arXiv subjects

Jiajun Zhang

Publications and source records attributed to Jiajun Zhang.

252 records · Page 14Linked to original sources

arXiv2017

Word, Subword or Character? An Empirical Study of Granularity in Chinese-English NMT

Neural machine translation (NMT), a new approach to machine translation, has been proved to outperform conventional statistical machine translation (SMT) across a variety of language pairs. Translation is an open-vocabulary problem, but most existing NMT systems operate with a fixed vocabulary, which causes the incapability of translating rare words. This problem can be alleviated by using different translation granularities, such as character, subword and hybrid word-character. Translation involving Chinese is one of the most difficult tasks in machine translation, however, to the best of our knowledge, there has not been any other work exploring which translation granularity is most suitable for Chinese in NMT. In this paper, we conduct an extensive comparison using Chinese-English NMT as a case study. Furthermore, we discuss the advantages and disadvantages of various translation granularities in detail. Our experiments show that subword model performs best for Chinese-to-English translation with the vocabulary which is not so big while hybrid word-character model is most suitable for English-to-Chinese translation. Moreover, experiments of different granularities show that Hybrid_BPE method can achieve best result on Chinese-to-English translation task.

cs.CL↗

arXiv2017

Towards Neural Machine Translation with Partially Aligned Corpora

While neural machine translation (NMT) has become the new paradigm, the parameter optimization requires large-scale parallel data which is scarce in many domains and language pairs. In this paper, we address a new translation scenario in which there only exists monolingual corpora and phrase pairs. We propose a new method towards translation with partially aligned sentence pairs which are derived from the phrase pairs and monolingual corpora. To make full use of the partially aligned corpora, we adapt the conventional NMT training method in two aspects. On one hand, different generation strategies are designed for aligned and unaligned target words. On the other hand, a different objective function is designed to model the partially aligned parts. The experiments demonstrate that our method can achieve a relatively good result in such a translation scenario, and tiny bitexts can boost translation quality to a large extent.

cs.CL↗

arXiv2017

Re-DPoctor: Real-time health data releasing with w-day differential privacy

Wearable devices enable users to collect health data and share them with healthcare providers for improved health service. Since health data contain privacy-sensitive information, unprotected data release system may result in privacy leakage problem. Most of the existing work use differential privacy for private data release. However, they have limitations in healthcare scenarios because they do not consider the unique features of health data being collected from wearables, such as continuous real-time collection and pattern preservation. In this paper, we propose Re-DPoctor, a real-time health data releasing scheme with $w$-day differential privacy where the privacy of health data collected from any consecutive $w$ days is preserved. We improve utility by using a specially-designed partition algorithm to protect the health data patterns. Meanwhile, we improve privacy preservation by applying newly proposed adaptive sampling technique and budget allocation method. We prove that Re-DPoctor satisfies $w$-day differential privacy. Experiments on real health data demonstrate that our method achieves better utility with strong privacy guarantee than existing state-of-the-art methods.

cs.CR↗

arXiv2017

Look-ahead Attention for Generation in Neural Machine Translation

The attention model has become a standard component in neural machine translation (NMT) and it guides translation process by selectively focusing on parts of the source sentence when predicting each target word. However, we find that the generation of a target word does not only depend on the source sentence, but also rely heavily on the previous generated target words, especially the distant words which are difficult to model by using recurrent neural networks. To solve this problem, we propose in this paper a novel look-ahead attention mechanism for generation in NMT, which aims at directly capturing the dependency relationship between target words. We further design three patterns to integrate our look-ahead attention into the conventional attention model. Experiments on NIST Chinese-to-English and WMT English-to-German translation tasks show that our proposed look-ahead attention mechanism achieves substantial improvements over state-of-the-art baselines.

cs.CL↗

arXiv2017

Learning Sentence Representation with Guidance of Human Attention

Recently, much progress has been made in learning general-purpose sentence representations that can be used across domains. However, most of the existing models typically treat each word in a sentence equally. In contrast, extensive studies have proven that human read sentences efficiently by making a sequence of fixation and saccades. This motivates us to improve sentence representations by assigning different weights to the vectors of the component words, which can be treated as an attention mechanism on single sentences. To that end, we propose two novel attention models, in which the attention weights are derived using significant predictors of human reading time, i.e., Surprisal, POS tags and CCG supertags. The extensive experiments demonstrate that the proposed methods significantly improve upon the state-of-the-art sentence representation models.

cs.CL↗

arXiv2017

Neural System Combination for Machine Translation

Neural machine translation (NMT) becomes a new approach to machine translation and generates much more fluent results compared to statistical machine translation (SMT). However, SMT is usually better than NMT in translation adequacy. It is therefore a promising direction to combine the advantages of both NMT and SMT. In this paper, we propose a neural system combination framework leveraging multi-source NMT, which takes as input the outputs of NMT and SMT systems and produces the final translation. Extensive experiments on the Chinese-to-English translation task show that our model archives significant improvement by 5.3 BLEU points over the best single system output and 3.4 BLEU points over the state-of-the-art traditional system combination methods.

cs.CL↗

arXiv2017

Shortcut Sequence Tagging

Deep stacked RNNs are usually hard to train. Adding shortcut connections across different layers is a common way to ease the training of stacked networks. However, extra shortcuts make the recurrent step more complicated. To simply the stacked architecture, we propose a framework called shortcut block, which is a marriage of the gating mechanism and shortcuts, while discarding the self-connected part in LSTM cell. We present extensive empirical experiments showing that this design makes training easy and improves generalization. We propose various shortcut block topologies and compositions to explore its effectiveness. Based on this architecture, we obtain a 6% relatively improvement over the state-of-the-art on CCGbank supertagging dataset. We also get comparable results on POS tagging task.

cs.CL↗

arXiv2016

Bridging Neural Machine Translation and Bilingual Dictionaries

Neural Machine Translation (NMT) has become the new state-of-the-art in several language pairs. However, it remains a challenging problem how to integrate NMT with a bilingual dictionary which mainly contains words rarely or never seen in the bilingual training data. In this paper, we propose two methods to bridge NMT and the bilingual dictionaries. The core idea behind is to design novel models that transform the bilingual dictionaries into adequate sentence pairs, so that NMT can distil latent bilingual mappings from the ample and repetitive phenomena. One method leverages a mixed word/character model and the other attempts at synthesizing parallel sentences guaranteeing massive occurrence of the translation lexicon. Extensive experiments demonstrate that the proposed methods can remarkably improve the translation quality, and most of the rare words in the test sentences can obtain correct translations if they are covered by the dictionary.

cs.CL↗

arXiv2016

An Empirical Exploration of Skip Connections for Sequential Tagging

In this paper, we empirically explore the effects of various kinds of skip connections in stacked bidirectional LSTMs for sequential tagging. We investigate three kinds of skip connections connecting to LSTM cells: (a) skip connections to the gates, (b) skip connections to the internal states and (c) skip connections to the cell outputs. We present comprehensive experiments showing that skip connections to cell outputs outperform the remaining two. Furthermore, we observe that using gated identity functions as skip mappings works pretty well. Based on this novel skip connections, we successfully train deep stacked bidirectional LSTM models and obtain state-of-the-art results on CCG supertagging and comparable results on POS tagging.

cs.CL↗

arXiv2016

A Dynamic Window Neural Network for CCG Supertagging

Combinatory Category Grammar (CCG) supertagging is a task to assign lexical categories to each word in a sentence. Almost all previous methods use fixed context window sizes as input features. However, it is obvious that different tags usually rely on different context window sizes. These motivate us to build a supertagger with a dynamic window approach, which can be treated as an attention mechanism on the local contexts. Applying dropout on the dynamic filters can be seen as drop on words directly, which is superior to the regular dropout on word embeddings. We use this approach to demonstrate the state-of-the-art CCG supertagging performance on the standard test set.

cs.CL↗

arXiv2016

One Sentence One Model for Neural Machine Translation

Neural machine translation (NMT) becomes a new state-of-the-art and achieves promising translation results using a simple encoder-decoder neural network. This neural network is trained once on the parallel corpus and the fixed network is used to translate all the test sentences. We argue that the general fixed network cannot best fit the specific test sentences. In this paper, we propose the dynamic NMT which learns a general network as usual, and then fine-tunes the network for each test sentence. The fine-tune work is done on a small set of the bilingual training data that is obtained through similarity search according to the test sentence. Extensive experiments demonstrate that this method can significantly improve the translation performance, especially when highly similar sentences are available.

cs.CL↗

arXiv2016

Neural Name Translation Improves Neural Machine Translation

In order to control computational complexity, neural machine translation (NMT) systems convert all rare words outside the vocabulary into a single unk symbol. Previous solution (Luong et al., 2015) resorts to use multiple numbered unks to learn the correspondence between source and target rare words. However, testing words unseen in the training corpus cannot be handled by this method. And it also suffers from the noisy word alignment. In this paper, we focus on a major type of rare words -- named entity (NE), and propose to translate them with character level sequence to sequence model. The NE translation model is further used to derive high quality NE alignment in the bilingual training corpus. With the integration of NE translation and alignment modules, our NMT system is able to surpass the baseline system by 2.9 BLEU points on the Chinese to English task.

cs.CL↗

arXiv2016

Extraction of cylinders and cones from minimal point sets

We propose new algebraic methods for extracting cylinders and cones from minimal point sets, including oriented points. More precisely, we are interested in computing efficiently cylinders through a set of three points, one of them being oriented, or through a set of five simple points. We are also interested in computing efficiently cones through a set of two oriented points, through a set of four points, one of them being oriented, or through a set of six points. For these different interpolation problems, we give optimal bounds on the number of solutions. Moreover, we describe algebraic methods targeted to solve these problems efficiently.

cs.CG↗

arXiv2015

Local Translation Prediction with Global Sentence Representation

Statistical machine translation models have made great progress in improving the translation quality. However, the existing models predict the target translation with only the source- and target-side local context information. In practice, distinguishing good translations from bad ones does not only depend on the local features, but also rely on the global sentence-level information. In this paper, we explore the source-side global sentence-level features for target-side local translation prediction. We propose a novel bilingually-constrained chunk-based convolutional neural network to learn sentence semantic representations. With the sentence-level feature representation, we further design a feed-forward neural network to better predict translations using both local and global information. The large-scale experiments show that our method can obtain substantial improvements in translation quality over the strong baseline: the hierarchical phrase-based translation model augmented with the neural network joint model.

cs.CL↗

arXiv2015

Beyond Word-based Language Model in Statistical Machine Translation

Language model is one of the most important modules in statistical machine translation and currently the word-based language model dominants this community. However, many translation models (e.g. phrase-based models) generate the target language sentences by rendering and compositing the phrases rather than the words. Thus, it is much more reasonable to model dependency between phrases, but few research work succeed in solving this problem. In this paper, we tackle this problem by designing a novel phrase-based language model which attempts to solve three key sub-problems: 1, how to define a phrase in language model; 2, how to determine the phrase boundary in the large-scale monolingual data in order to enlarge the training set; 3, how to alleviate the data sparsity problem due to the huge vocabulary size of phrases. By carefully handling these issues, the extensive experiments on Chinese-to-English translation show that our phrase-based language model can significantly improve the translation quality by up to +1.47 absolute BLEU score.

cs.CL↗

arXiv2009

Geometric Characteristics of Dynamic Correlations for Combinatorial Regulation in Gene Expression Noise

Knowing which mode of combinatorial regulation (typically, AND or OR logic operation) that a gene employs is important for determining its function in regulatory networks. Here, we introduce a dynamic cross-correlation function between the output of a gene and its upstream regulator concentrations for signatures of combinatorial regulation in gene expression noise. We find that the correlation function is always upwards convex for the AND operation whereas downwards convex for the OR operation, whichever sources of noise (intrinsic or extrinsic or both). In turn, this fact implies a means for inferring regulatory synergies from available experimental data. The extensions and applications are discussed.

q-bio.QM↗

arXiv2009

Synchronization and clustering of synthetic genetic networks: A role for cis-regulatory modules

The effect of signal integration through cis-regulatory modules (CRMs) on synchronization and clustering of populations of two-component genetic oscillators coupled by quorum sensing is in detail investigated. We find that the CRMs play an important role in achieving synchronization and clustering. For this, we investigate 6 possible cis-regulatory input functions (CRIFs) with AND, OR, ANDN, ORN, XOR, and EQU types of responses in two possible kinds of cell-to-cell communications: activator-regulated communication (i.e., the autoinducer regulates the activator) and repressor-regulated communication (i.e., the autoinducer regulates the repressor). Both theoretical analysis and numerical simulation show that different CRMs drive fundamentally different cellular patterns, such as complete synchronization, various cluster-balanced states and several cluster-nonbalanced states.

q-bio.MN↗

arXiv2009

Cis-Regulatory Modules Drive Dynamic Patterns of a Multicellular System

How intracellular and extracellular signals are integrated by transcription factors is essential for understanding complex cellular patterns at the population level. In this Letter, by using a synthetic genetic oscillator coupled to a quorum-sensing apparatus, we propose an experimentally feasible cis-regulatory module (CRM) which performs four possible logic operations (ANDN, ORN, NOR and NAND) of input signals. We show both numerically and theoretically that these different CRMs drive fundamentally different dynamic patterns, such as synchronization, clustering and splay state.

q-bio.QM↗