Papers with LSTM structure

2 papers
Sentence-State LSTM for Text Representation (P18-1)

Copied to clipboard

Challenge: LSTMs have been shown to suffer from various limitations due to their sequential nature.
Approach: They propose to model hidden states of all words simultaneously at each recurrent step rather than one word at a time.
Outcome: The proposed model has strong representation power, giving competitive performances compared to stacked BiLSTM models with similar parameter numbers.
A Graph-to-Sequence Model for AMR-to-Text Generation (P18-1)

Copied to clipboard

Challenge: Abstract Meaning Representation (AMR) is a semantic formalism that encodes the meaning of a sentence as a rooted, directed graph.
Approach: They propose a neural graph-to-sequence model that leverages LSTM to encode a linearized AMR structure.
Outcome: The proposed model outperforms existing methods on a benchmark.

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