Papers by Ted Briscoe

5 papers
Neural Automated Essay Scoring and Coherence Modeling for Adversarially Crafted Input (N18-1)

Copied to clipboard

Challenge: Existing approaches to Automated Essay Scoring (AES) are not well-suited to capture adversarially crafted input of grammatical but incoherent sequences of sentences.
Approach: They propose a neural model of local coherence that can effectively learn connectedness features between sentences.
Outcome: The proposed approach strengthens the validity of neural essay scoring models.
PeerQA: A Scientific Question Answering Dataset from Peer Reviews (2025.naacl-long)

Copied to clipboard

Challenge: a dataset of 579 QA pairs from 208 scientific articles contains answers that reviewers raised while thoroughly examining the scientific article.
Approach: They propose a dataset that contains questions that reviewers raised while thoroughly examining the scientific article.
Outcome: The proposed dataset contains 579 QA pairs from 208 academic articles . the results show that decontextualization approaches improve retrieval performance .
The Good, the Bad and the Constructive: Automatically Measuring Peer Review’s Utility for Authors (2025.emnlp-main)

Copied to clipboard

Challenge: Providing constructive feedback to authors is a core component of peer review . authors lack guidance on how to improve their review, a problem that is often overlooked .
Approach: They use a RevUtil dataset to benchmark fine-tuned models for assessing review comments . they find that machine-generated reviews generally underperform human reviews on these aspects .
Outcome: The proposed model outperforms closed models on four aspects of review comments . the proposed model achieves agreement levels comparable to and exceeding those of human models .
Which Word Orders Facilitate Length Generalization in LMs? An Investigation with GCG-Based Artificial Languages (2025.emnlp-main)

Copied to clipboard

Challenge: Whether language models have inductive biases favoring typologically frequent grammatical properties over rare, implausible ones has been investigated, typically using artificial languages (ALs).
Approach: They extend their context-free AL formalization by adopting Generalized Categorial Grammar (GCG) . they also examine the generalization ability of LMs to process unseen longer test sentences .
Outcome: The proposed models better capture features of natural languages and can process unseen longer test sentences.
Automatic learner summary assessment for reading comprehension (N19-1)

Copied to clipboard

Challenge: Summarization is a well-established method of measuring reading proficiency in traditional English as a second or other language assessments.
Approach: They propose three approaches to automatically assess learner summary for evaluating non-native reading comprehension using a summarization task and a long-term memory model.
Outcome: The proposed models outperform traditional methods and produce quality assessments close to professional examiners.

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