Dialogue state tracking (DST) is a component of the task-oriented dialogue system. It is responsible for extracting and managing slot values according to dialogue utterances, where each slot represents an essential part of the information to accomplish a task, and slot value is updated recurrently in each dialogue turn. However, many DST models cannot update slot values appropriately. These models may repeatedly inherit wrong slot values extracted in previous turns, resulting in the fail of the entire DST task.They cannot update indirectly mentioned slots well, either. This study designed a model with a mentioned slot pool (MSP) to tackle the update problem. The MSP is a slot-specific memory that records all mentioned slot values that may be inherited, and our model updates slot values according to the MSP and the dialogue context. Our model rejects inheriting the previous slot value when it predicates the value is wrong. Then, it re-extracts the slot value from the current dialogue context. As the contextual information accumulates with the dialogue progress, the new value is more likely to be correct. It also can track the indirectly mentioned slot by picking a value from the MSP. Experimental results showed our model reached state-of-the-art DST performance on MultiWOZ 2.1 and 2.2 datasets.

Aspect-based sentiment analysis (ABSA) typically requires in-domain annotated data for supervised training/fine-tuning. It is a big challenge to scale ABSA to a large number of new domains. This paper aims to train a unified model that can perform zero-shot ABSA without using any annotated data for a new domain. We propose a method called contrastive post-training on review Natural Language Inference (CORN). Later ABSA tasks can be cast into NLI for zero-shot transfer. We evaluate CORN on ABSA tasks, ranging from aspect extraction (AE), aspect sentiment classification (ASC), to end-to-end aspect-based sentiment analysis (E2E ABSA), which show ABSA can be conducted without any human annotated ABSA data.

Dialogue understanding has always been a bottleneck for many conversational tasks, such as dialogue response generation and conversational question answering. To expedite the progress in this area, we introduce the task of conversational aspect sentiment analysis (CASA) that can provide useful fine-grained sentiment information for dialogue understanding and planning. Overall, this task extends the standard aspect-based sentiment analysis to the conversational scenario with several major adaptations. To aid the training and evaluation of data-driven methods, we annotate 3,000 chit-chat dialogues (27,198 sentences) with fine-grained sentiment information, including all sentiment expressions, their polarities and the corresponding target mentions. We also annotate an out-of-domain test set of 200 dialogues for robustness evaluation. Besides, we develop multiple baselines based on either pretrained BERT or self-attention for preliminary study. Experimental results show that our BERT-based model has strong performances for both in-domain and out-of-domain datasets, and thorough analysis indicates several potential directions for further improvements.

This paper focusses on the main issues related to the development of a corpus for opinion and sentiment analysis, with a special attention to irony, and presents as a case study Senti-TUT, a project for Italian aimed at investigating sentiment and irony in social media. We present the Senti-TUT corpus, a collection of texts from Twitter annotated with sentiment polarity. We describe the dataset, the annotation, the methodologies applied and our investigations on two important features of irony: polarity reversing and emotion expressions.

Topic modeling has been widely used in text mining. Previous topic models such as Latent Dirichlet Allocation (LDA) are successful in learning hidden topics but they do not take into account metadata of documents. To tackle this problem, many augmented topic models have been proposed to jointly model text and metadata. But most existing models handle only categorical and numerical types of metadata. We identify another type of metadata that can be more natural to obtain in some scenarios.

Recently text-based sentiment prediction has been extensively studied, while image-centric sentiment analysis receives much less attention. In this paper,we study the problem of understanding human sentiments from large-scale social media images,considering both visual content and contextual information,such as comments on the images, captions,etc. The challenge of this problem lies in the "semantic gap" between low-level visual features and higher-level image sentiments. Moreover, the lack of proper annotations/labels in the majority of social media images presents another challenge.To address these two challenges, we propose a novel Unsupervised SEntiment Analysis (USEA) framework for social media images. Our approach exploits relations among visual content and relevant contextual information to bridge the "semantic gap" in the prediction of image sentiments. With experiments on two large-scale datasets, we show that the proposed method is effective in addressing the two challenges.

Sentiment expression in microblog posts often reflects user's specific individuality due to different language habit, personal character, opinion bias and so on. Existing sentiment classification algorithms largely ignore such latent personal distinctions among different microblog users. Meanwhile, sentiment data of microblogs are sparse for individual users, making it infeasible to learn effective personalized classifier. In this paper, we propose a novel, extensible personalized sentiment classification method based on a variant of latent factor model to capture personal sentiment variations by mapping users and posts into a low-dimensional factor space. We alleviate the sparsity of personal texts by decomposing the posts into words which are further represented by the weighted sentiment and topic units based on a set of syntactic units of words obtained from dependency parsing results. To strengthen the representation of users, we leverage users following relation to consolidate the individuality of a user fused from other users with similar interests. Results on real-world microblog datasets confirm that our method outperforms state-of-the-art baseline algorithms with large margins.

User-item connected documents, such as customer reviews for specific items in online shopping website and user tips in location-based social networks, have become more and more prevalent recently. Inferring the topic distributions of user-item connected documents is beneficial for many applications, including document classification and summarization of users and items. While many different topic models have been proposed for modeling multiple text, most of them cannot account for the dual role of user-item connected documents (each document is related to one user and one item simultaneously) in topic distribution generation process. In this paper, we propose a novel probabilistic topic model called Prior-based Dual Additive Latent Dirichlet Allocation (PDA-LDA). It addresses the dual role of each document by associating its Dirichlet prior for topic distribution with user and item topic factors, which leads to a document-level asymmetric Dirichlet prior. In the experiments, we evaluate PDA-LDA on several real datasets and the results demonstrate that our model is effective in comparison to several other models, including held-out perplexity on modeling text and document classification application.

Target-dependent sentiment analysis on Twitter has attracted increasing research attention. Most previous work relies on syntax, such as automatic parse trees, which are subject to noise for informal text such as tweets. In this paper, we show that competitive results can be achieved without the use of syntax, by extracting a rich set of automatic features. In particular, we split a tweet into a left context and a right context according to a given target, using distributed word representations and neural pooling functions to extract features. Both sentiment-driven and standard embeddings are used, and a rich set of neural pooling functions are explored. Sentiment lexicons are used as an additional source of information for feature extraction. In standard evaluation, the conceptually simple method gives a 4.8% absolute improvement over the state-of-the-art on three-way targeted sentiment classification, achieving the best reported results for this task.

In this study, we present an approach and a dataset for aspect-based sentiment analysis, showing how we extract and classify aspect phrases. The research field of aspect-based sentiment analysis aims at finding opinions expressed for individual characteristics of products or services in natural language texts. In the literature, reviews for common products or services such as smartphones or restaurants were mostly investigated. We describe our newly annotated dataset of German physician reviews, which presents a sensitive and linguistically complex domain, taking care to describe the annotation process and the functionality of our neural network approach. Finally, we introduce a model that can extract and classify aspect phrases in one step while obtaining an F1 score of 80%.