Lei Chen

Lei Chen
Hefei Institutes of Physical Science · Institute of Intelligent Machines

About

43
Publications
4,004
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
396
Citations

Publications

Publications (43)
Article
Recurrent Neural Network (RNN) based abstractive text summarization models have made great progress over the past few years, largely triggered by the encoder-decoder architecture. However, there has been little work improving the generation of relatively long summaries. In this paper, we concentrate on two prominent problems in long summary generat...
Article
Full-text available
Agricultural disease image recognition has an important role to play in the field of intelligent agriculture. Some advanced machine learning methods associated with the development of artificial intelligence technology in recent years, such as deep learning and transfer learning, have begun to be used for the recognition of agricultural diseases. H...
Article
Full-text available
Answer selection is the most important module of question answering system. Mining the semantic relevance between questions and answers is the key point of answer selection. However, the answer texts often contain some colloquial expressions and redundant information in some fields. In these cases, some traditional methods of mining text features a...
Chapter
Identification and control of agricultural diseases and pests is significant for improving agricultural yield. Food and Agriculture Organization of the United Nations reported that more than one-third of the annual natural loss is caused by agricultural diseases and pests. Traditional artificial identification is not accurate enough since it relies...
Chapter
Since the advantages of low cost and high efficiency, the three dimensional point cloud reconstruction based on multi-view image sequence and stereo matching has been widely used in agriculture. However, the reconstructed three dimensional point cloud often contains a lot of noise data because of the complex morphology of crop. In order to improve...
Chapter
Compared with traditional search engines, the query method of QA system is more intelligent and applicable in non-professional scenes, e.g., agricultural information retrieval. Question classification is an important issue in QA system. Since the particularities of agricultural questions, such as words sparsity, many technical terms, and so on, som...
Chapter
Machine learning has been widely used in the crop disease image classification. Traditional methods relying on the extraction of hand-crafted low-level image features are difficulty to get satisfactory results. Deep convolutional neural network can deal with this problem because of automatically learning the feature representations from raw image d...
Conference Paper
Full-text available
Fast1 and robust recognition of crop diseases is the basis for crop disease prevention and control. It is also an important guarantee for crop yield and quality. Most crop disease recognition methods focus on improving the recognition accuracy on public datasets, but ignoring the anti-interference ability of the methods, which result in poor recogn...
Conference Paper
As the latest breakthrough in the field of computer vision, deep convolutional neural network(CNN) is very promising for the classification of crop diseases. However, the common limitation applying the algorithm is reliance on a large amount of training data. In some cases, obtaining and labeling a large dataset might be difficult. We solve this pr...
Chapter
Machine learning has been widely applied to the crop disease image recognition. Traditional machine learning needs to satisfy two basic assumptions: (1) The training and test data should be under the same distribution; (2) A large scale of labeled training samples is required to learn a reliable classification model. However, in many cases, these t...
Chapter
According to the characteristics of crop leaf disease images, we proposed a new image retrieval method based on the improvement of inverted index to diagnose crop leaf diseases. First of all, the input crop disease images were preprocessed, including compression, denoising, enhancement, etc. And then the features of disease in the whole image were...
Article
Full-text available
We describe a theoretical model to analyze temperature effects on the Kretschmann surface plasmon resonance (SPR) sensor, and describe a new double-incident angle technique to simultaneously measure changes in refractive index (RI) and temperature. The method uses the observation that output signals obtained from two different incident angles each...
Article
In this paper, a morpheme-based weighting and its integration method are proposed as a smoothing method to alleviate the data sparseness in Chinese-Mongolian statistical machine translation (SMT). Besides, we present source-side reordering as the pre-processing model to verify the extensibility of our method. Experi-mental results show that the mor...
Conference Paper
Unlike previous Mongolian morphological segmentation methods based on large labeled training data or complicated rules concluded by linguists, we explore a novel semi-supervised method for a practical application, i.e., statistical machine translation (SMT), based on a low-resource learning setting, in which a small amount of labeled data and large...
Conference Paper
Reordering model is the crucial component in statistical machine translation (SMT), since it plays an important role in the generation of fluent translation results. However, the data sparseness is the key factor that greatly affects the performance of reordering model in SMT. In this paper, we exploit synonymous information to alleviate the data s...
Conference Paper
Feature matching is essential in computer vision. In this paper, we propose a robust and reliable image feature matching algorithm. It constructs several matching trees in which nodes correspond to traditional sparsely or densely sampled feature points, and feature lines are constructed between the nodes to build a cross-references based on a Diffe...
Article
The Three Gorges Reservoir (TGR) has a peculiar hydrological regime in China, with water level fluctuations of 30 m annually. In order to investigate the effects of hydrodynamic conditions on the diatom communities, limnological investigations were conducted monthly in front of the Three Gorges Dam (TGD) in 2013. We identified 18 diatom genera from...
Conference Paper
In order to improve the performance of statistical machine translation between Chinese and minority languages, most of which are under-resourced languages with different word order and rich morphology, the paper proposes a method which incorporates syntactic information of the source-side and morphological information of the target-side to simultan...
Conference Paper
Different order between Mongolian and Chinese and the scarcity of parallel corpus are the main problems in Mongolian-Chinese statistical machine translation (SMT). We propose a method that adopts morphological information as the features of the maximum entropy based phrase reordering model for Mongolian-Chinese SMT. By taking advantage of the Mongo...
Article
Full-text available
We explore a novel and rapid route for fabricating silver nanoparticles on the distal facet of an optical fiber. The reduction of neutral silver particles relies on the reaction between silver ions and organic free radicals initiated by the photolysis of photoinitiators. A similar approach has been extended to the fabrication of a silver nanopartic...
Conference Paper
We report on the laser-oriented growth of a polymer probe with a length of hundreds microns at the end of a single mode fiber. It has a high L/r ratio of 250 and a very low loss of 0.31 dB in optical transmission. It can be applied as an efficient scanning optical source and photo-detector.
Conference Paper
Key phrase extraction plays a significant role in many language processing tasks such as text summarization, text categorization and information retrieval. However, none study combines several approaches to improve the performance of key phrase extraction. This paper first implements three representative unsupervised algorithms TfIdf, Text Rank and...
Conference Paper
Comparable corpora are important basic resources in cross-language information processing. However, the existing methods of building comparable corpora, which use intertranslate words and relative features, cannot evaluate the topical relation between document pairs. This paper adopts the bilingual LDA model to predict the topical structures of the...
Article
Full-text available
In order to screen dioxin pollution in sediment of Three Gorges Dam (TGD) area, three sediment cores were obtained from two sites in 2010~2011; each core was divided into different samples with every 10 cm depth. Sediment dating determined by radiometry ((137)Cs, (210)Pb) and concentrations of dioxins were analyzed by high-resolution gas chromatogr...
Conference Paper
Parallel corpora are indispensable resources for a variety of multilingual natural language processing. This paper describes a system, which mines automatically parallel corpora from web pages. It attempts to overcome the shortage of parallel corpora in minority languages. Learning from the existing technology of mining web bilingual corpora, and c...
Conference Paper
In statistical machine translation, many translation errors may easily occur especially when the word orders are very different between source language and target language, especially with asymmetric morphological structures. The paper investigates combining a rule-based reordering model with conventional dependency parsing at the source side, whic...
Conference Paper
This paper presents an optimizing morphological segmentation metric for statistical machine translation performance. Unlike previous morpheme segmentation work for getting greater linguistic accuracy we focus on factors such as consistency, coverage and granularity, which directly affect MT performance. We propose a novel combination of dictionary...
Conference Paper
Morphological segmentation breaks words into morphemes. It is an important issue in natural language processing systems. The paper proposes a morphological segmentation method with hidden markov model method for Mongolian. The method uses sentences which consist of Mongolian words associated with affix sequences to establish a Hidden Markov Model....
Article
Since different languages put words in different orders, reordering is an important issue in statistical machine translation. The paper proposes a rule-based reordering method at the source side as a preprocessing step, which applies some syntactic reordering rules on the phrase structure subtree to reorder source language. The reordering rules int...
Article
Parallel corpora are important resources in data-driven natural language processing domain. Concerning the issues such as the scale, comprehensiveness and timeliness, the existing Chinese-Mongolian parallel corpora are significantly limited in practical use. Reviewing the traditional heuristic information used to identify major languages parallel w...

Network

Cited By