AbstractContext representations are a key element in distributional models of word meaning. A recently proposed approach suggests to represent a context of a target word by a substitute vector. In thi
IntroductionMost existing work on multi-task learning attempts to divide the features of different tasks into private and shared spaces, merely based on whether parameters of some components should be
IntroductionDiscourse structure represents the organization of a text as a tree. Experimental results show that variants of our model outperform prior work on four out of five tasks considered. In thi
DataStoriesAbstractThis paper built two sentiment analysis systems based on LSTM with two kinds of attention mechanism on top of word embeddings pre-trained on a big collection of Twitter messages. Th
AbstractCompare two variants of retrofitting and a joint-learning approach. Although the word embeddings is sometimes desirable, it may in other cases be detrimental to downstream performance. For ex
Abstract and IntroductionThey introduce a new vector space representation where antonyms lie on opposite sides of a sphere: in the word vector space, synonyms have cosine similarities close to one, wh
AbstractA new learning objective that incorporates both a neural language model objective and prior knowledge from semantic resources to learn improved lexical semantic embeddings. IntroductionIn thi
AbstractThey reveal that much of the performance gains of word embeddings are due to certain system design choices, rather than the embedding algorithms themselves. Furthermore, they show that these m
AbstractIn this paper, a novel morph-fitting procedure is proposed to injects morphological constraints generated using simple language-specific rules. Result: improves low-frequency word estimates;
wordscongruent:全等 AbstractThe paraphrase Database (PPDB) consists of a list of phrase pairs with heuristic confidence estimates. Its coverage is also necessarily incomplete. They propose models to: