On the WMT 2014 English-to-German and English-to-French translation tasks, this approach yields improvements of 1. 3 BLEU and 0. 3 BLEU over absolute position representations, respectively.
Ranked #10 on Machine Translation on WMT2014 English-French
We introduce a new type of deep contextualized word representation that models both (1) complex characteristics of word use (e. g., syntax and semantics), and (2) how these uses vary across linguistic contexts (i. e., to model polysemy).
There has been much recent work on training neural attention models at the sequence-level using either reinforcement learning-style methods or by optimizing the beam.
Ranked #4 on Machine Translation on IWSLT2015 German-English
The recent tremendous success of unsupervised word embeddings in a multitude of applications raises the obvious question if similar methods could be derived to improve embeddings (i. e. semantic representations) of word sequences as well.
We propose an unsupervised keyphrase extraction model that encodes topical information within a multipartite graph structure.
Emotion recognition in conversations is crucial for the development of empathetic machines.
Ranked #5 on Emotion Recognition in Conversation on SEMAINE
We introduce a fully differentiable approximation to higher-order inference for coreference resolution.
Ranked #6 on Coreference Resolution on OntoNotes
In the first task, we show that simple models can predict whether a paper is accepted with up to 21% error reduction compared to the majority baseline.
Sentence pair modeling is critical for many NLP tasks, such as paraphrase identification, semantic textual similarity, and natural language inference.