AAAI.2020 - Demonstration Track

Total: 25

#1 TraceHub - A Platform to Bridge the Gap between State-of-the-Art Time-Series Analytics and Datasets [PDF] [Copy] [Kimi]

Authors: Shubham Agarwal ; Christian Muise ; Mayank Agarwal ; Sohini Upadhyay ; Zilu Tang ; Zhongshen Zeng ; Yasaman Khazaeni

In this paper, we present TraceHub - a platform that connects new non-trivial state-of-the-art time-series analytics with datasets from different domains. Analytics owners can run their insights on new datasets in an automated setting to find insight's potential and improve it. Dataset owners can find all possible types of non-trivial insights based on latest research. We provide a plug-n-play system as a set of Dataset, Transformer pipeline, and Analytics APIs for both kinds of users. We show a usefulness measure of generated insights across various types of analytics in the system. We believe that this platform can be used to bridge the gap between time-series analytics and datasets by significantly reducing the time to find the true potential of budding time-series research and improving on it faster.

#2 MAPF Scenario: Software for Evaluating MAPF Plans on Real Robots [PDF] [Copy] [Kimi]

Authors: Roman Barták ; Jiří Švancara ; Ivan Krasičenko

Multi-Agent Path Finding (MAPF) deals with finding collision free paths for a set of agents (robots) moving on a graph. The interest in MAPF in the research community started to increase recently partly due to practical applications in areas such as warehousing and computer games. However, the academic community focuses mostly on solving the abstract version of the problem (moving of agents on the graph) with only a few results on real robots. The presented software MAPF Scenario provides a tool for specifying MAPF problems on grid maps, solving the problems using various abstractions (for example, assuming rotation actions or not), simulating execution of plans, and translating the abstract plans to control programs for small robots Ozobots. The tool is intended as a research platform for evaluating abstract MAPF plans on real robots and as an educational and demonstration tool bridging the areas of artificial intelligence and robotics.

#3 Doc2Dial: A Framework for Dialogue Composition Grounded in Documents [PDF] [Copy] [Kimi]

Authors: Song Feng ; Kshitij Fadnis ; Q. Vera Liao ; Luis A. Lastras

We introduce Doc2Dial, an end-to-end framework for generating conversational data grounded in given documents. It takes the documents as input and generates the pipelined tasks for obtaining the annotations specifically for producing the simulated dialog flows. Then, the dialog flows are used to guide the collection of the utterances via the integrated crowdsourcing tool. The outcomes include the human-human dialogue data grounded in the given documents, as well as various types of automatically or human labeled annotations that help ensure the quality of the dialog data with the flexibility to (re)composite dialogues. We expect such data can facilitate building automated dialogue agents for goal-oriented tasks. We demonstrate Doc2Dial system with the various domain documents for customer care.

#4 MatchU: An Interactive Matching Platform [PDF] [Copy] [Kimi]

Authors: James Ferris ; Hadi Hosseini

MatchU is a web-based platform that offers an interactive framework to find how to form mutually-beneficial relationships, decide how to distribute resources, or resolve conflicts through a suite of matching algorithms rooted in economics and artificial intelligence. In this paper, we discuss MatchU's vision, solutions, and future directions.

#5 Embedding High-Level Knowledge into DQNs to Learn Faster and More Safely [PDF] [Copy] [Kimi]

Authors: Zihang Gao ; Fangzhen Lin ; Yi Zhou ; Hao Zhang ; Kaishun Wu ; Haodi Zhang

Deep reinforcement learning has been successfully applied in many decision making scenarios. However, the slow training process and difficulty in explaining limit its application. In this paper, we attempt to address some of these problems by proposing a framework of Rule-interposing Learning (RIL) that embeds knowledge into deep reinforcement learning. In this framework, the rules dynamically effect the training progress, and accelerate the learning. The embedded knowledge in form of rule not only improves learning efficiency, but also prevents unnecessary or disastrous explorations at early stage of training. Moreover, the modularity of the framework makes it straightforward to transfer high-level knowledge among similar tasks.

