Attention and Slot Information Sharing (SAS) to reduce redundant information's interference and improve long dialogue context tracking.Specially, we first apply a Slot Attention to learn a set of slot-specific features from the original dialogue and then integrate them using a Slot Information Sharing.The sharing improve the models ability to deduce value from related slots.Our model yields a significantly improved performance compared to previous state-of-the-art models on the Multi-WOZ dataset.

Knowledge graphs have been used in a wide range of applications to support search, recommendation, and question answering (Q&A). For example, in Q&A systems, given a new question, we may use a knowledge graph to automatically identify the most suitable answers based on similarity evaluation. However, such systems may suffer from two major limitations. First, the knowledge graph constructed based on source data may contain errors. Second, the knowledge graph may become out of date and cannot quickly adapt to new knowledge. To address these issues, in this paper, we propose an interactive framework that refines and optimizes knowledge graphs through user votes. We develop an efficient similarity evaluation notion, called extended inverse P-distance, based on which the graph optimization problem can be formulated as a signomial geometric programming problem. We then propose a basic single-vote solution and a more advanced multi-vote solution for graph optimization. We also propose a split-and-merge optimization strategy to scale up the multi-vote solution. Extensive experiments based on real-life and synthetic graphs demonstrate the effectiveness and efficiency of our proposed framework.

A more intelligent chatbot should be able to express emotion, in addition to providing informative responses. Despite much works in designing neural dialogue generation systems in recent years, few studies consider both emotion to be expressed and topic relevance in the generation process. To address this problem, we present a Topic-aware Emotional Response Generation (TERG) model, which can not only exactly generate desired emotional response but perform well in topic relevance. Specifically, TERG equips an encoder-decoder structure with an emotion aware module to control the emotional sentence generation and a topic aware module to enhance topic relevance. We evaluate our model on a large real-world dataset of conversations from social media. Experimental results show that our model obtains a significant improvement against several strong baseline methods on both automatic and human evaluation.

In relation extraction tasks, distant supervision methods expand dataset by aligning entity pairs in different knowledge bases and completing the relations between two entities. However, these methods ignore the fact that sentences labels generated by distant supervision methods with high confidence are often incorrect in the real world called Unknown Unknowns (UUs). To deal with this challenge, we propose a crowdsourcing based human-in-the-loop denoising framework which iteratively discovers UUs and corrects them by crowdsourcing to better extract relations. During each epoch of iterations, we choose one sentence bag and repeat two steps: Firstly, attention based Long Short-Term Memory network is applied as a selector to discover potential UUs. Secondly, these UUs are annotated by crowdsourcing with two answer collecting strategies and fed back into selector as positive samples. Until the accuracy of selector reaches a threshold, all annotated samples are added into relation classifier as cleaned train set and framework moves on to next epoch with new sentence bags. The experiments on the New York Times dataset and analysis of potential UUs demonstrate that our framework denoise the dataset and outperforms all the baselines on distant supervision relation extraction tasks.

Electronic Medical Records (EMRs) are the digital equivalent of paper records, which include treatment and medical history about a patient. At present, the main research goal of Chinese EMRS is to accurately recognize the body parts, drugs, illnesses and other information in the Chinese medical process. Implementing EMRs can boost both the quality and safety of patient care. In Chinese EMRs, how to accurately recognize named entities is important because it is useful to predict the disease risk, therapeutic method and recovery probability. This paper proposes a novel deep learning framework, which uses character-word joint embedding and combines different feature information based on the dictionary. Compared with the predecessors, we incorporate word-level information based on the basic Bi-LSTM model. In addition, we propose an improved n-gram feature encoding method and compare it with PDET feature and PIET feature. Our experimental results demonstrate that our proposed model performs the best in predicting named entities in Chinese EMRs.

Natural language inference (NLI) has received widespread attention in recent years due to its contribution to various natural language processing tasks, such as question answering, abstract text summarization, and video caption. Most existing works focus on modeling the sentence interaction information, while the use of commonsense knowledge is not well studied for NLI. In this paper, we propose knowledge adaptive neural network (KANN) that adaptively incorporates commonsense knowledge at sentence encoding and inference stages. We first perform knowledge collection and representation to identify the relevant knowledge. Then we use a knowledge absorption gate to embed knowledge into neural network models. Experiments on two benchmark datasets, namely SNLI and MultiNLI for natural language inference, show the advantages of our proposed model. Furthermore, our model is comparable to if not better than the recent neural network based approaches on NLI.

In recommender systems, the essential task is to predict the personalized rating of a user to a new item. To address this task, recommender systems usually employ matrix factorization model to predict ratings over a user-item rating matrix. However, this model severely suffers from the problem of data sparsity. Noting the large amount of user reviews available in the Internet, we exploit user preferences and item attributes contained in reviews to alleviate the problem. Specifically, we propose a Neural Profile-Aware Matrix Factorization model, namely NPMF, which incorporates the user and item profiles modeled with neural networks for rating prediction. We evaluate the performance of NPMF using three large-scale real-world datasets released in Yelp. The experimental results show that NPMF outperforms other mainstream rating prediction techniques and indeed alleviates the data sparsity problem.

Services provided by mobile devices in the pervasive computing environment handle increasingly critical data and computation. But there is no dynamic and systematic way to evaluate which of the services can be entrusted. This paper proposes a dynamic trust evaluation algorithm to solve the service trust problem. The contribution of this paper is that a systematic and computational evaluation mechanism in such a service-oriented open environment is presented. Firstly, the optimized Subjective Logic is defined which is the basis of this paper. Then, how to update trust value dynamically including individual and composite services on a continuous basis is discussed. Finally, the algorithm is validated by simulation experiments.