Fuji Ren

TL;DR: The experimental results show that the proposed latent semi-CRF model is capable of detecting even low frequency new words together with their POS tags, and is found to be performing competitively with the state-of-the-art models presented.

TL;DR: This paper demonstrates that PK has higher precision and efficiency compared with LSK and GK for the problem of sentimental classification, and compares the performances on different semantic orientation dictionaries, and finds that the domain semantic orientation dictionary can enhance the performance greatly.

TL;DR: This work employs a Bidirectional Long Short Term Memory (BLSTM) neural network for event extraction, which can skip handcrafted complex feature extraction and proposes a multi-level attention mechanism, including word level attention which determines the importance of words in a sentence, and the sentence level Attention which determinesThe importance of relevant arguments.

TL;DR: A method for automatic extraction of super-function from a Japanese-English bilingual corpus that uses a bilingual dictionary to match Japanese and English nouns in each sentence pair is presented.

TL;DR: A Prior-based Bayesian Pairwise Ranking (PBPR) model is proposed, which relaxes the simple pairwise preference assumption in previous works by further considering the pairwise preferences between two unobserved items.