• Publications
  • Influence
STACL: Simultaneous Translation with Implicit Anticipation and Controllable Latency using Prefix-to-Prefix Framework
TLDR
A novel prefix-to-prefix framework for simultaneous translation that implicitly learns to anticipate in a single translation model and presents a very simple yet surprisingly effective wait-k policy trained to generate the target sentence concurrently with the source sentence. Expand
Classify or Select: Neural Architectures for Extractive Document Summarization
TLDR
Two novel and contrasting Recurrent Neural Network (RNN) based architectures for extractive summarization of documents are presented and the models under both architectures jointly capture the notions of salience and redundancy of sentences. Expand
STACL: Simultaneous Translation with Integrated Anticipation and Controllable Latency
TLDR
A very simple yet surprisingly effective “wait-k” model trained to generate the target sentence concurrently with the source sentence, but always k words behind, for any given k is introduced. Expand
Dependency-based Convolutional Neural Networks for Sentence Embedding
TLDR
This work proposes a tree-based convolutional neural network model which exploit various long-distance relationships between words, which improves the sequential baselines on all three sentiment and question classification tasks, and achieves the highest published accuracy on TREC. Expand
Textual Entailment with Structured Attentions and Composition
TLDR
This work shows that it is beneficial to extend the attention model to tree nodes between premise and hypothesis, and studies the recursive composition of this subtree-level entailment relation, which can be viewed as a soft version of the Natural Logic framework. Expand
Breaking the Beam Search Curse: A Study of (Re-)Scoring Methods and Stopping Criteria for Neural Machine Translation
TLDR
Results show that the hyperparameter-free methods outperform the widely-used hyperparameters-free heuristic of length normalization by +2.0 BLEU, and achieve the best results among all methods on Chinese-to-English translation. Expand
Simpler and Faster Learning of Adaptive Policies for Simultaneous Translation
TLDR
This work proposes a simple supervised-learning framework to learn an adaptive policy from oracle READ/WRITE sequences generated from parallel text, and shows that this method can learn flexible policies with better BLEU scores and similar latencies compared to previous work. Expand
Robust Neural Machine Translation with Joint Textual and Phonetic Embedding
TLDR
This work proposes to improve the robustness of NMT to homophone noises by jointly embedding both textual and phonetic information of source sentences, and augmenting the training dataset with homophone noise. Expand
Simultaneous Translation with Flexible Policy via Restricted Imitation Learning
TLDR
This work proposes a much simpler single model that adds a `delay' token to the target vocabulary, and designs a restricted dynamic oracle to greatly simplify training on simultaneous translation. Expand
Speculative Beam Search for Simultaneous Translation
TLDR
A new speculative beam search algorithm is proposed that hallucinates several steps into the future in order to reach a more accurate decision by implicitly benefiting from a target language model and makes beam search applicable for the first time to the generation of a single word in each step. Expand
...
1
2
3
4
...