从历代鼓吹曲辞句度之关系重新审视歌辞错简问题

通过详细考察汉、魏、吴、晋、梁鼓吹曲辞句度与音乐之关系,发现魏、吴、晋、梁朝廷制鼓吹曲辞采用“依前曲作新歌”的方式写作,因此历代鼓吹曲辞句度之间存在延续性和相似性,一定程度上需要遵守同题曲辞的句度模式。在此基础上,重新审视向回、户仓英美两位学者提出的魏曲、晋曲可能存在的错简问题,得出晋曲第七曲和第九曲,魏曲第五和第六曲均未发生错简的结论。

基于预训练模型的无监督剧本摘要

剧本是一种特殊的文本结构,以人物的对话和对场景的描述信息组成文本。无监督剧本摘要是指对篇幅很长的剧本进行压缩、提取,形成能够概括剧本信息的短文本。提出了一种基于预训练模型的无监督剧本摘要方法,首先在预训练过程中通过增加对文本序列处理的预训练任务,使得预训练生成的模型能够充分考虑剧本中对话的场景描述及人物说话的情感特点,然后使用该预训练模型作为训练器计算剧本中的句间相似度,结合TextRank算法对关键句进行打分、排序,最终抽取得分最高的句子作为摘要。实验结果表明,该方法相比基准模型方法取得了更好的效果,系统性能在ROUGE评价上有显著的提高。

多文档自动文摘中的特征组合优化

在分析当前多文档自动文摘方法中使用较多的特征基础上,提出了一种特征组合优化模型。该模型选用tf*idf,句子位置及与标题句相似度来判断句子包含信息的重要程度。并加入了句子长度特征解决由tf*idf特征引起的长度偏长的句子占优势的问题,采用这4个特征来判断句子的重要性。并给每个特征指定权重来解决优化问题,实验结果表明特征组合优化模型在多文档自动文摘中的可行性。

基于词语量化相关关系的句际相关度计算

语篇上下文句子之间形式上是否衔接、意义上是否关联,是文本推理和文本结构分析的重要依据。上下文句子之间的关联性分析可分为定性和定量两种形式,作者以词语相关关系量化分析为基础,将上下文句子之间的相关度看成是由组成两个句子的所有词对之间的量化相关关系的组合结果,来定量地计算句子之间的相关度。实验结果表明,文中给出的句子相关度计算方法能够避免相似性度量中句子长度窗口受限问题;同时,与人工给出的句子间相关度进行相关系数计算表明,该方法能够很好的模拟人的认知来计算句子之间的语义相关性。

Annoyance-type speech emotion detection in working environment

In order to recognize people＇s annoyance emotions in the working environment and evaluate emotional well- being, emotional speech in a work environment is induced to obtain adequate samples of emotional speech, and a Mandarin database with two thousands samples is built. In searching for annoyance-type emotion features, the prosodic feature and the voice quality feature parameters of the emotional statements are extracted first. Then an improved back propagation （BP） neural network based on the shuffled frog leaping algorithm （SFLA） is proposed to recognize the emotion. The recognition capability of the BP, radical basis function （RBF） and the SFLA neural networks are compared experimentally. The results show that the recognition ratio of the SFLA neural network is 4. 7% better than that of the BP neural network and 4. 3% better than that of the RBF neural network. The experimental results demonstrate that the random initial data trained by the SFLA can optimize the connection weights and thresholds of the neural network, speed up the convergence and improve the recognition rate.

水解匀浆膳的临床应用

目的 探讨水解匀浆膳在临床管喂饮食中的应用价值。方法 用α 耐高温淀粉酶制作匀浆 ,将其成分与普通匀浆对比。结果 普通匀浆黏稠度是水解匀浆的 1 4倍 ,而单位体积营养素含量水解匀浆比普通匀浆高。结论 水解匀浆提高了管饲饮食临床应用的成功率。

Knowledge presentation model for QnA web forums

For an extract description of threads information in question and answer （QnA） web forums, it is proposed to construct a QnA knowledge presentation model in the English language, and then an entire solution for the QnA knowledge system is presented, including data gathering, platform building and applications design. With pre-defined dictionary and grammatical analysis, the model draws semantic information, grammatical information and knowledge confidence into IR methods, in the form of statement sets and term sets with semantic links. Theoretical analysis shows that the statement model can provide an exact presentation for QnA knowledge, breaking through any limits from original QnA patterns and being adaptable to various query demands; the semantic links between terms can assist the statement model, in terms of deducing new from existing knowledge. The model makes use of both information retrieval （IR） and natural language processing （NLP） features, strengthening the knowledge presentation ability. Many knowledge-based applications built upon this model can be improved, providing better performance.

