Papers by Shuailong Liang
Does it Make Sense? And Why? A Pilot Study for Sense Making and Explanation (P19-1)
Copied to clipboard
| Challenge: | Existing benchmarks measure common sense knowledge indirectly or without reasoning. |
| Approach: | They propose a benchmark to test whether a system can differentiate natural language statements that make sense from those that do not make sense. |
| Outcome: | The proposed benchmarks show that models trained on large corpora perform better than humans on some benchmarks. |
Design Challenges and Misconceptions in Neural Sequence Labeling (C18-1)
Copied to clipboard
| Challenge: | Existing neural sequence labeling models have been used for many tasks such as POS tagging, chunking and named entity recognition (NER). |
| Approach: | They propose to replicate twelve neural sequence labeling models and compare them to three benchmarks to find out which models are effective and which are inconsistent. |
| Outcome: | The proposed models are compared on NER, Chunking, and POS tagging benchmarks. |
Subword Encoding in Lattice LSTM for Chinese Word Segmentation (N19-1)
Copied to clipboard
| Challenge: | Using subwords, Chinese word segmentation models use character combination information to disambiguate characters. |
| Approach: | They propose a subword-based neural word segmentor that integrates character embeddings into a Lattice LSTM network over a character sequence. |
| Outcome: | The proposed model can utilize abundant character combination information, which is effective to disambiguate characters. |