#6 Causal Knowledge Extraction through Large-Scale Text Mining [PDF] [Copy] [Kimi]

Authors: Oktie Hassanzadeh ; Debarun Bhattacharjya ; Mark Feblowitz ; Kavitha Srinivas ; Michael Perrone ; Shirin Sohrabi ; Michael Katz

In this demonstration, we present a system for mining causal knowledge from large corpuses of text documents, such as millions of news articles. Our system provides a collection of APIs for causal analysis and retrieval. These APIs enable searching for the effects of a given cause and the causes of a given effect, as well as the analysis of existence of causal relation given a pair of phrases. The analysis includes a score that indicates the likelihood of the existence of a causal relation. It also provides evidence from an input corpus supporting the existence of a causal relation between input phrases. Our system uses generic unsupervised and weakly supervised methods of causal relation extraction that do not impose semantic constraints on causes and effects. We show example use cases developed for a commercial application in enterprise risk management.

#7 DAMN: Defeasible Reasoning Tool for Multi-Agent Reasoning [PDF] [Copy] [Kimi]

Authors: Abdelraouf Hecham ; Madalina Croitoru ; Pierre Bisquert

This demonstration paper introduces DAMN: a defeasible reasoning platform available on the web. It is geared towards decision making where each agent has its own knowledge base that can be combined with other agents to detect and visualize conflicts and potentially solve them using a semantics. It allows the use of different defeasible reasoning semantics (ambiguity blocking/propagating with or without team defeat) and integrates agent collaboration and visualization features.

#8 D-Agree: Crowd Discussion Support System Based on Automated Facilitation Agent [PDF] [Copy] [Kimi]

Authors: Takayuki Ito ; Shota Suzuki ; Naoko Yamaguchi ; Tomohiro Nishida ; Kentaro Hiraishi ; Kai Yoshino

Large-scale online discussion platforms are receiving great attention as potential next-generation methods for smart democratic citizen platforms. One of the studies clarified the critical problem faced by human facilitators caused by the difficulty of facilitating large-scale online discussions. In this demonstration, we present our current implementation of D-agree, a crowd-scale discussion support system based on an automated facilitation agent. We conducted a large-scale social experiment with Nagoya local government. The results demonstrate that the agent worked well compared with human facilitators.

#9 ‘Watch the Flu’: A Tweet Monitoring Tool for Epidemic Intelligence of Influenza in Australia [PDF] [Copy] [Kimi]

Authors: Brian Jin ; Aditya Joshi ; Ross Sparks ; Stephen Wan ; Cécile Paris ; C Raina MacIntyre

‘Watch The Flu’ is a tool that monitors tweets posted in Australia for symptoms of influenza. The tool is a unique combination of two areas of artificial intelligence: natural language processing and time series monitoring, in order to assist public health surveillance. Using a real-time data pipeline, it deploys a web-based dashboard for visual analysis, and sends out emails to a set of users when an outbreak is detected. We expect that the tool will assist public health experts with their decision-making for disease outbreaks, by providing them insights from social media.

#10 Diana's World: A Situated Multimodal Interactive Agent [PDF] [Copy] [Kimi]

Authors: Nikhil Krishnaswamy ; Pradyumna Narayana ; Rahul Bangar ; Kyeongmin Rim ; Dhruva Patil ; David McNeely-White ; Jaime Ruiz ; Bruce Draper ; Ross Beveridge ; James Pustejovsky

State of the art unimodal dialogue agents lack some core aspects of peer-to-peer communication—the nonverbal and visual cues that are a fundamental aspect of human interaction. To facilitate true peer-to-peer communication with a computer, we present Diana, a situated multimodal agent who exists in a mixed-reality environment with a human interlocutor, is situation- and context-aware, and responds to the human's language, gesture, and affect to complete collaborative tasks.