基于TextRank算法的联合打分文本摘要生成

自动文本摘要生成是自然语言处理领域中颇具挑战性的问题之一,其任务是为书籍、篇章、新闻或者微博等某一文本资源生成简洁而又具有意义的文本摘要。TextRank算法是一种基于图的文本摘要生成算法,只利用当前文档即可实现关键词提取和文摘生成,因其简洁有效而得到广泛应用。本文在TextRank算法的基础上提出一个无监督抽取式联合打分模型。一方面,结合词频逆句频余弦相似度与词向量余弦相似度共同计算句子得分;另一方面,采用最大边缘相关度算法(Maximal Marginal Relevance,MMR)将抽取得到的摘要去除冗余。实验表明,改进后的方法生成的摘要具有更高的质量,尤其具有更好的梗概性和多样性。

A Hybrid Method of Extractive Text Summarization Based on Deep Learning and Graph Ranking Algorithms

In the era of Big Data,we are faced with an inevitable and challenging problem of“overload information”.To alleviate this problem,it is important to use effective automatic text summarization techniques to obtain the key information quickly and efficiently from the huge amount of text.In this paper,we propose a hybrid method of extractive text summarization based on deep learning and graph ranking algorithms(ETSDG).In this method,a pre-trained deep learning model is designed to yield useful sentence embeddings.Given the association between sentences in raw documents,a traditional LexRank algorithm with fine-tuning is adopted fin ETSDG.In order to improve the performance of the extractive text summarization method,we further integrate the traditional LexRank algorithm with deep learning.Testing results on the data set DUC2004 show that ETSDG has better performance in ROUGE metrics compared with certain benchmark methods.

Genre Effect on L2 Syntactic Complexity and Holistic Rating for Writing Quality of Intermediate EFL Learners

This exploratory study examines whether genre has an impact on syntactic complexity and holistic rating in EFL writing. Over 300 sample texts produced by intermediate learners were collected from a test and some regular after-class assignments for English writing courses. Each participant completed two writing tasks, one argumentative and the other narrative. Results show that genre type has a significant impact on L2 syntactic complexity. Genre effect is found stronger with timed writing tasks. L2 holistic ratings show correlation with syntactic complexity on the different measure(s) depending on genre type and planning conditions. Regression analyses reveal that for timed writing tasks, clausal density(clauses per sentence) is a reliable predictor for holistic assessment on intermediate EFL learners’ writing quality. It is found to account for 6% of the score variance for timed writing and 10% for timed argumentative writing. Genre is evidenced to be related to EFL writing holistic ratings. Closer examination indicates that while syntactic complexity is predictive of holistic writing scores for argumentative writing, it does not correlate with holistic scores for narrative writing. Other linguistic features rather than syntactic complexity may be accountable. Overall, the study lends support to genre effect in the relationship between syntactic complexity and L2 writing quality holistic rating.

On an Effective Thesis Statement

The thesis statement, as an arguable statement that communicates the author＇s stance on a topic to the reader in one or two sentences, functions as an aid for the author to focus on the subject and the reader to understand the main idea. After drafting a preliminary thesis statement, one should shape it from aspects of the structure, content and position. Structurally, an effective thesis statement includes one claim and several rea^ons. In content, consideration should be put in the author＇s stand, the value of debate, and clearness and concreteness of the main argument. The review and revising stage is indispensable after writing a thesis statement.

