| Exploiting Document Knowledge For Aspect-Level Sentiment Classification | 4 | 0.38 | 2018 |
| Adaptive Semi-supervised Learning for Cross-domain Sentiment Classification. | 0 | 0.34 | 2018 |
| Effective Attention Modeling for Aspect-Level Sentiment Classification. | 7 | 0.39 | 2018 |
| Memory networks for fine-grained opinion mining. | 1 | 0.37 | 2018 |
| An Unsupervised Neural Attention Model For Aspect Extraction | 32 | 1.49 | 2017 |
| On The Challenges Of Translating Nlp Research Into Commercial Products | 0 | 0.34 | 2017 |
| Character-Based Text Classification using Top Down Semantic Model for Sentence Representation. | 1 | 0.35 | 2017 |
| Multi-task Coupled Attentions for Category-specific Aspect and Opinion Terms Co-extraction. | 1 | 0.34 | 2017 |
| Coupled Multi-Layer Attentions for Co-Extraction of Aspect and Opinion Terms. | 11 | 0.48 | 2017 |
| Power-saving transportation mode identification for large-scale applications. | 1 | 0.38 | 2017 |
| Inferring Activities and Optimal Trips: Lessons From Singapore's National Science Experiment. | 0 | 0.34 | 2016 |
| Recursive Neural Conditional Random Fields for Aspect-based Sentiment Analysis. | 23 | 0.72 | 2016 |
| Learning the Peculiar Value of Actions | 0 | 0.34 | 2014 |
| SAP-RI: A Constrained and Supervised Approach for Aspect-Based Sentiment Analysis | 0 | 0.34 | 2014 |
| Not So Unique in the Crowd: a Simple and Effective Algorithm for Anonymizing Location Data. | 0 | 0.34 | 2014 |
| Part-of-Speech is (almost) enough: SAP Research & Innovation at the #Microposts2014 NEEL Challenge. | 0 | 0.34 | 2014 |
| SAP-RI: Twitter Sentiment Analysis in Two Days | 0 | 0.34 | 2014 |
| A Biclustering-Based Classification Framework for Microarray Analysis. | 1 | 0.35 | 2014 |
| Part-of-Speech is (almost) enough: SAP Research & Innovation at the #Microposts2014 NEEL Challenge. | 0 | 0.34 | 2014 |
| Building a Large Annotated Corpus of Learner English: The NUS Corpus of Learner English. | 0 | 0.34 | 2013 |
| Building a Large Annotated Corpus of Learner English: The NUS Corpus of Learner English | 86 | 3.44 | 2013 |
| NUS at the HOO 2012 shared task | 5 | 0.44 | 2012 |
| NUS at the HOO 2012 Shared Task. | 0 | 0.34 | 2012 |
| A beam-search decoder for grammatical error correction | 18 | 0.84 | 2012 |
| A Beam-Search Decoder for Grammatical Error Correction | 0 | 0.34 | 2012 |
| Better evaluation for grammatical error correction | 73 | 3.91 | 2012 |
| Grammatical error correction with alternating structure optimization | 44 | 1.65 | 2011 |
| Correcting semantic collocation errors with L1-induced paraphrases | 28 | 1.58 | 2011 |
| Better evaluation metrics lead to better machine translation | 20 | 2.63 | 2011 |
| TESLA at WMT 2011: translation evaluation and tunable metric | 11 | 1.28 | 2011 |
| NUS at the HOO 2011 pilot shared task | 4 | 0.43 | 2011 |
| TESLA: translation evaluation of sentences with linear-programming-based analysis | 22 | 1.08 | 2010 |
| Domain adaptation for semantic role labeling in the biomedical domain. | 17 | 0.61 | 2010 |
| PEM: a paraphrase evaluation metric exploiting parallel texts | 18 | 0.82 | 2010 |
| Joint learning of preposition senses and semantic roles of prepositional phrases | 16 | 0.72 | 2009 |
| On the practical importance of communication complexity for secure multi-party computation protocols | 16 | 0.95 | 2009 |