#11 GENO – Optimization for Classical Machine Learning Made Fast and Easy [PDF] [Copy] [Kimi]

Authors: Sören Laue ; Matthias Mitterreiter ; Joachim Giesen

Most problems from classical machine learning can be cast as an optimization problem. We introduce GENO (GENeric Optimization), a framework that lets the user specify a constrained or unconstrained optimization problem in an easy-to-read modeling language. GENO then generates a solver, i.e., Python code, that can solve this class of optimization problems. The generated solver is usually as fast as hand-written, problem-specific, and well-engineered solvers. Often the solvers generated by GENO are faster by a large margin compared to recently developed solvers that are tailored to a specific problem class. An online interface to our framework can be found at

#12 CAiRE: An End-to-End Empathetic Chatbot [PDF] [Copy] [Kimi]

Authors: Zhaojiang Lin ; Peng Xu ; Genta Indra Winata ; Farhad Bin Siddique ; Zihan Liu ; Jamin Shin ; Pascale Fung

We present CAiRE, an end-to-end generative empathetic chatbot designed to recognize user emotions and respond in an empathetic manner. Our system adapts the Generative Pre-trained Transformer (GPT) to empathetic response generation task via transfer learning. CAiRE is built primarily to focus on empathy integration in fully data-driven generative dialogue systems. We create a web-based user interface which allows multiple users to asynchronously chat with CAiRE. CAiRE also collects user feedback and continues to improve its response quality by discarding undesirable generations via active learning and negative training.

#13 Plan2Dance: Planning Based Choreographing from Music [PDF] [Copy] [Kimi]

Authors: Yuechang Liu ; Dongbo Xie ; Hankz Hankui Zhuo ; Liqian Lai

The field of dancing robots has drawn much attention from numerous sources. Despite the success of previous systems on choreography for robots to dance with external stimuli, they are often either limited to a pre-defined set of movements or lack of considering “hard” relations among dancing motions. In the demonstration, we design a planning based choreographing system, which views choreography with music as planning problems and solve the problems with off-the-shelf planners. Our demonstration exhibits the effectiveness of our system via evaluating our system with various music.

#14 Deep Poetry: A Chinese Classical Poetry Generation System [PDF] [Copy] [Kimi]

Authors: Yusen Liu ; Dayiheng Liu ; Jiancheng Lv

In this work, we demonstrate a Chinese classical poetry generation system called Deep Poetry. Existing systems for Chinese classical poetry generation are mostly template-based and very few of them can accept multi-modal input. Unlike previous systems, Deep Poetry uses neural networks that are trained on over 200 thousand poems and 3 million ancient Chinese prose. Our system can accept plain text, images or artistic conceptions as inputs to generate Chinese classical poetry. More importantly, users are allowed to participate in the process of writing poetry by our system. For the user's convenience, we deploy the system at the WeChat applet platform, users can use the system on the mobile device whenever and wherever possible.

#15 PulseSatellite: A Tool Using Human-AI Feedback Loops for Satellite Image Analysis in Humanitarian Contexts [PDF] [Copy] [Kimi]

Authors: Tomaz Logar ; Joseph Bullock ; Edoardo Nemni ; Lars Bromley ; John A. Quinn ; Miguel Luengo-Oroz

Humanitarian response to natural disasters and conflicts can be assisted by satellite image analysis. In a humanitarian context, very specific satellite image analysis tasks must be done accurately and in a timely manner to provide operational support. We present PulseSatellite, a collaborative satellite image analysis tool which leverages neural network models that can be retrained on-the fly and adapted to specific humanitarian contexts and geographies. We present two case studies, in mapping shelters and floods respectively, that illustrate the capabilities of PulseSatellite.

