Natural language generation (NLG) has been featured in at most a handful of shipped games and interactive stories. This is certainly due to it being a very specialized practice, but another contributing factor is that the state of the art today, in terms of content quality, is simply inadequate. The major benefits of NLG are its alleviation of authorial burden and the capability it gives to a system of generating state-bespoke content, but we believe we can have these benefits without actually employing a full NLG pipeline. In this paper, we present the preliminary design of Expressionist, an in-development mixed-initiative authoring tool that instantiates an authoring scheme residing somewhere between conventional NLG and conventional human content authoring. In this scheme, a human author plays the part of an NLG module in that she starts from a set of deep representations constructed for the game or story domain and proceeds to specify dialogic content that may express those representations. Rather than authoring static dialogue, the author defines a probabilistic context-free grammar that yields templated dialogue. This allows a human author to still harness a computer's generativity, but in a capacity in which it can be trusted: operating over probabilities and treelike control structures. Additional features of Expressionist's design include arbitrary markup and realtime feedback showing currently valid derivations.

For young children, adults learning English, or individuals with language disorders, complex narratives are difficult to create and understand.  While narratives can easily be assessed in terms of their lexical and syntactic difficulty, automatically measuring the level of narrative complexity is a challenging problem.  We present and evaluate a preliminary system for assessing narrative complexity, which should help identify suitable texts for readers and assist in narrative skill evaluation.

Crowdsourcing for linguistic data typically aims to replicate expert annotations using simplified tasks. But an alternative goal — one that is especially relevant for research in the domains of language meaning and use — is to tap into people's rich experience as everyday users of language. Research in these areas has the potential to tell us a great deal about how language works, but designing annotation frameworks for crowdsourcing of this kind poses special challenges. In this paper we define and exemplify two approaches to linguistic data collection corresponding to these differing goals (model-driven and user-driven) and discuss some hybrid cases in which they overlap. We also describe some design principles and resolution techniques helpful for eliciting linguistic wisdom from the crowd.

We present a new recommendation setting for picking out two items from a given set to be highlighted to a user, based on contextual input. These two items are presented to a user who chooses one of them, possibly stochastically, with a bias that favours the item with the higher value. We propose a second-order algorithm framework that members of it use uses relative upper-confidence bounds to trade off exploration and exploitation, and some explore via sampling. We analyze one algorithm in this framework in an adversarial setting with only mild assumption on the data, and prove a regret bound of $O(Q_T + \sqrt{TQ_T\log T} + \sqrt{T}\log T)$, where $T$ is the number of rounds and $Q_T$ is the cumulative approximation error of item values using a linear model. Experiments with product reviews from 33 domains show the advantage of our methods over algorithms designed for related settings, and that UCB based algorithms are inferior to greed or sampling based algorithms.

In this article, we report on a multiphase R&D effort to develop a conversational second screen application for TV program discovery. Our goal is to share with the community the breadth of artificial intelligence (AI) and natural language (NL) technologies required to develop such an application along with learnings from target end-users. We first give an overview of our application from the perspective of the end-user. We then present the architecture of our application along with the main AI and NL components, which were developed over multiple phases. The first phase focuses on enabling core functionality such as effectively finding programs matching the user’s intent. The second phase focuses on enabling dialog with the user. Finally, we present two user studies, corresponding to these two phases. The results from both studies demonstrate the effectiveness of our application in the target domain.

Textual inference is an important component in many applications for understanding natural language. Classical approaches to textual inference rely on logical representations for meaning, which may be regarded as "external" to the natural language itself. However, practical applications usually adopt shallower lexical or lexical-syntactic representations, which correspond closely to language structure. In many cases, such approaches lack a principled meaning representation and inference framework. We describe an inference formalism that operates directly on language-based structures, particularly syntactic parse trees. New trees are generated by applying inference rules, which provide a unified representation for varying types of inferences. We use manual and automatic methods to generate these rules, which cover generic linguistic structures as well as specific lexical-based inferences. We also present a novel packed data-structure and a corresponding inference algorithm that allows efficient implementation of this formalism. We proved the correctness of the new algorithm and established its efficiency analytically and empirically. The utility of our approach was illustrated on two tasks: unsupervised relation extraction from a large corpus, and the Recognizing Textual Entailment (RTE) benchmarks.

