Multimodal sentiment analysis (MSA) and emotion recognition in conversation (ERC) are key research topics for computers to understand human behaviors. From a psychological perspective, emotions are the expression of affect or feelings during a short period, while sentiments are formed and held for a longer period. However, most existing works study sentiment and emotion separately and do not fully exploit the complementary knowledge behind the two. In this paper, we propose a multimodal sentiment knowledge-sharing framework (UniMSE) that unifies MSA and ERC tasks from features, labels, and models. We perform modality fusion at the syntactic and semantic levels and introduce contrastive learning between modalities and samples to better capture the difference and consistency between sentiments and emotions. Experiments on four public benchmark datasets, MOSI, MOSEI, MELD, and IEMOCAP, demonstrate the effectiveness of the proposed method and achieve consistent improvements compared with state-of-the-art methods.

Practical dialog systems need to deal with various knowledge sources, noisy user expressions, and the shortage of annotated data. To better solve the above problems, we propose CGoDial, new challenging and comprehensive Chinese benchmark for multi-domain Goal-oriented Dialog evaluation. It contains 96,763 dialog sessions and 574,949 dialog turns totally, covering three datasets with different knowledge sources: 1) a slot-based dialog (SBD) dataset with table-formed knowledge, 2) a flow-based dialog (FBD) dataset with tree-formed knowledge, and a retrieval-based dialog (RBD) dataset with candidate-formed knowledge. To bridge the gap between academic benchmarks and spoken dialog scenarios, we either collect data from real conversations or add spoken features to existing datasets via crowd-sourcing. The proposed experimental settings include the combinations of training with either the entire training set or a few-shot training set, and testing with either the standard test set or a hard test subset, which can assess model capabilities in terms of general prediction, fast adaptability and reliable robustness.

To make a long story short: In principle; yes. And if my colleagues at the University of Edinburgh are to be believed, it even works in cases where an opinion is not explicitly expressed. In fact, the terms "sentiment analysis" or "opinion mining" are nothing new to people who deal with language technology. However, this is not infrequently a marketing ploy: because what sounds like opinion analysis is in fact usually nothing more than a polarity analysis of the feelings that are transported via a text. In other words, it analyzes whether a social media post has positive or negative vibes.

Aspect-Based Sentiment Analysis (ABSA) aims to provide fine-grained aspect-level sentiment information. There are many ABSA tasks, and the current dominant paradigm is to train task-specific models for each task. However, application scenarios of ABSA tasks are often diverse. This solution usually requires a large amount of labeled data from each task to perform excellently. These dedicated models are separately trained and separately predicted, ignoring the relationship between tasks. To tackle these issues, we present UnifiedABSA, a general-purpose ABSA framework based on multi-task instruction tuning, which can uniformly model various tasks and capture the inter-task dependency with multi-task learning. Extensive experiments on two benchmark datasets show that UnifiedABSA can significantly outperform dedicated models on 11 ABSA tasks and show its superiority in terms of data efficiency.

This paper introduces Doc2Bot, a novel dataset for building machines that help users seek information via conversations. This is of particular interest for companies and organizations that own a large number of manuals or instruction books. Despite its potential, the nature of our task poses several challenges: (1) documents contain various structures that hinder the ability of machines to comprehend, and (2) user information needs are often underspecified. Compared to prior datasets that either focus on a single structural type or overlook the role of questioning to uncover user needs, the Doc2Bot dataset is developed to target such challenges systematically. Our dataset contains over 100,000 turns based on Chinese documents from five domains, larger than any prior document-grounded dialog dataset for information seeking. We propose three tasks in Doc2Bot: (1) dialog state tracking to track user intentions, (2) dialog policy learning to plan system actions and contents, and (3) response generation which generates responses based on the outputs of the dialog policy. Baseline methods based on the latest deep learning models are presented, indicating that our proposed tasks are challenging and worthy of further research.

Several hundreds of thousands of raw data files are uploaded by users every day to social media sites. Online user data provides access to an enormous amount of information regarding products, services, places, and events, which makes it suitable for sentiment analysis. Valuable information can be extracted by analyzing the sentiment of the data. It is a method for interpreting opinions within a text that uses Natural Language Processing (NLP) to extract positive, negative, and natural meanings from user-generated content shared on social media platforms. Sentiment analysis has been previously applied to products or movie reviews to understand customers' interests better and, thus, improve outcomes and service offerings.

Some deep learning and machine learning applications need to ensure accuracy through human oversight of sensitive data. This provides the collection of health data, increases the model accuracy, and helps continuous improvements with updated predictions. Data augmentation is a critical process for data companies that spend tons of dollars on this. Today, we will create a sentiment analysis workflow on Amazon Human Review Workflow, an Amazon A2I service.

Human conversations can evolve in many different ways, creating challenges for automatic understanding and summarization. Goal-oriented conversations often have meaningful sub-dialogue structure, but it can be highly domain-dependent. This work introduces an unsupervised approach to learning hierarchical conversation structure, including turn and sub-dialogue segment labels, corresponding roughly to dialogue acts and sub-tasks, respectively. The decoded structure is shown to be useful in enhancing neural models of language for three conversation-level understanding tasks. Further, the learned finite-state sub-dialogue network is made interpretable through automatic summarization.

Aspect-based sentiment analysis (ABSA) task aim at associating a piece of text with a set of aspects and meanwhile infer their respective sentimental polarities. The state-of-the-art approaches are built upon fine-tuning of various pre-trained language models. They commonly attempt to learn aspect-specific representation from the corpus. Unfortunately, the aspect is often expressed implicitly through a set of representatives and thus renders implicit mapping process unattainable unless sufficient labeled examples are available. However, high-quality labeled examples may not be readily available in real-world scenarios. In this paper, we propose to jointly address aspect categorization and aspect-based sentiment subtasks in a unified framework. Specifically, we first introduce a simple but effective mechanism to construct an auxiliary-sentence for the implicit aspect based on the semantic information in the corpus. Then, we encourage BERT to learn the aspect-specific representation in response to the automatically constructed auxiliary-sentence instead of the aspect itself. Finally, we empirically evaluate the performance of the proposed solution by a comparative study on real benchmark datasets for both ABSA and Targeted-ABSA tasks. Our extensive experiments show that it consistently achieves state-of-the-art performance in terms of aspect categorization and aspect-based sentiment across all datasets and the improvement margins are considerable. The code of BERT-ASC is available in GitHub: https://github.com/amurtadha/BERT-ASC.

In dialogue state tracking (DST), labeling the dataset involves considerable human labor. We propose a new self-training framework for fewshot generative DST that utilize unlabeled data. Our self-training method iteratively improves the model by pseudo labeling and employs Purpose Preserving augmentation (PPaug) to prevent overfitting. We increase the few-shot (10%) performance by approximately 4% on Figure 1: Dialogue example of DST dataset and its belief MultiWOZ 2.1 (Eric et al., 2019) and enhances state. The underlined part of the dialogue is the the slot-recall 8.34% for unseen values compared value of the belief state and has specific information to baseline.