Frame semantic parsing is an important component of task-oriented dialogue systems. Current models rely on a significant amount training data to successfully identify the intent and slots in the user's input utterance. This creates a significant barrier for adding new domains to virtual assistant capabilities, as creation of this data requires highly specialized NLP expertise. In this work we propose OpenFSP, a framework that allows for easy creation of new domains from a handful of simple labels that can be generated without specific NLP knowledge. Our approach relies on creating a small, but expressive, set of domain agnostic slot types that enables easy annotation of new domains. Given such annotation, a matching algorithm relying on sentence encoders predicts the intent and slots for domains defined by end-users. Extensive experiments on the TopV2 dataset shows that our model outperforms strong baselines in this simple labels setting.

Machine learning systems regularly deal with structured data in real-world applications. Unfortunately, such data has been difficult to faithfully represent in a way that most machine learning techniques would expect, i.e. as a real-valued vector of a fixed, pre-specified size. In this work, we introduce a novel approach that compiles structured data into a satisfiability problem which has in its set of solutions at least (and often only) the input data. The satisfiability problem is constructed from constraints which are generated automatically a priori from a given signature, thus trivially allowing for a bag-of-words-esque vector representation of the input to be constructed. The method is demonstrated in two areas, automated reasoning and natural language processing, where it is shown to produce vector representations of natural-language sentences and first-order logic clauses that can be precisely translated back to their original, structured input forms.

Human action recognition remains a difficult problem for AI. Traditional machine learning techniques can have high recognition accuracy, but they are typically black boxes whose internal models are not inspectable and whose results are not explainable. This paper describes a new pipeline for recognizing human actions from skeleton data via analogical generalization. Specifically, starting with Kinect data, we segment each human action by temporal regions where the motion is qualitatively uniform, creating a sketch graph that provides a form of qualitative representation of the behavior that is easy to visualize. Models are learned from sketch graphs via analogical generalization, which are then used for classification via analogical retrieval. The retrieval process also produces links between the new example and components of the model that provide explanations. To improve recognition accuracy, we implement dynamic feature selection to pick reasonable relational features. We show the explanation advantage of our approach by example, and results on three public datasets illustrate its utility.

Creating systems that can learn to answer natural language questions has been a longstanding challenge for artificial intelligence. Most prior approaches focused on producing a specialized language system for a particular domain and dataset, and they required training on a large corpus manually annotated with logical forms. This paper introduces an analogy-based approach that instead adapts an existing general purpose semantic parser to answer questions in a novel domain by jointly learning disambiguation heuristics and query construction templates from purely textual question-answer pairs. Our technique uses possible semantic interpretations of the natural language questions and answers to constrain a query-generation procedure, producing cases during training that are subsequently reused via analogical retrieval and composed to answer test questions. Bootstrapping an existing semantic parser in this way significantly reduces the number of training examples needed to accurately answer questions. We demonstrate the efficacy of our technique using the Geoquery corpus, on which it approaches state of the art performance using 10-fold cross validation, shows little decrease in performance with 2-folds, and achieves above 50% accuracy with as few as 10 examples.

The naturalness of qualitative reasoning suggests that qualitative representations might be an important component of the semantics of natural language. Prior work showed that frame-based representations of qualitative process theory constructs could indeed be extracted from natural language texts. That technique relied on the parser recognizing specific syntactic constructions, which had limited coverage. This paper describes a new approach, using narrative function to represent the higher-order relationships between the constituents of a sentence and between sentences in a discourse. We outline how narrative function combined with query-driven abduction enables the same kinds of information to be extracted from natural language texts. Moreover, we also show how the same technique can be used to extract type-level qualitative representations from text, and used to improve performance in playing a strategy game.

One of the major challenges to building intelligent educational software is determining what kinds of feedback to give learners. Useful feedback makes use of models of domain-specific knowledge, especially models that are commonly held by potential students. To empirically determine what these models are, student data can be clustered to reveal common misconceptions or common problem-solving strategies. This paper describes how analogical retrieval and generalization can be used to cluster automatically analyzed hand-drawn sketches incorporating both spatial and conceptual information. We use this approach to cluster a corpus of hand-drawn student sketches to discover common answers. Common answer clusters can be used for the design of targeted feedback and for assessment.

Understanding conceptual change is an important problem in modeling human cognition and in making integrated AI systems that can learn autonomously. This paper describes a model of explanation-based conceptual change, integrating sketch understanding, analogical processing, qualitative models, truth-maintenance, and heuristic-based reasoning within the Companions cognitive architecture. Sketch understanding is used to automatically encode stimuli in the form of comic strips. Qualitative models and conceptual quantities are constructed for new phenomena via analogical reasoning and heuristics. Truth-maintenance is used to integrate conceptual and episodic knowledge into explanations, and heuristics are used to modify existing conceptual knowledge in order to produce better explanations. We simulate the learning and revision of the concept of force, testing the concepts learned via a questionnaire of sketches given to students, showing that our model follows a similar learning trajectory.

Representing and comparing two-dimensional shapes is an important problem. Our hypothesis about human representations is that that people utilize two representations of shape: an abstract, qualitative representation of the spatial relations between the shape’s parts, and a detailed, quantitative representation. The advantage of relational, qualitative representations is that they facilitate shape comparison: two shapes can be compared via structural alignment processes which have been used to model similarity and analogy more broadly. This comparison process plays an important role in determining when two objects share the same shape, or in identifying transformations (rotations and reflections) between two shapes. Based on our hypothesis, we have built a computational model which automatically constructs both qualitative and quantitative representations and uses them to compare two-dimensional shapes in visual scenes. We demonstrate the effectiveness of our model by summarizing a series of studies which have simulated human spatial reasoning.