Learn More
Shift-reduce dependency parsers give comparable accuracies to their chartbased counterparts, yet the best shiftreduce constituent parsers still lag behind the state-of-the-art. One important reason is the existence of unary nodes in phrase structure trees, which leads to different numbers of shift-reduce actions between different outputs for the same input.(More)
Cytoplasmic (or non-muscle) myosin II isoforms are widely expressed molecular motors playing essential cellular roles in cytokinesis and cortical tension maintenance. Two of the three human non-muscle myosin II isoforms (IIA and IIB) have been investigated at the protein level. Transient kinetics of non-muscle myosin IIB showed that this motor has a very(More)
It is intuitively obvious that the ability of a cell to repair DNA damage is saturable, either by limitation of enzymatic activities, the time allotted to achieve their function, or both. However, very little is known regarding the mechanisms that establish such a threshold. Here we demonstrate that the CUL4A ubiquitin ligase restricts the cellular repair(More)
In this paper, we propose an approach to automatically learning feature embeddings to address the feature sparseness problem for dependency parsing. Inspired by word embeddings, feature embeddings are distributed representations of features that are learned from large amounts of auto-parsed data. Our target is to learn feature embeddings that can not only(More)
Sentiment classification on Twitter has attracted increasing research in recent years. Most existing work focuses on feature engineering according to the tweet content itself. In this paper, we propose a contextbased neural network model for Twitter sentiment analysis, incorporating contextualized features from relevant Tweets into the model in the form of(More)
Acute leukemia characterized by chromosomal rearrangements requires additional molecular disruptions to develop into full-blown malignancy, yet the cooperative mechanisms remain elusive. Using whole-genome sequencing of a pair of monozygotic twins discordant for MLL (also called KMT2A) gene-rearranged leukemia, we identified a transforming MLL-NRIP3 fusion(More)
Neural probabilistic parsers are attractive for their capability of automatic feature combination and small data sizes. A transition-based greedy neural parser has given better accuracies over its linear counterpart. We propose a neural probabilistic structured-prediction model for transition-based dependency parsing, which integrates search and learning.(More)