US2RO: Union of Superpoints to Recognize Objects

The creation of interactive virtual reality (VR) applications from 3D scanned content usually includes a lot of manual and repetitive work. Our research aim is to develop agents that recognize objects to enhance the creation of interactive VR applications. We trained partition agents in our superpoint growing environment that we extended with an expert function. This expert function solves the sparse reward signal problem of the previous approaches and enables to use a variant of imitation learning and deep reinforcement learning with dense feedback. Additionally, the function allows to calculate a performance metric for the degree of imitation for different partitions. Furthermore, we introduce an environment to optimize the superpoint generation. We trained our agents with 1182 scenes of the ScanNet data set. More specifically, we trained different neural network architectures with 1170 scenes and tested their performance with 12 scenes. Our intermediate results are promising such that our partition system might be able to assist the VR application development from 3D scanned content in near future.

Generating Predictable and Adaptive Dialog Policies in Single- and Multi-domain Goal-oriented Dialog Systems

Most existing commercial goal-oriented chatbots are diagram-based; i.e. they follow a rigid dialog flow to fill the slot values needed to achieve a user’s goal. Diagram-based chatbots are predictable, thus their adoption in commercial settings; however, their lack of flexibility may cause many users to leave the conversation before achieving their goal. On the other hand, state-of-the-art research chatbots use Reinforcement Learning (RL) to generate flexible dialog policies. However, such chatbots can be unpredictable, may violate the intended business constraints, and require large training datasets to produce a mature policy. We propose a framework that achieves a middle ground between the diagram-based and RL-based chatbots: we constrain the space of possible chatbot responses using a novel structure, the chatbot dependency graph, and use RL to dynamically select the best valid responses. Dependency graphs are directed graphs that conveniently express a chatbot’s logic by defining the dependencies among slots: all valid dialog flows are encapsulated in one dependency graph. Our experiments in both single-domain and multi-domain settings show that our framework quickly adapts to user characteristics and achieves up to 23.77% improved success rate compared to a state-of-the-art RL model.

Inspiring Movement — Physical Activity in a Virtual Sea as a Driver for Ecological Awareness

As environmental pollution continues to expand, new ways for raising awareness for the consequences need to be explored. Virtual reality has emerged as an effective tool for behavioral change. This paper investigates if virtual reality applications controlled through physical activity can support an even stronger effect, because they enhance attention and recall performance by stimulating working memory through motor functions. This was tested in an experimental study ([Formula: see text]) using a virtual reality head-mounted display in combination with the ICAROS fitness device enabling participants to explore either a plastic-polluted or a non-polluted sea. Results indicated that using a regular controller elicits more presence and a more intense Flow experience than the ICAROS condition, which people controlled via their physical activity. Moreover, the plastic-polluted stimulus was more effective in inducing people’s stated tendency to change their attitude than a non-polluted sea.

Automatic Title Generation for Learning Resources and Pathways with Pre-trained Transformer Models

To create curiosity and interest for a topic in online learning is a challenging task. A good preview that outlines the contents of a learning pathway could help learners know the topic and get interested in it. Towards this end, we propose a hierarchical title generation approach to generate semantically relevant titles for the learning resources in a learning pathway and a title for the pathway itself. Our approach to Automatic Title Generation for a given text is based on pre-trained Transformer Language Model GPT-2. A pool of candidate titles are generated and an appropriate title is selected among them which is then refined or de-noised to get the final title. The model is trained on research paper abstracts from arXiv and evaluated on three different test sets. We show that it generates semantically and syntactically relevant titles as reflected in ROUGE, BLEU scores and human evaluations. We propose an optional abstractive Summarizer module based on pre-trained Transformer model T5 to shorten medium length documents. This module is also trained and evaluated on research papers from arXiv dataset. Finally, we show that the proposed model of hierarchical title generation for learning pathways has promising results.

Learning a Generalizable Model of Team Conflict from Multiparty Dialogues

Good communication is indubitably the foundation of effective teamwork. Over time teams develop their own communication styles and often exhibit entrainment, a conversational phenomena in which humans synchronize their linguistic choices. Conversely, teams may experience conflict due to either personal incompatibility or differing viewpoints. We tackle the problem of predicting team conflict from embeddings learned from multiparty dialogues such that teams with similar post-task conflict scores lie close to one another in vector space. Embeddings were extracted from three types of features: (1) dialogue acts, (2) sentiment polarity, and (3) syntactic entrainment. Machine learning models often suffer domain shift; one advantage of encoding the semantic features is their adaptability across multiple domains. To provide intuition on the generalizability of different embeddings to other goal-oriented teamwork dialogues, we test the effectiveness of learned models trained on the Teams corpus on two other datasets. Unlike syntactic entrainment, both dialogue act and sentiment embeddings are effective for identifying team conflict. Our results show that dialogue act-based embeddings have the potential to generalize better than sentiment and entrainment-based embeddings. These findings have potential ramifications for the development of conversational agents that facilitate teaming.

Identifying and Translating Subjective Content Descriptions Among Texts

An agent pursuing a task may work with a corpus of documents as a reference library. Subjective content descriptions (SCDs) provide additional data that add value in the context of the agent’s task. In the pursuit of documents to add to the corpus, an agent may come across new documents where content text and SCDs from another agent are interleaved and no distinction can be made unless the agent knows the content from somewhere else. Therefore, this paper presents a hidden Markov model-based approach to identify SCDs in a new document where SCDs occur inline among content text. Additionally, we present a dictionary selection approach to identify suitable translations for content text and SCDs based on [Formula: see text]-grams. We end with a case study evaluating both approaches based on simulated and real-world data.