It is important for sociable recommendation dialog systems to perform as both on-task content and social content to engage users and gain their favor. In addition to understand the user preferences and provide a satisfying recommendation, such systems must be able to generate coherent and natural social conversations to the user. Traditional dialog state tracking cannot be applied to such systems because it does not track the attributes in the social content. To address this challenge, we propose DEUX, a novel attribute-guided framework to create better user experiences while accomplishing a movie recommendation task. DEUX has a module that keeps track of the movie attributes (e.g., favorite genres, actors,etc.) in both user utterances and system responses. This allows the system to introduce new movie attributes in its social content. Then, DEUX has multiple values for the same attribute type which suits the recommendation task since a user may like multiple genres, for instance. Experiments suggest that DEUX outperforms all the baselines on being more consistent, fitting the user preferences better, and providing a more engaging chat experience. Our approach can be used for any similar problems of sociable task-oriented dialog system.

Topic modeling algorithms traditionally model topics as list of weighted terms. These topic models can be used effectively to classify texts or to support text mining tasks such as text summarization or fact extraction. The general procedure relies on statistical analysis of term frequencies. The focus of this work is on the implementation of the knowledge-based topic modelling services in a KNIME workflow. A brief description and evaluation of the DBPedia-based enrichment approach and the comparative evaluation of enriched topic models will be outlined based on our previous work. DBpedia-Spotlight is used to identify entities in the input text and information from DBpedia is used to extend these entities. We provide a workflow developed in KNIME implementing this approach and perform a result comparison of topic modeling supported by knowledge base information to traditional LDA. This topic modeling approach allows semantic interpretation both by algorithms and by humans.

Multimodal Sentiment Analysis (MuSe) 2021 is a challenge focusing on the tasks of sentiment and emotion, as well as physiological-emotion and emotion-based stress recognition through more comprehensively integrating the audio-visual, language, and biological signal modalities. The purpose of MuSe 2021 is to bring together communities from different disciplines; mainly, the audio-visual emotion recognition community (signal-based), the sentiment analysis community (symbol-based), and the health informatics community. We present four distinct sub-challenges: MuSe-Wilder and MuSe-Stress which focus on continuous emotion (valence and arousal) prediction; MuSe-Sent, in which participants recognise five classes each for valence and arousal; and MuSe-Physio, in which the novel aspect of `physiological-emotion' is to be predicted. For this years' challenge, we utilise the MuSe-CaR dataset focusing on user-generated reviews and introduce the Ulm-TSST dataset, which displays people in stressful depositions. This paper also provides detail on the state-of-the-art feature sets extracted from these datasets for utilisation by our baseline model, a Long Short-Term Memory-Recurrent Neural Network. For each sub-challenge, a competitive baseline for participants is set; namely, on test, we report a Concordance Correlation Coefficient (CCC) of .4616 CCC for MuSe-Wilder; .4717 CCC for MuSe-Stress, and .4606 CCC for MuSe-Physio. For MuSe-Sent an F1 score of 32.82 % is obtained.

Speech processing research is at a high right now, with virtual assistants like Alexa, Siri, Google and others always listening and willing to help. But without a keen eye -- or ear -- for who this technology aims to assist, interest could wane, said Maxine Eskenazi, a Carnegie Mellon University researcher in the School of Computer Science who has worked on speech processing and spoken dialogue systems for decades. "We need to stop focusing on the agent and start focusing on the user," Eskenazi said. "It's only a dialogue if there are two individuals participating. If we make systems that are just fun for us to make but do not serve the user and do not help the user, then they'll stop using Alexa or Google."