Accessibility and Visibility Analysis of Moinhos de Vento Park in Porto Alegre, Rio Grande do Sul, Brazil

This paper analyzes physical and visual accessibility at Moinhos de Vento Park in Porto Alegre, Rio Grande do Sul, Brazil, through Space Syntax methods. The Park presents a particularity in its configuration： it is crossed by an important avenue in the city that splits it in two portions linked by an elevated pedestrian path. The two portions of the park have different accessibility degrees and intensity of use due to -- we believed -- the way they are inserted in the urban pattern. Both the barrier caused by the avenue crossing the park and the differences of connectedness of each portion to its surrounding grid result in the level of integration occurring in different ways, turning the east portion less intensely used. The all-line and visibility integration maps showed that this was the case, and confirmed that spatial configuration plays an important role in rendering the east portion less integrated and in explaining the more intense use of the west portion. Integration maps showed that the most integrated areas are indeed the most used ones, although line and visibility integration differed slightly as to the exact location. This difference was probably due to the way barriers were modeled, since permeability took into account the paths while visibility considered all the ground as a whole, provided there were no barriers to sight. Another explanation for the difference is the lake located at the center of the west portion which contributed to this location＇s visual integration but, on the other hand, displaced line integration to the larger convex space to the north.

L2 Syntactic Alignment in the Reading-Writing Integrated Continuation Task: Evidence From Chinese EFL Learners’ Description of Motion Events

This study investigated how the mode in which the reading-writing integrated continuation task was conducted modulates the effects of second language(L2) syntactic alignment, through the English motion event construction with manner verbs. Ninety Chinese students were assigned to either of the two experimental groups or a control group, and they all experienced a pretest, an alignment phase and a posttest. In the alignment phase, the two experimental groups completed a reading-writing integrated continuation task but in different modes. For the multi-turn mode,participants reconstructed a picture story by continuing the episodes extracted from the story with one episode presented and continued at a time;for the single-turn mode, the first half of the same picture story was presented as a chunk, and then participants read and continued it. Results show that L2 learners aligned with the target structure in completing the story, and the alignment effect was retained in the posttest conducted after a delay of two weeks. Moreover, syntactic alignment was modulated by task mode with the multi-turn group exhibiting stronger immediate and longterm alignment effects. We conclude that the continuation task is a fruitful context for L2 structural alignment, and the magnitude of alignment effect hinges on interactive intensity.

《全宋词》补辑

开宝货药叟夫妇失调名蓝采禾。蓝采禾。尘世纷纷事更多。争如卖药沽酒饮,归去深崖拍手歌。[出处]宋马令《南唐书》卷一五:开宝中,常见一叟,角发被褐,与老媪货药于市。获钱则市鲜对饮,旁若无人。既醉,行舞而歌曰(词略)。按:此与《潇湘神》调句度、押韵格式全同,惟声律稍异。《全宋词》中无“开宝货药叟夫妇”名目,此盖笔者据《南唐书》代拟。

乐府诗体式研究评述

体式是乐府诗的五个重要构成要素(题名、本事、曲调、体式、风格)之一,因受内在音乐的制约,其形成和演变有相对的稳定性,是一首乐府诗的重要标志。系统地考察乐府诗的体式,研究众多乐府诗体式的特点、功能及其形成原因,不仅是乐府学的一项必不可少的工作,也是文体学的一项重要工作,更是传统诗学一项重要工作。因为这是对乐府诗一个构成要素认识的深化,也是对乐府诗这一文体认识的深化,同时也是对汉唐这一中国诗歌史上最为辉煌时期诗歌认识的深化。本文通过对乐府诗体式现象的系统考察,试图揭示乐府诗语言形式与音乐表演艺术之间的关系,以求对乐府诗文体的形成、功能及意义作出更深入的解释。

The Relative Significance of Vocabulary Breadth and Syntactic Knowledge in the Prediction of Reading Comprehension Test Performance

Founded on the componential model of reading, Nation＇s construct of vocabulary breadth test and structuralists＇ view of syntactic knowledge, this paper attempts to investigate the relative significance of vocabulary breadth and syntactic knowledge in the prediction of Chinese EFL learners＇ reading comprehension test performance and whether the relative significance is moderated by the learners＇ different L2 proficiency. An experiment including three tests was carried out with 68 sophomores in Anhui Medical University. The findings show that： 1） there is a positive linear correlation between the learners＇ performance on a reading comprehension test and their vocabulary breadth and syntactic knowledge, with the multiple r being 0.551; 2） syntactic knowledge outperforms vocabulary breadth in predictive power and emerges as the stronger predictor of reading comprehension test performance; and the relative significance of syntactic knowledge over vocabulary breadth in the prediction of reading comprehension does not change with the EFL learners＇ L2 proficiency. The findings of this study provide implications for both reading instruction and remediation of learners＇ reading problems.