Ian Perera


2023

pdf bib
Detoxifying Online Discourse: A Guided Response Generation Approach for Reducing Toxicity in User-Generated Text
Ritwik Bose | Ian Perera | Bonnie Dorr
Proceedings of the First Workshop on Social Influence in Conversations (SICon 2023)

The expression of opinions, stances, and moral foundations on social media often coincide with toxic, divisive, or inflammatory language that can make constructive discourse across communities difficult. Natural language generation methods could provide a means to reframe or reword such expressions in a way that fosters more civil discourse, yet current Large Language Model (LLM) methods tend towards language that is too generic or formal to seem authentic for social media discussions. We present preliminary work on training LLMs to maintain authenticity while presenting a community’s ideas and values in a constructive, non-toxic manner.

2018

pdf bib
Building and Learning Structures in a Situated Blocks World Through Deep Language Understanding
Ian Perera | James Allen | Choh Man Teng | Lucian Galescu
Proceedings of the First International Workshop on Spatial Language Understanding

We demonstrate a system for understanding natural language utterances for structure description and placement in a situated blocks world context. By relying on a rich, domain-specific adaptation of a generic ontology and a logical form structure produced by a semantic parser, we obviate the need for an intermediate, domain-specific representation and can produce a reasoner that grounds and reasons over concepts and constraints with real-valued data. This linguistic base enables more flexibility in interpreting natural language expressions invoking intrinsic concepts and features of structures and space. We demonstrate some of the capabilities of a system grounded in deep language understanding and present initial results in a structure learning task.

pdf
A Situated Dialogue System for Learning Structural Concepts in Blocks World
Ian Perera | James Allen | Choh Man Teng | Lucian Galescu
Proceedings of the 19th Annual SIGdial Meeting on Discourse and Dialogue

We present a modular, end-to-end dialogue system for a situated agent to address a multimodal, natural language dialogue task in which the agent learns complex representations of block structure classes through assertions, demonstrations, and questioning. The concept to learn is provided to the user through a set of positive and negative visual examples, from which the user determines the underlying constraints to be provided to the system in natural language. The system in turn asks questions about demonstrated examples and simulates new examples to check its knowledge and verify the user’s description is complete. We find that this task is non-trivial for users and generates natural language that is varied yet understood by our deep language understanding architecture.

pdf
Cogent: A Generic Dialogue System Shell Based on a Collaborative Problem Solving Model
Lucian Galescu | Choh Man Teng | James Allen | Ian Perera
Proceedings of the 19th Annual SIGdial Meeting on Discourse and Dialogue

The bulk of current research in dialogue systems is focused on fairly simple task models, primarily state-based. Progress on developing dialogue systems for more complex tasks has been limited by the lack generic toolkits to build from. In this paper we report on our development from the ground up of a new dialogue model based on collaborative problem solving. We implemented the model in a dialogue system shell (Cogent) that al-lows developers to plug in problem-solving agents to create dialogue systems in new domains. The Cogent shell has now been used by several independent teams of researchers to develop dialogue systems in different domains, with varied lexicons and interaction style, each with their own problem-solving back-end. We believe this to be the first practical demonstration of the feasibility of a CPS-based dialogue system shell.

2015

pdf
Quantity, Contrast, and Convention in Cross-Situated Language Comprehension
Ian Perera | James Allen
Proceedings of the Nineteenth Conference on Computational Natural Language Learning