Brian McMahan


2020

pdf bib
Analyzing Speaker Strategy in Referential Communication
Brian McMahan | Matthew Stone
Proceedings of the 21th Annual Meeting of the Special Interest Group on Discourse and Dialogue

We analyze a corpus of referential communication through the lens of quantitative models of speaker reasoning. Different models place different emphases on linguistic reasoning and collaborative reasoning. This leads models to make different assessments of the risks and rewards of using specific utterances in specific contexts. By fitting a latent variable model to the corpus, we can exhibit utterances that give systematic evidence of the diverse kinds of reasoning speakers employ, and build integrated models that recognize not only speaker reference but also speaker reasoning.

2016

pdf bib
Syntactic realization with data-driven neural tree grammars
Brian McMahan | Matthew Stone
Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers

A key component in surface realization in natural language generation is to choose concrete syntactic relationships to express a target meaning. We develop a new method for syntactic choice based on learning a stochastic tree grammar in a neural architecture. This framework can exploit state-of-the-art methods for modeling word sequences and generalizing across vocabulary. We also induce embeddings to generalize over elementary tree structures and exploit a tree recurrence over the input structure to model long-distance influences between NLG choices. We evaluate the models on the task of linearizing unannotated dependency trees, documenting the contribution of our modeling techniques to improvements in both accuracy and run time.

2015

pdf bib
A Bayesian Model of Grounded Color Semantics
Brian McMahan | Matthew Stone
Transactions of the Association for Computational Linguistics, Volume 3

Natural language meanings allow speakers to encode important real-world distinctions, but corpora of grounded language use also reveal that speakers categorize the world in different ways and describe situations with different terminology. To learn meanings from data, we therefore need to link underlying representations of meaning to models of speaker judgment and speaker choice. This paper describes a new approach to this problem: we model variability through uncertainty in categorization boundaries and distributions over preferred vocabulary. We apply the approach to a large data set of color descriptions, where statistical evaluation documents its accuracy. The results are available as a Lexicon of Uncertain Color Standards (LUX), which supports future efforts in grounded language understanding and generation by probabilistically mapping 829 English color descriptions to potentially context-sensitive regions in HSV color space.

2013

pdf bib
Training an integrated sentence planner on user dialogue
Brian McMahan | Matthew Stone
Proceedings of the SIGDIAL 2013 Conference