Papers by John Lee
Personalized Text Retrieval for Learners of Chinese as a Foreign Language (C18-1)
Copied to clipboard
| Challenge: | a personalized text retrieval algorithm helps language learners select the most suitable reading material in terms of vocabulary complexity. |
| Approach: | They propose a personalized text retrieval algorithm that helps language learners select the most suitable reading material in terms of vocabulary complexity. |
| Outcome: | The proposed algorithm is effective in identifying simpler texts for low-proficiency learners, and more challenging ones for high-proficient learners. |
Personalizing Lexical Simplification (C18-1)
Copied to clipboard
| Challenge: | Experimental results show that even a simple personalized CWI model can help the system avoid some unnecessary simplifications and produce more readable output. |
| Approach: | They evaluate the performance of a state-of-the-art LS system on individual learners of English at different proficiency levels and measure the benefits of using complex word identification models to personalize the system. |
| Outcome: | The proposed system produces a more readable output for learners with special needs and those with language disabilities. |
Bayesian Optimization for Controlled Image Editing via LLMs (2025.findings-acl)
Copied to clipboard
Chengkun Cai, Haoliang Liu, Xu Zhao, Zhongyu Jiang, Tianfang Zhang, Zongkai Wu, John Lee, Jenq-Neng Hwang, Lei Li
| Challenge: | achieving precise control over generated content and maintaining semantic consistency remain significant limitations, particularly concerning grounding techniques and the necessity for model fine-tuning. |
| Approach: | They propose an off-the-shelf approach that integrates Large Language Models with Bayesian Optimization to facilitate precise and user-friendly image editing. |
| Outcome: | The proposed approach outperforms existing methods in editing accuracy and semantic preservation, as validated using different LLMs including Claude3 and GPT-4. |
A Dataset for Investigating the Impact of Feedback on Student Revision Outcome (2020.lrec-1)
Copied to clipboard
| Challenge: | Despite numerous studies on the kinds of feedback that can best promote learning, this question remains an open debate in the area of Second Language Acquisition (SLA). |
| Approach: | They annotate a corpus of student-written sentences with teacher feedback provided for the errors. |
| Outcome: | The proposed annotation scheme and the teacher feedback dataset are based on student-written sentences in their original and revised versions with teacher feedback provided for the errors. |
L1-L2 Parallel Treebank of Learner Chinese: Overused and Underused Syntactic Structures (L18-1)
Copied to clipboard
| Challenge: | Currently, the treebank consists of 600 L2 sentences and 697 L1 sentences. |
| Approach: | They propose to use "L1-L2 parallel treebanks" to facilitate analyses of learner language. |
| Outcome: | The proposed treebank consists of 600 L2 sentences and 697 L1 sentences. |
Paraphrasing Compound Nominalizations (2021.emnlp-main)
Copied to clipboard
| Challenge: | Nominalizations are difficult to interpret because of ambiguous semantic relations between deverbal noun and its arguments. |
| Approach: | They propose to generate clausal paraphrases for nominalizations by mapping arguments to verbs . they use a contextualized language model to re-rank nominalization candidates . |
| Outcome: | The proposed task is based on a pre-trained model to re-rank paraphrase candidates identified by a textual entailment model. |
Using Bilingual Patents for Translation Training (2020.coling-main)
Copied to clipboard
| Challenge: | While bilingual corpora have been instrumental for machine translation, their utility for training translators has been understudied. |
| Approach: | They propose to use bilingual corpora to train translators in the technical domain. |
| Outcome: | The proposed method improves translation quality of technical terms by concordance with bilingual examples in the in-domain corpus than with general-domain bilingual corpus. |
Automatic Assistance for Academic Word Usage (2020.coling-main)
Copied to clipboard
| Challenge: | Experimental results show that lexical formality analysis helps improve the quality of substitution suggestions over a number of competitive baselines. |
| Approach: | They propose a system that automatically suggests lexical substitutions that aim to incorporate more academic vocabulary. |
| Outcome: | The proposed system improves the quality of substitution suggestions over a baseline that relies on the masked language model. |
Automatic Compilation of Resources for Academic Writing and Evaluating with Informal Word Identification and Paraphrasing System (2020.lrec-1)
Copied to clipboard
| Challenge: | a systematic review of academic writing aids aims to build a writing aid system that automatically edits a text to adhere to the academic style of writing. |
| Approach: | They propose to build a writing aid system that automatically edits a text to adhere to the academic style of writing. |
| Outcome: | The proposed system outperforms existing academic resources in terms of word identification and ranking . the informal word identification component achieves an F-1 score of 82% . |
Enhancing Automatic Readability Assessment with Pre-training and Soft Labels for Ordinal Regression (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Existing models do not exploit ordinal nature of difficulty grades and make little effort for initialization to facilitate fine-tuning. |
| Approach: | They propose a readability assessment task that assigns a difficulty grade to a text . they use ordinal regression and pairwise relative text difficulty to train the model . |
| Outcome: | The proposed model outperforms competitive neural models and statistical classifiers on most datasets. |
Sleepless Nights, Sugary Days: Creating Synthetic Users with Health Conditions for Realistic Coaching Agent Interactions (2025.findings-acl)
Copied to clipboard
Taedong Yun, Eric Yang, Mustafa Safdari, Jong Ha Lee, Vaishnavi Vinod Kumar, S. Sara Mahdavi, Jonathan Amar, Derek Peyton, Reut Aharony, Andreas Michaelides PhD, Logan Douglas Schneider, Isaac Galatzer-Levy, Yugang Jia, John Canny, Arthur Gretton, Maja Mataric
| Challenge: | Structured data is generated grounded in health and lifestyle factors and full profiles of synthetic users are developed conditioned on the structured data. |
| Approach: | They propose an end-to-end framework for generating synthetic users for evaluating interactive agents designed to encourage positive behavior changes, such as in health and lifestyle coaching. |
| Outcome: | The proposed framework is validated in the domains of sleep and diabetes coaching using two independently-developed agents for sleep and diabetic coaching as case studies. |
A Corpus of Simulated Counselling Sessions with Dialog Act Annotation (2022.lrec-1)
Copied to clipboard
| Challenge: | Consisting of 152K Chinese characters, the corpus labels the dialog act of both client and counsellor utterances and segments each dialog into stages. |
| Approach: | They propose to use a corpus of 152K Chinese characters to model counselling conversations in Cantonese. |
| Outcome: | The proposed corpus can be used for counselling chatbot development and to better understand the characteristics of successful counselling. |
Integrating Question Classification and Deep Learning for improved Answer Selection (C18-1)
Copied to clipboard
| Challenge: | Question Answering (QA) is the task of automatically generating answers to questions posed in natural language. |
| Approach: | They propose a system for Answer Selection that integrates fine-grained Question Classification with a Deep Learning model designed for Answer selection. |
| Outcome: | The proposed system outperforms the current state of the art in all variations except one . the proposed system improves QA by reducing the search space of potential answers . |