Recursive neural models, which use syntactic parse trees to recursively generate representations bottom-up, are a popular architecture. But there have not been rigorous evaluations showing for exactly which tasks this syntax-based method is appropriate. In this paper we benchmark {\bf recursive} neural models against sequential {\bf recurrent} neural models (simple recurrent and LSTM models), enforcing apples-to-apples comparison as much as possible. We investigate 4 tasks: (1) sentiment classification at the sentence level and phrase level; (2) matching questions to answer-phrases; (3) discourse parsing; (4) semantic relation extraction (e.g., {\em component-whole} between nouns). Our goal is to understand better when, and why, recursive models can outperform simpler models. We find that recursive models help mainly on tasks (like semantic relation extraction) that require associating headwords across a long distance, particularly on very long sequences. We then introduce a method for allowing recurrent models to achieve similar performance: breaking long sentences into clause-like units at punctuation and processing them separately before combining. Our results thus help understand the limitations of both classes of models, and suggest directions for improving recurrent models.

We consider problems of sequential robot manipulation (aka. combined task and motion planning) where the objective is primarily given in terms of a cost function over the final geometric state, rather than a symbolic goal description. In this case we should leverage optimization methods to inform search over potential action sequences. We propose to formulate the problem holistically as a 1st-order logic extension of a mathematical program: a non-linear constrained program over the full world trajectory where the symbolic state-action sequence defines the (in-)equality constraints. We tackle the challenge of solving such programs by proposing three levels of approximation: The coarsest level introduces the concept of the effective end state kinematics, parametrically describing all possible end state configurations conditional to a given symbolic action sequence. Optimization on this level is fast and can inform symbolic search. The other two levels optimize over interaction keyframes and eventually over the full world trajectory across interactions. We demonstrate the approach on a problem of maximizing the height of a physically stable construction from an assortment of boards, cylinders and blocks.

We consider problems of sequential robot manipulation (aka. combined task and motion planning) where the objective is primarily given in terms of a cost function over the final geometric state, rather than a symbolic goal description. In this case we should leverage optimization methods to inform search over potential action sequences. We propose to formulate the problem holistically as a 1st-order logic extension of a mathematical program: a non-linear constrained program over the full world trajectory where the symbolic state-action sequence defines the (in-)equality constraints. We tackle the challenge of solving such programs by proposing three levels of approximation: The coarsest level introduces the concept of the effective end state kinematics, parametrically describing all possible end state configurations conditional to a given symbolic action sequence. Optimization on this level is fast and can inform symbolic search. The other two levels optimize over interaction keyframes and eventually over the full world trajectory across interactions. We demonstrate the approach on a problem of maximizing the height of a physically stable construction from an assortment of boards, cylinders and blocks.

We consider problems of sequential robot manipulation (aka. combined task and motion planning) where the objective is primarily given in terms of a cost function over the final geometric state, rather than a symbolic goal description. In this case we should leverage optimization methods to inform search over potential action sequences. We propose to formulate the problem holistically as a 1st-order logic extension of a mathematical program: a non-linear constrained program over the full world trajectory where the symbolic state-action sequence defines the (in-)equality constraints. We tackle the challenge of solving such programs by proposing three levels of approximation: The coarsest level introduces the concept of the effective end state kinematics, parametrically describing all possible end state configurations conditional to a given symbolic action sequence. Optimization on this level is fast and can inform symbolic search. The other two levels optimize over interaction keyframes and eventually over the full world trajectory across interactions. We demonstrate the approach on a problem of maximizing the height of a physically stable construction from an assortment of boards, cylinders and blocks.