Paper Reviews

Topics

Here is a tentative list of topics that I personally interested in NLP filed.  If you so, please scroll down for a list of papers and click the title for detail commentary I wrote. 

1. Language Modeling 

2. Creative Text Generation

3. Text understanding

4. Natural Language Reasoning

5. Multi-modal NLP

6. Dialogue systems

7. Fairness and bias in NLP

8. Large Languae Models

Contents(Last update: Mar. 20th, 2024)

Creative Text Generation

1. Vaswani, Shazeer, Parmar, Uszkoreit, Jones, Gomez, Kaiser, and Polosukhin, 2017. Attention is all you need. NIPS.

2. Yao, Peng, Weischedel, Knight, Zhao and Yan, 2019. Plan-And-Write: Towards Better Automatic Storytelling. AAAI.

3. Goldfarb-Tarrant, S., Feng, H. and Peng, N., 2019. Plan, Write, and Revise: an Interactive System for Open-Domain Story Generation. arXiv

4. McIntyre, and Lapata, 2010. Plot induction and evolutionary search for story generation. ACL.

5. Xu , Ren , Zhang , Zeng , Cai, and Sun, 2018. A Skeleton-Based Model for Promoting Coherence Among Sentences in Narrative Story Generation. EMNLP.

6. Harrison and Walker, 2018. Neural Generation of Diverse Questions using Answer Focus, Contextual and Linguistic Features. INLG.

7. Hajdik, V., Buys, J., Goodman, M.W. and Bender, E.M., 2019. Neural Text Generation from Rich Semantic Representations. NAACL.

8. Iyyer, M., Wieting, J., Gimpel, K. and Zettlemoyer, L., 2018, June. Adversarial Example Generation with Syntactically Controlled Paraphrase Networks. NAACL.

9. Sheng Shen, Daniel Fried, Jacob Andreas, Dan Klein, 2019. Pragmatically Informative Text Generation. NAACL 2019

10. Amit Moryossef, Yoav Goldberg, Ido Dagan, 2019. Step-by-Step: Separating Planning from Realization in Neural Data-to-Text Generation, NAACL 2019

11. Wiseman, S., Shieber, S. and Rush, A., 2018. Learning Neural Templates for Text Generation. EMNLP

12. Ari Holtzman, Jan Buys, Maxwell Forbes, Antoine Bosselut, David Golub, Yejin Choi, 2018. Learning to Write with Cooperative Discriminators. ACL 2018

Character-centric Narrative understanding

1. Iyyer, Guha, Chaturvedi, Boyd-Graber, Daume III, 2016. Feuding Families and Former Friends: Unsupervised Learning for Dynamic Fictional Relationships. NAACL.

2. Bamman, Underwood and Smith, 2014. A Bayesian Mixed Effects Model of Literary Character. ACL.

3. Chaturvedi, Srivastava, and Roth, 2018. Where Have I Heard This Story Before? Identifying Narrative Similarity in Movie Remakes.NAACL-HLT.

4. Roemmele and Gordon, 2018. An Encoder-decoder Approach to Predicting Causal Relations in Stories. NAACL Workshop on Storytelling.

5. Chaturvedi, Peng, and Roth, 2017. Story Comprehension for Predicting What Happens Next. EMNLP 2017

6. Elizabeth Clark, Yangfeng Ji, Noah A. Smith, 2018 Neural Text Generation in Stories Using Entity Representations as Context. NAACL 2018

Event-centric text understanding(Scripts, plot-units, etc.)

1. Chambers and Jurafsky, 2008. Unsupervised Learning of Narrative Event Chains. ACL.

2. Chambers and Jurafsky, 2009. Unsupervised Learning of Narrative Schemas and their Participants. ACL.

3. Chambers, 2013. Event Schema Induction with a Probabilistic Entity-Driven Model. EMNLP. 

4. Pichotta and Mooney, 2016. Learning Statistical Scripts with LSTM Recurrent Neural Networks. AAAI.

5. Peng and Roth, 2016. Two Discourse Driven Language Models for Semantics. ACL.

Multi-modal NLP

1. Iyyer, Manjunatha, Guha, Vyas, Boyd-Graber, Daumé III, and Davis, 2017. The Amazing Mysteries of the Gutter: Drawing Inferences Between Panels in Comic Book Narratives. CVPR.

2. Gillick and Bamman, 2018. Telling Stories with Soundtracks: An Empirical Analysis of Music in Film. First Workshop on Storytelling NAACL.

3. González-Rico and Fuentes-Pineda, 2018. Contextualize, Show and Tell: A Neural Visual Storyteller. First Workshop on Storytelling NAACL.

Stylistic Transfer

1. Oraby, Reed, Tandon, Sharath, Lukin and Walker, 2018, July. Controlling Personality-Based Stylistic Variation with Neural Natural Language Generators. ACL.

2. Wang, Y.C., Wang, R., Tur, G. and Williams, H., Can You be More Polite and Positive? Infusing Social Language into Task-Oriented Conversational Agents.

3. Niu, T. and Bansal, M., 2018. Polite Dialogue Generation Without Parallel Data. ACL.

NLP Dataset

1. Rao, S. and Tetreault, J., 2018, June. Dear Sir or Madam, May I Introduce the GYAFC Dataset: Corpus, Benchmarks and Metrics for Formality Style Transfer. NAACL.

2. Kolhatkar, V., Wu, H., Cavasso, L., Francis, E., Shukla, K. and Taboada, M., 2018. The sfu opinion and comments corpus: A corpus for the analysis of online news comments.

3. Trischler, A., Wang, T., Yuan, X., Harris, J., Sordoni, A., Bachman, P. and Suleman, K., 2017. NewsQA: A Machine Comprehension Dataset. ACL.

4. Novikova, J., Dušek, O. and Rieser, V., 2017, August. The E2E Dataset: New Challenges For End-to-End Generation. ACL.

5. S. Oraby, V. Harrison, A. Ebrahimi, and M. Walker. 2019Curate and Generate: A Corpus and Method for Joint Control of Semantics and Style in Neural NLG. 

Other

1. Sutskever, Ilya, Oriol Vinyals, and Quoc V. Le. 2014. Sequence to sequence learning with neural networks. NIPS.

2. Langkilde, I. and Knight, K., 1998, August. Generation that exploits corpus-based statistical knowledge. ACM.

3. Di Fabbrizio, G., Stent, A. and Gaizauskas, R., 2014, June. A hybrid approach to multi-document summarization of opinions in reviews. INLG.

4. Cervone, A., Khatri, C., Goel, R., Hedayatnia, B., Venkatesh, A., Hakkani-Tur, D. and Gabriel, R., 2019. Natural Language Generation at Scale: A Case Study for Open Domain Question Answering. arXiv

5. Young, T., Cambria, E., Chaturvedi, I., Zhou, H., Biswas, S. and Huang, M., 2018, April. Augmenting end-to-end dialogue systems with commonsense knowledge.AAAI.