Larry Birnbaum

AAMAS Conference 2025 Conference Paper

Selecting Interlacing Committees

• Chris Dong
• Martin Bullinger
• Tomasz Was
• Larry Birnbaum
• Edith Elkind

Polarization is a major concern for a well-functioning society. Often, mass polarization of a society is driven by polarizing political representation, even when the latter is easily preventable. The existing computational social choice methods for the task of committee selection are not designed to address this issue. We enrich the standard approach to committee selection by defining two quantitative measures that evaluate how well a given committee interconnects the voters. Maximizing these measures aims at avoiding polarizing committees. While the corresponding maximization problems are NP-complete in general, we obtain efficient algorithms for profiles in the voter-candidate interval domain. Moreover, we analyze the compatibility of our goals with other representation objectives, such as excellence, diversity, and proportionality. We identify tradeoffs between approximation guarantees, and describe algorithms that achieve simultaneous constant-factor approximations.

AAAI Conference 2017 Conference Paper

Definition Modeling: Learning to Define Word Embeddings in Natural Language

• Thanapon Noraset
• Chen Liang
• Larry Birnbaum
• Doug Downey

Distributed representations of words have been shown to capture lexical semantics, as demonstrated by their effectiveness in word similarity and analogical relation tasks. But, these tasks only evaluate lexical semantics indirectly. In this paper, we study whether it is possible to utilize distributed representations to generate dictionary definitions of words, as a more direct and transparent representation of the embeddings’ semantics. We introduce definition modeling, the task of generating a definition for a given word and its embedding. We present several definition model architectures based on recurrent neural networks, and experiment with the models over multiple data sets. Our results show that a model that controls dependencies between the word being defined and the definition words performs significantly better, and that a characterlevel convolution layer designed to leverage morphology can complement word-level embeddings. Finally, an error analysis suggests that the errors made by a definition model may provide insight into the shortcomings of word embeddings.

EAAI Journal 1999 Journal Article

Integrating diverse information resources in a case-based design environment

• David B Leake
• Larry Birnbaum
• Kristian Hammond
• Cameron Marlow
• Hao Yang

The success of case-based design aids depends both on the case-based reasoning processes they apply and on effectively integrating those processes into the larger task context: on making the case-based reasoning component present case information at the right time and in the right way, on exploiting additional information resources as needed to supplement the case library and to guide case application, on capturing useful information from current reasoning and providing it to up- and down-stream designers, and on unobtrusively learning new cases during the design process. This article presents a set of principles and techniques for integrated case-based design support systems and illustrates their application through a case study of the Stamping Advisor, a system to support feasibility analysis for sheet metal automotive parts.

IJCAI Conference 1995 Conference Paper

Determining what to learn through component-task modeling

• Bruce Krulwich
• Larry Birnbaum
• Gregg Collins