Papers by Chris Quirk

8 papers
Multilingual Whispers: Generating Paraphrases with Translation (D19-55)

Copied to clipboard

Challenge: Humans naturally paraphrase, but they can generate approximately the same meaning with a different surface realization.
Approach: They compare translation-based paraphrase gathering using human, automatic, or hybrid techniques to monolingual paraphrasing by experts and non-experts.
Outcome: The proposed methods outperform human translation systems in a variety of translation tasks.
Microsoft Icecaps: An Open-Source Toolkit for Conversation Modeling (P19-3)

Copied to clipboard

Challenge: upcoming open-source natural language processing repository aims to train conversational agents for multi-turn situations.
Approach: They present the Intelligent Conversation Engine: Code and Pre-trained Systems (ICECAPS) the framework wraps TensorFlow functionality in a modular component-based architecture.
Outcome: The Intelligent Conversation Engine: Code and Pre-trained Systems (ICECAPS) is an open-source natural language processing repository.
When does text prediction benefit from additional context? An exploration of contextual signals for chat and email messages (2021.naacl-industry)

Copied to clipboard

Challenge: Prior-message context provides the greatest lift in Teams (chat) scenario.
Approach: They compare prior-message context with email and chat messages from Microsoft Teams and Outlook.
Outcome: The proposed model outperforms existing models on two of the largest commercial communication platforms: Microsoft Teams and Outlook.
Probing Factually Grounded Content Transfer with Factual Ablation (2022.findings-acl)

Copied to clipboard

Challenge: Despite recent success, large neural models often generate factually incorrect text . lack of a standard evaluation for factuality complicates factual grounded generation .
Approach: They propose a method to measure factual consistency by presenting two evaluation sets . large pretrained models have shown impressive effectiveness at longstanding tasks .
Outcome: The proposed method improves over strong baselines by presenting two evaluation sets.
Towards Content Transfer through Grounded Text Generation (N19-1)

Copied to clipboard

Challenge: Recent work in neural natural language generation has attracted significant interest in controlling the form of text, such as style, persona, and wordiness.
Approach: They propose a task where the task is to generate a next sentence in a document that fits its context and is grounded in . external textual source such as a news story.
Outcome: The proposed task is based on 640k Wikipedia referenced sentences paired with the source articles to show significant improvements against baselines.
SimulatorArena: Are User Simulators Reliable Proxies for Multi-Turn Evaluation of AI Assistants? (2025.emnlp-main)

Copied to clipboard

Challenge: Large language models (LLMs) are increasingly used in interactive applications, and human evaluation remains the gold standard for assessing their performance in multi-turn conversations.
Approach: They propose to use large language models to simulate users for automatic assistant evaluation.
Outcome: The proposed model outperforms human evaluations on two interactive tasks and achieves Spearman’s of 0.7 on both tasks.
Confidence Modeling for Neural Semantic Parsing (P18-1)

Copied to clipboard

Challenge: Experimental results show that neural semantic parsers are difficult to interpret due to their complexity.
Approach: They propose to use confidence models to estimate predictions for neural semantic parsers . they outline three major causes of uncertainty and use metrics to quantify them .
Outcome: The proposed model outperforms a widely used method that relies on posterior probability and improves interpretation quality.
Text Editing by Command (2021.naacl-main)

Copied to clipboard

Challenge: Recent work has focused on making such models more controllable and factually grounded.
Approach: They propose a novel interactive text generation setting in which the user interacts with the system by issuing commands to edit existing text.
Outcome: The proposed model outperforms baseline models and obtains positive results in automatic and human evaluations.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations