- Full text PDF available (14)
- This year (4)
- Last 5 years (19)
- Last 10 years (24)
Journals and Conferences
We investigate whether a neural, encoderdecoder translation system learns syntactic information on the source side as a by-product of training. We propose two methods to detect whether the encoder has learned local and global source syntax. A fine-grained analysis of the syntactic structure learned by the encoder reveals which kinds of syntax are learned… (More)
We describe Hafez, a program that generates any number of distinct poems on a usersupplied topic. Poems obey rhythmic and rhyme constraints. We describe the poetrygeneration algorithm, give experimental data concerning its parameters, and show its generality with respect to language and poetic form.
We investigate how neural, encoder-decoder translation systems output target strings of appropriate lengths, finding that a collection of hidden units learns to explicitly implement this functionality.
To model red blood cell (RBC) deformation and multiple-cell interactions in flow, the recently developed technique derived from the lattice Boltzmann method and the distributed Lagrange multiplier/fictitious domain method is extended to employ the mesoscopic network model for simulations of RBCs in flow. The flow is simulated by the lattice Boltzmann method… (More)
Sentence compression is one of the most challenging tasks in natural language processing, which may be of increasing interest to many applications such as abstractive summarization and text simplification for mobile devices. In this paper, we present a novel sentence compression model based on first-order logic, using Markov Logic Network. Sentence… (More)
BACKGROUND Childhood diabetes has become a growing concern. We conducted a study to evaluate the status and trend of diabetes from 14 medical centers in China. Pre-diabetic status among obese children was also noted. METHODS Hospital medical records were reviewed, and data of diabetes were collected from 1995 through 2010. We took every five years as a… (More)
With novel underwater wireless sensor array network architecture, the weighted least square (WLS) source localization method is developed. In this method, each sensor node is attached to a local sensor array which can estimated Signal-Noise-Ratio (SNR) as well the local direction-of-Arrival (DOA). Global localization can combined with estimated DOA selected… (More)
OBJECTIVES Regulatory T cells play an active role in the maintenance of the immune system's tolerance of both foreign and self antigens. Particularly, CD(4) (+) CD(25) (+) regulatory T cells participate in tumor immunity. The study provided further evidence on the involvement of CD(4) (+ )CD(25) (+) regulatory T cells in immune system impairment in patients… (More)
We develop a system that lets people overcome language barriers by letting them speak a language they do not know. Our system accepts text entered by a user, translates the text, then converts the translation into a phonetic spelling in the user’s own orthography. We trained the system on phonetic spellings in travel phrasebooks.