Kristina Striegnitz

Generation as Dependency Parsing

Natural-Language Generation from flat semantics is an NP-complete problem. This makes it necessary to develop algorithms that run with reasonable efficiency in practice despite the high worst-case complexity. We show how to convert TAG generation problems into dependency parsing problems, which is useful because optimizations in recent dependency parsers based on constraint programming tackle exactly the combinatorics that make generation hard. Indeed, initial experiments display promising runtimes.

The first challenge on generating instructions in virtual environments

This paper describes the First Challenge on Generating Instructions in Virtual Environments (GIVE-1). GIVE is a shared task for generation systems which give real-time natural-language instructions to users in a virtual 3D world. These systems are evaluated by connecting users and NLG systems over the Internet. We describe the design and results of GIVE-1 as well as the participating NLG systems, and validate the experimental methodology by comparing the results collected over the Internet with results from a more traditional laboratory-based experiment.

Referring expressions as formulas of description logic

In this paper, we propose to reinterpret the problem of generating referring expressions (GRE) as the problem of computing a formula in a description logic that is only satisfied by the referent. This view offers a new unifying perspective under which existing GRE algorithms can be compared. We also show that by applying existing algorithms for computing simulation classes in description logic, we can obtain extremely efficient algorithms for relational referring expressions without any danger of running into infinite regress.

Report on the First NLG Challenge on Generating Instructions in Virtual Environments (GIVE)

We describe the first installment of the Challenge on Generating Instructions in Virtual Environments (GIVE), a new shared task for the NLG community. We motivate the design of the challenge, describe how we carried it out, and discuss the results of the system evaluation.

Generating Instructions in Virtual Environments (GIVE):A Challenge and an Evaluation Testbed for NLG

Would it be helpful or detrimental for the field of NLG to have a generally accepted competition? Competitions have definitely advanced the state of the art in some fields of NLP, but the benefits sometimes come at the price of over-competitiveness, and there is a danger of overfitting systems to the concrete evaluation metrics. Moreover, it has been argued that there are intrinsic difficulties in NLG that make it harder to evaluate than other NLP tasks (Scott and Moore, 2006). We agree that NLG is too diverse for a single “competition”, and there are no mutually accepted evaluation metrics. Instead, we suggest that all the positive aspects, and only a few of the negative ones, can be achieved by putting forth a challenge to the community. Research teams would implement systems that address various aspects of the challenge. These systems would then be evaluated regularly, and the results compared at a workshop. There would be no “winner” in the sense of a competition; rather, the focus should be on learning what works and what doesn’t, building upon the best ideas, and perhaps reusing the best modules for next year’s round. As a side effect, the exercise should result in a growing body of shareable tools and modules.

Put My Galakmid Coin into the Dispenser and Kick It: Computational Linguistics and Theorem Proving in a Computer Game

We combine state-of-the-art techniques from computational linguisticsand theorem proving to build an engine for playing text adventures,computer games with which the player interacts purely through naturallanguage. The system employs a parser for dependency grammar and ageneration system based on TAG, and has components for resolving andgenerating referring expressions. Most of these modules make heavy useof inferences offered by a modern theorem prover for descriptionlogic. Our game engine solves some problems inherent in classical textadventures, and is an interesting test case for the interactionbetween natural language processing and inference.

Validating the web-based evaluation of NLG systems

The GIVE Challenge is a recent shared task in which NLG systems are evaluated over the Internet. In this paper, we validate this novel NLG evaluation methodology by comparing the Internet-based results with results we collected in a lab experiment. We find that the results delivered by both methods are consistent, but the Internet-based approach offers the statistical power necessary for more fine-grained evaluations and is cheaper to carry out.

Neuropsychological Benefits of Neuro-exergaming for Older Adults: A Pilot Study of an Interactive Physical and Cognitive Exercise System (iPACES™).

Dementia cases are on the rise and researchers seek innovative ways to prevent or ameliorate cognitive impairment in later life. Some research has reported that combining mental and physical exercise may benefit cognition more than either alone. This randomized pilot trial examined the feasibility and cognitive benefit for older adults (n = 30) of a single bout of neuro-exergaming (physical activity with cognitive training) using an interactive physical and cognitive exercise system (iPACES), compared with that of exergaming or neurogaming alone. Intent-to-treat and sensitivity analyses were conducted using repeated-measures ANOVA, controlling for age, sex, and education. A significant interaction effect was found for executive function (Color Trails 2), with a significant improvement in the neuro-exergaming condition. Results demonstrate feasibility for older adults to use a novel and theoretically-derived neuro-exergame, and also provide promising new evidence that neuro-exergaming can yield greater cognitive benefit than either of its component parts.

GENERATING BRIDGING DEFINITE DESCRIPTIONS

In this paper, we focus on the role knowledge based reasoning plays in the generation of definite descriptions. Specifically, we propose an extension of Dale and Reiters incremental algorithm which covers not only directly anaphoric descriptions but also indirect and associative anaphora. Starting from a formalism independent algorithm, we further show how this algorithm can be implemented using description logic.

The Software Architecture for the First Challenge on Generating Instructions in Virtual Environments

The GIVE Challenge is a new Internet-based evaluation effort for natural language generation systems. In this paper, we motivate and describe the software infrastructure that we developed to support this challenge.