We present MultiGranCNN, a general deep learning architecture for matching text chunks. MultiGranCNN supports multigranular comparability of representations: shorter sequences in ...
In this article, we first propose to exploit a new criterion for improving distributional thesauri. Following a bootstrapping perspective, we select relations between the terms o...
Human labeled corpus is indispensable for the training of supervised word segmenters. However, it is time-consuming and laborintensive to label corpus manually. During the process...
Dakui Zhang, Yu Mao, Yang Liu, Hanshi Wang, Chuyua...
We propose Neural Responding Machine (NRM), a neural network-based response generator for Short-Text Conversation. NRM takes the general encoderdecoder framework: it formalizes th...
We study the problem of explaining relationships between pairs of knowledge graph entities with human-readable descriptions. Our method extracts and enriches sentences that refer ...
Nikos Voskarides, Edgar Meij, Manos Tsagkias, Maar...
Current distributed representations of words show little resemblance to theories of lexical semantics. The former are dense and uninterpretable, the latter largely based on famili...
In this paper, we propose a general framework to incorporate semantic knowledge into the popular data-driven learning process of word embeddings to improve the quality of them. Un...
Quan Liu, Hui Jiang 0001, Si Wei, Zhen-Hua Ling, Y...
The inability to model long-distance dependency has been handicapping SMT for years. Specifically, the context independence assumption makes it hard to capture the dependency bet...
In order to build psycholinguistic models of processing difficulty and evaluate these models against human data, we need highly accurate language models. Here we specifically co...