The potential for agents, whether embodied or software, to learn by observing other agents performing procedures involving objects and actions is rich. Current research on automatic procedure learning heavily relies on action labels or video subtitles, even during the evaluation phase, which makes them infeasible in real-world scenarios. This leads to our question: can the human-consensus structure of a procedure be learned from a large set of long, unconstrained videos (e.g., instructional videos from YouTube) with only visual evidence? To answer this question, we introduce the problem of procedure segmentation---to segment a video procedure into category-independent procedure segments. Given that no large-scale dataset is available for this problem, we collect a large-scale procedure segmentation dataset with procedure segments temporally localized and described; we use cooking videos and name the dataset YouCook2. We propose a segment-level recurrent network for generating procedure segments by modeling the dependencies across segments. The generated segments can be used as pre-processing for other tasks, such as dense video captioning and event parsing. We show in our experiments that the proposed model outperforms competitive baselines in procedure segmentation.

To have a more meaningful impact, educational applications need to significantly improve the way feedback is offered to teachers and students. We propose two methods for determining propositional-level entailment relations between a reference answer and a student's response. Both methods, one using hand-crafted features and an SVM and the other using word embeddings and deep neural networks, achieve significant improvements over a state-of-the-art system and two alternative approaches.

A computer science faculty member and a philosophy faculty member collaborated in the development of a one-week introduction to ethics which was integrated into a traditional AI course. The goals were to: (1) encourage students to think about the moral complexities involved in developing accident algorithms for autonomous vehicles, (2) identify what issues need to be addressed in order to develop a satisfactory solution to the moral issues surrounding these algorithms, and (3) and to offer students an example of how computer scientists and ethicists must work together to solve a complex technical and moral problems. The course module introduced Utilitarianism and engaged students in considering the classic "Trolley Problem," which has gained contemporary relevance with the emergence of autonomous vehicles. Students used this introduction to ethics in thinking through the implications of their final projects. Results from the module indicate that students gained some fluency with Utilitarianism, including a strong understanding of the Trolley Problem. This short paper argues for the need of providing students with instruction in ethics in AI course. Given the strong alignment between AI's decision-theoretic approaches and Utilitarianism, we highlight the difficulty of encouraging AI students to challenge these assumptions.

Can student behavior be anticipated in real-time so that an intelligent tutor system can adapt its content to keep the student engaged? Current methods detect affective states of students during learning session to determine their engagement levels but apply the learning in next session in the form of intervention policies and tutor responses. However, if students' imminent behavioral action could be anticipated from their affective states in real-time, this could lead to much more responsive intervention policies by the tutor and assist in keeping the student engaged in an activity, thereby increasing tutor efficacy as well as student engagement levels. In this paper we explore if there exist any links between a student's affective states and his/her imminent behavior action in RoboTutor, an intelligent tutor system for children to learn math, reading and writing. We then exploit our findings to develop a real-time student behavior prediction module.

While constraints are ubiquitous in artificial intelligence and constraints are also commonly used in machine learning and data mining, the problem of learning constraints from examples has received less attention. In this paper, we discuss the problem of constraint learning in detail, indicate some subtle differences with standard machine learning problems, sketch some applications and summarize the state-of-the-art.

Inspired by recent works in Aspect-Based Sentiment Analysis (ABSA) on product reviews and faced with more complex posts on social media platforms mentioning multiple entities as well as multiple aspects, we define a novel task called Multi-Entity Aspect-Based Sentiment Analysis (ME-ABSA). This task aims at fine-grained sentiment analysis of (entity, aspect) combinations, making the well-studied ABSA task a special case of it. To address the task, we propose an innovative method that models Context memory, Entity memory and Aspect memory, called CEA method. Our experimental results show that our CEA method achieves a significant gain over several baselines, including the state-of-the-art method for the ABSA task, and their enhanced versions, on datasets for ME-ABSA and ABSA tasks. The in-depth analysis illustrates the significant advantage of the CEA method over baseline methods for several hard-to-predict post types. Furthermore, we show that the CEA method is capable of generalizing to new (entity, aspect) combinations with little loss of accuracy. This observation indicates that data annotation in real applications can be largely simplified.

We present assertion based question answering (ABQA), an open domain question answering task that takes a question and a passage as inputs, and outputs a semi-structured assertion consisting of a subject, a predicate and a list of arguments. An assertion conveys more evidences than a short answer span in reading comprehension, and it is more concise than a tedious passage in passage-based QA. These advantages make ABQA more suitable for human-computer interaction scenarios such as voice-controlled speakers. Further progress towards improving ABQA requires richer supervised dataset and powerful models of text understanding. To remedy this, we introduce a new dataset called WebAssertions, which includes hand-annotated QA labels for 358,427 assertions in 55,960 web passages. To address ABQA, we develop both generative and extractive approaches. The backbone of our generative approach is sequence to sequence learning. In order to capture the structure of the output assertion, we introduce a hierarchical decoder that first generates the structure of the assertion and then generates the words of each field. The extractive approach is based on learning to rank. Features at different levels of granularity are designed to measure the semantic relevance between a question and an assertion. Experimental results show that our approaches have the ability to infer question-aware assertions from a passage. We further evaluate our approaches by incorporating the ABQA results as additional features in passage-based QA. Results on two datasets show that ABQA features significantly improve the accuracy on passage-based QA.

In this paper, we aim at tackling the problem of dynamic user profiling in the context of streams of short texts. Profiling users' expertise in such context is more challenging than in the case of long documents in static collection as it is difficult to track users' dynamic expertise in streaming sparse data. To obtain better profiling performance, we propose a streaming profiling algorithm (SPA). SPA first utilizes the proposed user expertise tracking topic model (UET) to track the changes of users' dynamic expertise and then utilizes the proposed streaming keyword diversification algorithm (SKDA) to produce top-k diversified keywords for profiling users' dynamic expertise at a specific point in time. Experimental results validate the effectiveness of the proposed algorithms.

Hidden variable models are important tools for solving open domain machine comprehension tasks and have achieved remarkable accuracy in many question answering benchmark datasets. Existing models impose strong independence assumptions on hidden variables, which leaves the interaction among them unexplored. Here we introduce linguistic structures to help capturing global evidence in hidden variable modeling. In the proposed algorithms, question-answer pairs are scored based on structured inference results on parse trees and semantic frames, which aims to assign hidden variables in a global optimal way. Experiments on the MCTest dataset demonstrate that the proposed models are highly competitive with state-of-the-art machine comprehension systems.

In this paper we study a new learning problem defined as "Single-Teacher Multi-Student" (STMS) problem, which investigates how to learn a series of student (simple and specific) models from a single teacher (complex and universal) model. Taking the multiclass and binary classification for example, we focus on learning multiple binary classifiers from a single multiclass classifier, where each of binary classifier is responsible for a certain class. This actually derives from some realistic problems, such as identifying the suspect based on a comprehensive face recognition system. By treating the already-trained multiclass classifier as the teacher, and multiple binary classifiers as the students, we propose a gated support vector machine (gSVM) as a solution. A series of gSVMs are learned with the help of single teacher multiclass classifier. The teacher's help is two-fold; first, the teacher's score provides the gated values for students' decision; second, the teacher can guide the students to accommodate training examples with different difficulty degrees. Extensive experiments on real datasets validate its effectiveness.