#16 LearnIt: On-Demand Rapid Customization for Event-Event Relation Extraction [PDF] [Copy] [Kimi]

Authors: Bonan Min ; Manaj Srivastava ; Haoling Qiu ; Prasannakumar Muthukumar ; Joshua Fasching

We present a system which allows a user to create event-event relation extractors on-demand with a small amount of effort. The system provides a suite of algorithms, flexible workflows, and a user interface (UI), to allow rapid customization of event-event relation extractors for new types and domains of interest. Experiments show that it enables users to create extractors for 6 types of causal and temporal relations, with less than 20 minutes of effort per type. Our system (source code, UI) is available at A demonstration video is available at

#17 Exploratory Navigation and Selective Reading [PDF] [Copy] [Kimi]

Authors: Natwar Modani ; Paridhi Maheshwari ; Harsh Deshpande ; Saurab Sirpurkar ; Diviya . ; Somak Aditya

Navigating a collection of documents can be facilitated by obtaining a human-understandable concept hierarchy with links to the content. This is a non-trivial task for two reasons. First, defining concepts that are understandable by an average consumer and yet meaningful for a large variety of corpora is hard. Second, creating semantically meaningful yet intuitive hierarchical representation is hard, and can be task dependent. We present out system which automatically processes a document collection, induces a concept hierarchy using Wikipedia and presents an interactive interface that helps user navigate to individual paragraphs using concepts.

#18 PARTNER: Human-in-the-Loop Entity Name Understanding with Deep Learning [PDF] [Copy] [Kimi]

Authors: Kun Qian ; Poornima Chozhiyath Raman ; Yunyao Li ; Lucian Popa

Entity name disambiguation is an important task for many text-based AI tasks. Entity names usually have internal semantic structures that are useful for resolving different variations of the same entity. We present, PARTNER, a deep learning-based interactive system for entity name understanding. Powered by effective active learning and weak supervision, PARTNER can learn deep learning-based models for identifying entity name structure with low human effort. PARTNER also allows the user to design complex normalization and variant generation functions without coding skills.

#19 Cognitive Compliance: Assessing Regulatory Risk in Financial Advice Documents [PDF] [Copy] [Kimi]

Authors: Wanita Sherchan ; Sue Ann Chen ; Simon Harris ; Nebula Alam ; Khoi-Nguyen Tran ; Christopher J. Butler

This paper describes Cognitive Compliance - a solution that automates the complex manual process of assessing regulatory compliance of personal financial advice. The solution uses natural language processing (NLP), machine learning and deep learning to characterise the regulatory risk status of personal financial advice documents with traffic light rating for various risk factors. This enables comprehensive coverage of the review and rapid identification of documents at high risk of non-compliance with government regulations.

#20 DICR: AI Assisted, Adaptive Platform for Contract Review [PDF] [Copy] [Kimi]

Authors: Dan G. Tecuci ; Ravi Palla ; Hamid R. Motahari Nezhad ; Nishchal Ahuja ; Alex Monteiro ; Tigran Ishkhanov ; Nigel Duffy

In the regular course of business, companies spend a lot of effort reading and interpreting documents, a highly manual process that involves tedious tasks, such as identifying dates and names or locating the presence or absence of certain clauses in a contract. Dealing with natural language is complex and further complicated by the fact that these documents come in various formats (scanned image, digital formats) and have different degrees of internal structure (spreadsheets, invoices, text documents). We present DICR, an end-to-end, modular, and trainable system that automates the mundane aspects of document review and allows humans to perform the validation. The system is able to speed up this work while increasing quality of information extracted, consistency, throughput, and decreasing time to decision. Extracted data can be fed into other downstream applications (from dashboards to Q&A and to report generation).

#21 Data-Driven Ranking and Visualization of Products by Competitiveness [PDF] [Copy] [Kimi]

Authors: Sheema Usmani ; Mariana Bernagozzi ; Yufeng Huang ; Michelle Morales ; Amir Sabet Sarvestani ; Biplav Srivastava

Competitive analysis is a critical part of any business. Product managers, sellers, and marketers spend time and resources scouring through a huge volume of online and offline content, aiming to discover what their competitors are doing in the marketplace and to understand what type of threat they pose to their business' financial well-being. Currently, this process is slow, costly and labor-intensive. We demonstrate Clarity, a data-driven unsupervised system for assessment of products, which is currently in deployment at IBM. Clarity has been running for more than a year and is used by over 1,500 people to perform over 160 competitive analyses involving over 800 products. The system considers multiple factors from a collection of online content: numeric ratings by users, sentiment towards key product drivers, content volume, and recency of content. The results and explanations of factors leading to the results are visualized in an interactive dashboard that allows users to track the performance of their products as well as understand the main contributing factors. main contributing factors.

