An essay about mimicking some aspects of language processing in our heads, using information fusion and competing patterns.

We propose NEURAL ENQUIRER — a neural network architecture for answering natural language (NL) questions given a knowledge base (KB) table. Unlike previous work on end-to-end training of semantic parsers, NEURAL ENQUIRER is fully “neuralized”: it gives distributed representations of queries and KB tables, and executes queries through a series of differentiable operations. The model can be train...

Active learning reduces the amount of manually annotated sentences necessary when training state-ofthe-art statistical parsers. One popular method, uncertainty sampling, selects sentences for which the parser exhibits low certainty. However, this method does not quantify confidence about the current statistical model itself. In particular, we should be less confident about selection decisions b...

We describe a corpus-based approach to natural language generation (NLG). The approach has been implemented as a component of a spoken dialog system and a series of evaluations were carried out. Our system uses n-gram language models, which have been found useful in other language technology applications, in a generative mode. It is not yet clear whether the simple n-grams can adequately model ...

For a cognitive account of reasoning it is useful to factor out the syntactic aspect — the aspect that has to do with pattern matching and simple substitution — from the rest. The calculus of monotonicity, alias the calculus of natural logic, does precisely this, for it is a calculus of appropriate substitutions at marked positions in syntactic structures. We first introduce the semantic and th...