Semantic role labeling (SRL) aims to extract the arguments for each predicate in an input sentence. Traditional SRL can fail to analyze dialogues because it only works on every single sentence, while ellipsis and anaphora frequently occur in dialogues. To address this problem, we propose the conversational SRL task, where an argument can be the dialogue participants, a phrase in the dialogue history or the current sentence. As the existing SRL datasets are in the sentence level, we manually annotate semantic roles for 3,000 chit-chat dialogues (27,198 sentences) to boost the research in this direction. Experiments show that while traditional SRL systems (even with the help of coreference resolution or rewriting) perform poorly for analyzing dialogues, modeling dialogue histories and participants greatly helps the performance, indicating that adapting SRL to conversations is very promising for universal dialogue understanding. Our initial study by applying CSRL to two mainstream conversational tasks, dialogue response generation and dialogue context rewriting, also confirms the usefulness of CSRL.

For task-oriented dialog systems, training a Reinforcement Learning (RL) based Dialog Management module suffers from low sample efficiency and slow convergence speed due to the sparse rewards in RL.To solve this problem, many strategies have been proposed to give proper rewards when training RL, but their rewards lack interpretability and cannot accurately estimate the distribution of state-action pairs in real dialogs. In this paper, we propose a multi-level reward modeling approach that factorizes a reward into a three-level hierarchy: domain, act, and slot. Based on inverse adversarial reinforcement learning, our designed reward model can provide more accurate and explainable reward signals for state-action pairs.Extensive evaluations show that our approach can be applied to a wide range of reinforcement learning-based dialog systems and significantly improves both the performance and the speed of convergence.

We introduce Dynabench, an open-source platform for dynamic dataset creation and model benchmarking. Dynabench runs in a web browser and supports human-and-model-in-the-loop dataset creation: annotators seek to create examples that a target model will misclassify, but that another person will not. In this paper, we argue that Dynabench addresses a critical need in our community: contemporary models quickly achieve outstanding performance on benchmark tasks but nonetheless fail on simple challenge examples and falter in real-world scenarios. With Dynabench, dataset creation, model development, and model assessment can directly inform each other, leading to more robust and informative benchmarks. We report on four initial NLP tasks, illustrating these concepts and highlighting the promise of the platform, and address potential objections to dynamic benchmarking as a new standard for the field.

We live in a world where the globe is connected and communication made easy with the click of a button. In this social age, the evolution of the World Wide Web (www), characterized by the advancement of smartphones and semantic technology, has redefined social media as a retail platform and an indispensable marketing tool. Social media marketing (SMM) is a form of digital marketing that involves sharing content on social media platforms in an attempt to actualize a firm's branding, sales, and web traffic goals. Social media has become essential to helping brands connect to a wider range of customers, establish brand presence, and increase sales both in-store and online. Considering the size of this new virtual market, it comes as no surprise that marketers would choose to use social media to increase brand awareness.

Short text is a popular avenue of sharing feedback, opinions and reviews on social media, e-commerce platforms, etc. Many companies need to extract meaningful information (which may include thematic content as well as semantic polarity) out of such short texts to understand users' behaviour. However, obtaining high quality sentiment-associated and human interpretable themes still remains a challenge for short texts. In this paper we develop ELJST, an embedding enhanced generative joint sentiment-topic model that can discover more coherent and diverse topics from short texts. It uses Markov Random Field Regularizer that can be seen as a generalisation of skip-gram based models. Further, it can leverage higher-order semantic information appearing in word embedding, such as self-attention weights in graphical models. Our results show an average improvement of 10% in topic coherence and 5% in topic diversification over baselines. Finally, ELJST helps understand users' behaviour at more granular levels which can be explained. All these can bring significant values to the service and healthcare industries often dealing with customers.

The main motive of using sentiment analysis is to find out the true feelings of the varied people living in our society. It can be used for analyzing the customer feedback of a particular company, normal users on social media towards a product, services, social issues, or political agendas. Companies also use it for brand analysis, reputation crises, campaigns performances, competitor analysis, and improve the service offered to the customers. Analyzing the sentiments of the customers helps the customer support team to prioritize their work for offering better service to end-users. What are the common challenges with which sentiment analysis deals?