526 citations · 1.4k across the 19 of their papers we have counts for
4 papers · 1 filter
Character-based Neural Machine Translation
Wang Ling, Isabel Trancoso, Chris Dyer +1
We introduce a neural machine translation model that views the input and output sentences as sequences of characters rather than words. Since word-level information provides a cruc…
Privacy-Preserving Multi-Document Summarization
Luís Marujo, José Portêlo, Wang Ling +6
State-of-the-art extractive multi-document summarization systems are usually designed without any concern about privacy issues, meaning that all documents are open to third parties…
Finding Function in Form: Compositional Character Models for Open Vocabulary Word Representation
Wang Ling, Tiago Luís, Luís Marujo +5
We introduce a model for constructing vector representations of words by composing characters using bidirectional LSTMs. Relative to traditional word representation models that hav…
Transition-Based Dependency Parsing with Stack Long Short-Term Memory
Chris Dyer, Miguel Ballesteros, Wang Ling +2
We propose a technique for learning representations of parser states in transition-based dependency parsers. Our primary innovation is a new control structure for sequence-to-seque…