• Publications
  • Influence
Identifying the Discourse Function of News Article Paragraphs
This work applied the hierarchical theory of news discourse developed by van Dijk to examine how paragraphs operate as units of discourse structure within news articles to generate a gold-standard, adjudicated corpus of 50 documents for document-level discourse annotation based on the ACE Phase 2 corpus.
Dynamic and Probabilistic CP-nets
In this paper we present a two-fold generalization of conditional preference networks (CP-nets) that incorporates uncertainty. CPnets are a formal tool to model qualitative conditional preference
Updates and Uncertainty in CP-Nets
This paper presents and study a generalization of CP-nets which supports changes and allows for encoding uncertainty, expressed in probabilistic terms, over the structure of the dependency links and over the individual preference relations.
Reasoning with PCP-nets in a Multi-Agent Context
This paper uses PCP-nets in a multi-agent context to compactly represent a collection of CP-nets, thus using probabilistic uncertainty to reconcile possibly conflicting qualitative preferences expressed by a group of agents.
Symbolic Regression using Mixed-Integer Nonlinear Optimization
Tyler Josephson and Lior Horesh gratefully acknowledge the support of the Institute for Mathematics and its Applications (IMA), where a part of this work was initiated.
Question Answering over Knowledge Bases by Leveraging Semantic Parsing and Neuro-Symbolic Reasoning
A semantic parsing and reasoning-based Neuro-Symbolic Question Answering system that achieves state-of-the-art performance on QALD-9 and LC-QuAD 1.0 and integrates multiple, reusable modules that are trained specifically for their individual tasks and do not require end-to-end training data.
Improving Graph Neural Network Representations of Logical Formulae with Subgraph Pooling
This work proposes a novel approach for embedding logical formulae that is designed to overcome the representational limitations of prior approaches and achieves state-of-the-art performance on both premise selection and proof step classification.
Leveraging Abstract Meaning Representation for Knowledge Base Question Answering
Neuro-Symbolic Question Answering (NSQA) is proposed, a modular KBQA system that leverages Abstract Meaning Representation (AMR) parses for task-independent question understanding and achieves state-of-the-art performance on two prominentKBQA datasets based on DBpedia.
Multi-agent soft constraint aggregation via sequential voting: theoretical and experimental results
The experimental study shows that the proposed sequential procedure yields a considerable saving in time with respect to a non-sequential approach, while the winners satisfy the agents just as well, independently of the variable ordering, and of the presence of coalitions of agents.
Voting with CP-nets using a Probabilistic Preference Structure
Probabilistic conditional preference networks (PCP-nets) provide a compact representation of a probability distribution over a collection of CP-nets. In this paper we view a PCP-net as the result of