publications

2019

1. Variance of average surprisal: a better predictor for quality of grammar from unsupervised PCFG induction Jin, Lifeng, and Schuler, William In ACL 2019 [Preprint]
2. Unsupervised Learning of PCFGs with Normalizing Flow Jin, Lifeng, Doshi-Velez, Finale, Miller, Timothy, Schwartz, Lane, and Schuler, William In ACL 2019 [Preprint]
3. Using Virtual Standardized Patients to Accurately Assess Information Gathering Skills in Medical Students Maicher, Kellen, Zimmerman, Laura, Wilcox, Bruce, Liston, Beth, Cronau, Holly, Macerollo, Allison, Jin, Lifeng, Jaffe, Evan, White, Michael, Fosler-Lussier, Eric, Schuler, William, Way, David, and Danforth, Douglas Medical Teacher 2019

2018

1. Depth-bounding is effective: Improvements and evaluation of unsupervised PCFG induction Jin, Lifeng, Doshi-Velez, Finale, Miller, Timothy A, Schuler, William, and Schwartz, Lane In EMNLP 2018 [PDF]
2. Unsupervised Grammar Induction with Depth-bounded PCFG Jin, Lifeng, Schuler, William, Doshi-Velez, Finale, Miller, Timothy A, and Schwartz, Lane Transactions of the Association for Computational Linguistics (TACL) 2018 [Abs]

   There has been recent interest in applying cognitively or empirically motivated bounds on recursion depth to limit the search space of grammar induction models (Ponvert et al., 2011; Noji and Johnson, 2016; Shain et al., 2016). This work extends this depth-bounding approach to probabilistic context-free grammar induction (DB-PCFG), which has a smaller parameter space than hierarchic sequence models, and therefore more fully exploits the space reductions of depth-bounding. Results for this model on grammar acquisition from transcribed child-directed speech exceed those of other models when evaluated on parse accuracy. Moreover, grammars acquired from this model demonstrate a consistent use of category labels, something which has not been demonstrated by other acquisition models.

3. Using Paraphrasing and Memory-Augmented Models to Combat Data Sparsity in Question Interpretation with a Virtual Patient Dialogue System Jin, Lifeng, King, David, Hussein, Amad, White, Michael, and Danforth, Douglas In Proceedings of the 13th Workshop on Innovative Use of NLP for Building Educational Applications 2018 [Abs]

   When interpreting questions in a virtual patient dialogue system, one must inevitably tackle the challenge of a long tail of relatively infrequently asked questions. To make progress on this challenge, we investigate the use of paraphrasing for data augmentation and neural memory-based classification, finding that the two methods work best in combination. In particular, we find that the neural memory-based approach not only outperforms a straight CNN classifier on low frequency questions, but also takes better advantage of the augmented data created by paraphrasing, together yielding a nearly 10% absolute improvement in accuracy on the least frequently asked questions.

2017

1. Modeling syntax acquisition via cognitively-constrained unsupervised grammar induction Shain, Cory, Bryce, William, Jin, Lifeng, Krakovna, Victoria, Doshi-Velez, Finale, Miller, Timothy, Schuler, William, and Schwartz, Lane In CUNY 2017 2017
2. Combining CNNs and Pattern Matching for Question Interpretation in a Virtual Patient Dialogue System Jin, Lifeng, White, Michael, Jaffe, Evan, Zimmerman, Laura, and Danforth, Douglas In Proceedings of the 12th Workshop on Innovative Use of NLP for Building Educational Applications 2017

2016

1. Memory-Bounded Left-Corner Unsupervised Grammar Induction on Child-Directed Input Shain, Cory, Bryce, William, Jin, Lifeng, Krakovna, Victoria, Doshi-Velez, Finale, Miller, Timothy, Schuler, William, and Schwartz, Lane In Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers 2016
2. OSU_CHGCG at SemEval-2016 Task 9: Chinese Semantic Dependency Parsing with Generalized Categorial Grammar Duan, Manjuan, Jin, Lifeng, and Schuler, William In Proceedings of the 10th International Workshop on Semantic Evaluation (SemEval-2016) 2016
3. OCLSP at SemEval-2016 Task 9: Multilayered LSTM as a Neural Semantic Dependency Parser Jin, Lifeng, Duan, Manjuan, and Schuler, William In Proceedings of the 10th International Workshop on Semantic Evaluation (SemEval-2016) 2016

2015

1. Recommender System for E-Learning Based on Semantic Relatedness of Concepts Ye, Mao, Tang, Zhi, Xu, Jianbo, and Jin, Lifeng Information 2015
2. AZMAT: Sentence Similarity Using Associative Matrices Jaffe, Evan, Jin, Lifeng, King, David, and Schijndel, Marten In Proceedings of the 9th International Workshop on Semantic Evaluation (SemEval-2015) 2015
3. The Overall Markedness of Discourse Relations Jin, Lifeng, and Marneffe, Marie-Catherine In Conference on Empirical Methods in Natural Language Processing (EMNLP) 2015
4. A Comparison of Word Similarity Performance Using Explanatory and Non-explanatory Texts Jin, Lifeng, and Schuler, William In Proceedings of NAACL-HLT 2015

2014

1. Sentences Extraction from Digital Publication for Domain-Specific Knowledge Service Ye, Mao, Jin, Lifeng, Tang, Zhi, and Xu, Jianbo In Human-Computer Interaction International Conference 2014 2014
2. A Semantic Recommender System for Learning Based on Encyclopedia of Digital Publication Ye, Mao, Jin, Lifeng, Tang, Zhi, and Xu, Jianbo In Human-Computer Interaction International Conference 2014 2014