Aspect sentiment quad prediction (ASQP) is a critical subtask of aspect-level sentiment analysis. Current ASQP datasets are characterized by their small size and low quadruple density, which hinders technical development. To expand capacity, we construct two large Chinese ASQP datasets crawled from multiple online platforms. The datasets hold several significant characteristics: larger size (each with 10,000+ samples) and rich aspect categories, more words per sentence, and higher density than existing ASQP datasets. Moreover, we are the first to evaluate the performance of Generative Pre-trained Transformer (GPT) series models on ASQP and exhibit potential issues. The experiments with state-of-the-art ASQP baselines underscore the need to explore additional techniques to address ASQP, as well as the importance of further investigation into methods to improve the performance of GPTs.

Identifying suicidality including suicidal ideation, attempts, and risk factors in electronic health record data in clinical notes is difficult. A major difficulty is the lack of training samples given the small number of true positive instances among the increasingly large number of patients being screened. This paper describes a novel methodology that identifies suicidality in clinical notes by addressing this data sparsity issue through zero-shot learning. U.S. Veterans Affairs clinical notes served as data. The training dataset label was determined using diagnostic codes of suicide attempt and self-harm. A base string associated with the target label of suicidality was used to provide auxiliary information by narrowing the positive training cases to those containing the base string. A deep neural network was trained by mapping the training documents contents to a semantic space. For comparison, we trained another deep neural network using the identical training dataset labels and bag-of-words features. The zero shot learning model outperformed the baseline model in terms of AUC, sensitivity, specificity, and positive predictive value at multiple probability thresholds. In applying a 0.90 probability threshold, the methodology identified notes not associated with a relevant ICD 10 CM code that documented suicidality, with 94 percent accuracy. This new method can effectively identify suicidality without requiring manual annotation.

Purpose The purpose of this paper is to explore which structures of academic articles referees would pay more attention to, what specific content referees focus on, and whether the distribution of PRC is related to the citations. Design/methodology/approach Firstly, utilizing the feature words of section title and hierarchical attention network model (HAN) to identify the academic article structures. Secondly, analyzing the distribution of PRC in different structures according to the position information extracted by rules in PRC. Thirdly, analyzing the distribution of feature words of PRC extracted by the Chi-square test and TF-IDF in different structures. Finally, four correlation analysis methods are used to analyze whether the distribution of PRC in different structures is correlated to the citations. Findings The count of PRC distributed in Materials and Methods and Results section is significantly more than that in the structure of Introduction and Discussion, indicating that referees pay more attention to the Material and Methods and Results. The distribution of feature words of PRC in different structures is obviously different, which can reflect the content of referees' concern. There is no correlation between the distribution of PRC in different structures and the citations. Research limitations/implications Due to the differences in the way referees write peer review reports, the rules used to extract position information cannot cover all PRC. Originality/value The paper finds a pattern in the distribution of PRC in different academic article structures proving the long-term empirical understanding. It also provides insight into academic article writing: researchers should ensure the scientificity of methods and the reliability of results when writing academic article to obtain a high degree of recognition from referees.

Providing personalized explanations for recommendations can help users to understand the underlying insight of the recommendation results, which is helpful to the effectiveness, transparency, persuasiveness and trustworthiness of recommender systems. Current explainable recommendation models mostly generate textual explanations based on pre-defined sentence templates. However, the expressiveness power of template-based explanation sentences are limited to the pre-defined expressions, and manually defining the expressions require significant human efforts. Motivated by this problem, we propose to generate free-text natural language explanations for personalized recommendation. In particular, we propose a hierarchical sequence-to-sequence model (HSS) for personalized explanation generation. Different from conventional sentence generation in NLP research, a great challenge of explanation generation in e-commerce recommendation is that not all sentences in user reviews are of explanation purpose. To solve the problem, we further propose an auto-denoising mechanism based on topical item feature words for sentence generation. Experiments on various e-commerce product domains show that our approach can not only improve the recommendation accuracy, but also the explanation quality in terms of the offline measures and feature words coverage. This research is one of the initial steps to grant intelligent agents with the ability to explain itself based on natural language sentences.

We propose KDSL, a new word sense disambiguation (WSD) framework that utilizes knowledge to automatically generate sense-labeled data for supervised learning. First, from WordNet, we automatically construct a semantic knowledge base called DisDict, which provides refined feature words that highlight the differences among word senses, i.e., synsets. Second, we automatically generate new sense-labeled data by DisDict from unlabeled corpora. Third, these generated data, together with manually labeled data and unlabeled data, are fed to a neural framework conducting supervised and unsupervised learning jointly to model the semantic relations among synsets, feature words and their contexts. The experimental results show that KDSL outperforms several representative state-of-the-art methods on various major benchmarks. Interestingly, it performs relatively well even when manually labeled data is unavailable, thus provides a potential solution for similar tasks in a lack of manual annotations.

An intelligent system of the future should make its user feel comfortable, which is impossible without understanding context they coexist in. However, our past research did not treat language information as a part of the context a robot works in, and data about reasons why the user had made his decisions was not obtained. Therefore, we decided to utilize the Web as a knowledge source to discover context information that could suggest a robot's behavior when it acquires verbal information from its user or users. By comparing user utterances (blogs, Twitter or Facebook entries, not direct orders) with other people's written experiences (mostly blogs), a system can judge whether it is a situation in which the robot can perform or improve its performance. In this paper we introduce several methods that can be applied to a simple floor-cleaning robot. We describe basic experiments showing that text processing is helpful when dealing with multiple users who are not willing to give rich feedback. For example, we describe a method for finding usual reasons for cleaning on the Web by using Okapi BM25 to extract feature words from sentences retrieved by the query word "cleaning". Then, we introduce our ideas for dealing with conflicts of interest in multiuser environments and possible methods for avoiding such conflicts by achieving better situation understanding. Also, an emotion recognizer for guessing user needs and moods and a method to calculate situation naturalness are described.

Most information extraction research identifies the state of the world in text, including the entities and the relationships that exist between them. Much less attention has been paid to the understanding of dynamics, or how the state of the world changes over time. Because intelligent behavior seeks to change the state of the world in rational and utility-maximizing ways, common-sense knowledge about dynamics is essential for intelligent agents. In this paper, we describe a novel system, Prepost , that tackles the problem of extracting the preconditions and effects of actions and events, two important kinds of knowledge for connecting world state and the actions that affect it. In experiments on Web text, Prepost is able to improve by 79% over a baseline technique for identifying the effects of actions (64% improvement for preconditions).