#22 DRAGON-V: Detection and Recognition of Airplane Goals with Navigational Visualization [PDF] [Copy] [Kimi]

Authors: Christabel Wayllace ; Sunwoo Ha ; Yuchen Han ; Jiaming Hu ; Shayan Monadjemi ; William Yeoh ; Alvitta Ottley

We introduce Detection and Recognition of Airplane GOals with Navigational Visualization (DRAGON-V), a visualization system that uses probabilistic goal recognition to infer and display the most probable airport runway that a pilot is approaching. DRAGON-V is especially useful in cases of miscommunication, low visibility, or lack of airport familiarity which may result in a pilot deviating from the assigned taxiing route. The visualization system conveys relevant information, and updates according to the airplane's current geolocation. DRAGON-V aims to assist air traffic controllers in reducing incidents of runway incursions at airports.

#23 PresentationTrainer: Oral Presentation Support System for Impression-Related Feedback [PDF] [Copy] [Kimi]

Authors: Shengzhou Yi ; Hiroshi Yumoto ; Xueting Wang ; Toshihiko Yamasaki

In order to support the pratice of oral presentation, we developed PresentationTrainer which includes (1) a presentation impression prediction system and (2) a presentation slide analysis system. For the presentation impression prediction system, we proposed two methods, using Support Vector Machine and Markov Random Field, or using multimodal neural network, to predict audiences' impressions for speech videos. For the slide analysis system, we used Convolutional Neural Network and Global Average Pooling to evaluate the design of slides. We then used Class Activation Mapping to provide visual feedback for showing which areas should be modified.

#24 Automatic Car Damage Assessment System: Reading and Understanding Videos as Professional Insurance Inspectors [PDF] [Copy] [Kimi]

Authors: Wei Zhang ; Yuan Cheng ; Xin Guo ; Qingpei Guo ; Jian Wang ; Qing Wang ; Chen Jiang ; Meng Wang ; Furong Xu ; Wei Chu

We demonstrate a car damage assessment system in car insurance field based on artificial intelligence techniques, which can exempt insurance inspectors from checking cars on site and help people without professional knowledge to evaluate car damages when accidents happen. Unlike existing approaches, we utilize videos instead of photos to interact with users to make the whole procedure as simple as possible. We adopt object and video detection and segmentation techniques in computer vision, and take advantage of multiple frames extracted from videos to achieve high damage recognition accuracy. The system uploads video streams captured by mobile devices, recognizes car damage on the cloud asynchronously and then returns damaged components and repair costs to users. The system evaluates car damages and returns results automatically and effectively in seconds, which reduces laboratory costs and decreases insurance claim time significantly.

#25 Combining Machine Learning Models Using combo Library [PDF] [Copy] [Kimi]

Authors: Yue Zhao ; Xuejian Wang ; Cheng Cheng ; Xueying Ding

Model combination, often regarded as a key sub-field of ensemble learning, has been widely used in both academic research and industry applications. To facilitate this process, we propose and implement an easy-to-use Python toolkit, combo, to aggregate models and scores under various scenarios, including classification, clustering, and anomaly detection. In a nutshell, combo provides a unified and consistent way to combine both raw and pretrained models from popular machine learning libraries, e.g., scikit-learn, XGBoost, and LightGBM. With accessibility and robustness in mind, combo is designed with detailed documentation, interactive examples, continuous integration, code coverage, and maintainability check; it can be installed easily through Python Package Index (PyPI) or {}.