Share This Author
Challenges in Data-to-Document Generation
A new, large-scale corpus of data records paired with descriptive documents is introduced, a series of extractive evaluation methods for analyzing performance are proposed, and baseline results are obtained using current neural generation methods.
An introduction to unification-based approaches to grammar
- S. Shieber
This book surveys the important concept of unification as it relates to linguistic theory and, in particular, to Functional Unification Grammar, Definite-Clause Grammars, Lexical-Function Grammar,…
Ellipsis and higher-order unification
A new method for characterizing the interpretive possibilities generated by elliptical constructions in natural language, which predicts correctly a wide range of interactions between ellipsis and other semantic phenomena such as quantifier scope and bound anaphora.
An empirical study of algorithms for point-feature label placement
This paper proposes two new methods for point-feature label placement, one based on a discrete form of gradient descent, the other on simulated annealing, and reports on a series of empirical tests comparing these and the other known algorithms for the problem.
A new genetic platform for direct cloning and broad-host-range heterologous expression of BGCs in Gram-negative proteobacterial expression hosts is introduced, and the assumption that host phylogeny is an accurate predictor of host compatibility is challenged.
Evidence against the context-freeness of natural language
- S. Shieber
- Linguistics, Computer Science
- 1 August 1985
In searching for universal constraints on the class of natural languages, linguists have investigated a number of formal properties, including that of context-freeness, which is interpreted strongly and weakly both as a way of characterizing structure sets and even weakly for characterizing string sets.
Prolog and Natural-Language Analysis
From the Publisher: A concise and practical introduction to logic programming and the logic-programming language Prolog, both as vehicles for understanding elementary computational linguistics and…
Learning Global Features for Coreference Resolution
RNNs are proposed to be used to learn latent, global representations of entity clusters directly from their mentions, which are especially useful for the prediction of pronominal mentions, and can be incorporated into an end-to-end coreference system that outperforms the state of the art without requiring any additional search.
Design galleries: a general approach to setting parameters for computer graphics and animation
This paper describes the use of DG interfaces for several parameter-setting problems: light selection and placement for image rendering, both standard and image-based; opacity and color transfer-function specification for volume rendering; and motion control for particle-system and articulated-figure animation.