Papers by Shuailong Liang

3 papers
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.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations