CN106021239A - Method for real-time evaluation of translation quality - Google Patents

Method for real-time evaluation of translation quality Download PDF

Info

Publication number
CN106021239A
CN106021239A CN 201610272936 CN201610272936A CN106021239A CN 106021239 A CN106021239 A CN 106021239A CN 201610272936 CN201610272936 CN 201610272936 CN 201610272936 A CN201610272936 A CN 201610272936A CN 106021239 A CN106021239 A CN 106021239A
Authority
CN
Grant status
Application
Patent type
Prior art keywords
translation
statement
user
engine
quality
Prior art date
Application number
CN 201610272936
Other languages
Chinese (zh)
Other versions
CN106021239B (en )
Inventor
陈罡
Original Assignee
北京创鑫旅程网络技术有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING; COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F17/00Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/20Handling natural language data
    • G06F17/28Processing or translating of natural language
    • G06F17/2854Translation evaluation
    • GPHYSICS
    • G06COMPUTING; CALCULATING; COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F17/00Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/20Handling natural language data
    • G06F17/28Processing or translating of natural language
    • G06F17/289Use of machine translation, e.g. multi-lingual retrieval, server side translation for client devices, real-time translation

Abstract

The invention discloses a method for real-time evaluation of translation quality. The method comprises the steps that a statement initiated by a user is received according to the user's translation request; multiple translation engines receive the statement initiated by the user; according to statistic results of total quantity of translation times of each engine as well as frequencies for the user to collect and play the statement, a weighted utilization frequency of translation results of each translation engine, and a per capita utilization frequency are calculated and taken as a quality score; the proportion occupied by the quality score in the quality score sum of all the engines is taken as a probability; the translation engine with the highest probability is taken as the optimal translation engine for the statement request; and the obtained optimal translation engine is taken as a preferential engine for the statement request, the translation engine is called to translate the statement requested by the user, and finally a translation result is obtained. The method disclosed by the invention has the advantages that the automatic and real-time quality evaluation is carried out to the translation quality of the multiple engines; and optimal translation engine results can be provided for different statements in need of translation.

Description

一种翻译质量实时评价方法 One kind of real-time translation quality evaluation method

技术领域 FIELD

[0001] 本发明涉及翻译质量评价领域,具体地说是一种翻译质量实时评价方法。 [0001] The present invention relates to the field of quality evaluation of the translation, in particular a method for real-time evaluation of the quality of translation. 背景技术 Background technique

[0002] 人们在使用翻译工具时,通常是通过一种翻译引擎实现,并人工识别这个翻译结果的准确度,若觉得翻译结果不够理想,则会尝试换一种翻译引擎再进行尝试,直到无法得到更优结果为止。 [0002] When people use translation tools, usually achieved by means of a translation engine and manual identification accuracy of the translation, if that translation is not ideal, it will try to put it another translation engine to try again, until I can not far better results obtained. 这种人工切换翻译引擎的方式,获得最优翻译结果的效率低,耗时长,尤其无法满足实时翻译的需求。 This manually switch the translation engine, inefficient translation obtain optimal results, time-consuming and, in particular, can not meet the needs of real-time translation.

[0003] 那么,集成多个翻译引擎,为用户提供覆盖度更高的翻译结果,能够部分解决上述技术问题,尤其适用于出境游用户。 [0003] Then, the integration of multiple translation engines to provide users with greater translation coverage, can partially solve the aforementioned problems, especially for outbound users. 为了给出境游用户提供高品质的翻译结果,提升翻译覆盖度,会集成多个翻译引擎,确保翻译的覆盖度,但同一个待翻译语句,对于有限的常用语句的使用,可以请专家进行评审,来选择和确定最优翻译结果,而这种方式显然无法应对复杂的翻译需求。 In order to provide high-quality translation to outbound users to enhance translation coverage, it will integrate multiple translation engines to ensure coverage of translation, but with a sentence to be translated, for limited use of common expressions, can ask the expert review to select and determine the optimal translation of results, and this approach is clearly unable to cope with complex translation needs. 现有的专家评审的方式,最大的缺点是无法做到快速的实时响应,对于海量翻译语句,人力评审成本高,无法做到自动化和量化的程度,也无法持续改进评价方式。 Existing expert review of the way, the biggest drawback is that can not be done fast real-time response, the translated sentence for massive, high labor cost assessment, to quantify the degree of automation and can not do, can not continue to improve evaluation methods. 另一种方式是对每个翻译引擎进行抽样质量评估,评价某个引擎的综合翻译质量。 Another way is to sample quality assessment for each translation engine, a comprehensive evaluation of the quality of a translation engine. 但无法做到精确到不同语句的翻译质量。 But you can not do the quality of translation is accurate to a different statement.

[0004] 更难处理的是,针对实时的在线翻译,如何量化评估多个引擎的翻译结果,是获得最优翻译结果所必须要解决的技术问题,这就成了一个很迫切的技术问题。 [0004] is more difficult to deal with, for real-time online translation, how to quantify the results of evaluating multiple translation engines, it is to obtain the optimum translation results technical problems that must be addressed, which has become a very urgent technical problems. 现有技术往往通过分析语言结构来解决这一技术问题,例如国家知识产权局公开的专利申请号为201410461334.9的发明专利申请机器翻译方法及系统,但这同样无法适应不同的语境、场合以及用户的语言习惯等,因此无法解决上述技术问题。 The prior art often to solve this technical problem by analyzing the structure of language, such as the State Intellectual Property Office published patent application No. 201410461334.9 of invention patent applications machine translation method and system, but the same can not adapt to different contexts, situations and users language habits, can not solve the above problems. 发明内容 SUMMARY

[0005] 有鉴于此,本发明针对上述现有技术存在的无法高效地获得最优翻译结果的技术问题,提供了一种集成多个翻译引擎并实时在线评估的翻译质量实时评价方法,以获得最优翻译结果。 [0005] Accordingly, the present invention is directed to the above-described prior art can not exist efficiently obtain optimal translation results technical problem, a method for real-time evaluation of the quality of translation plurality of translation engines and an integrated real-time online evaluation, to obtain optimal translation results.

[0006] 本发明的技术解决方案是,提供一种以下步骤的翻译质量实时评价方法,包括以下步骤: [0006] The technical solution of the invention is to provide a method for real-time evaluation of the steps of translation quality, comprising the steps of:

[0007] 步骤1:根据用户的翻译请求,接收用户所发起的语句; [0007] Step 1: The translation request user, receiving a user-initiated statement;

[0008] 步骤2:集成的多个翻译引擎均接收到所述用户发起的语句,根据统计不同引擎的各自的总翻译次数及用户所收藏该语句、播放该语句的频次,计算相应翻译引擎的翻译结果的加权使用频次和计算人均使用频次作为质量分,并以质量分占所有引擎的质量分加和的比例为概率,概率最高的翻译引擎则作为本次语句请求的最优翻译引擎; [0008] Step 2: Integrated plurality of translation engines are receiving the user-initiated statement, which is the total collection in accordance with the respective user statistics and the number of different translation engines, play the statement frequency, calculate the corresponding translation engine weighted using the translation results of frequency and calculate per capita frequency of use as a mass fraction, and the quality of sub-accounts for the quality of all engine points plus and a ratio of probability, the best translation engines highest probability translation engine is as this statement is requested;

[0009] 步骤3:将上述的得到的最优翻译引擎作为请求此语句的优先使用引擎,调度该翻译引擎来翻译用户所请求的语句,得到翻译结果,返回给用户。 [0009] Step 3: The above obtained optimal translation engine as a request statement is preferably used for this engine, the translation engine to schedule sentence translation requested by the user, to obtain the translation result to the user.

[0010] 采用以上步骤,本发明与现有技术相比,具有以下优点:采用本发明,针对用户发起的特定语句,每个翻译引擎不尽相同,通过计算相应翻译引擎的翻译结果的加权使用频次和计算人均使用频次作为质量分,作为对不同翻译引擎针对该语句之翻译结果的评价, 以评价较高者作为优先使用的翻译引擎,完成对该语句最优翻译引擎的选择,从而得到最优翻译结果,返回给用户。 [0010] With the above steps, as compared with the prior art the present invention has the following advantages: the present invention, the statement for a particular user-initiated, each translation engine vary, weighted by the corresponding translation engines using translation frequency and frequency of use per capita is calculated as the mass fraction, as the evaluation of different translation engine for translation of the statement in order to evaluate the person as a higher priority use of the translation engine, to complete the selection of the optimal sentence translation engine, resulting in the most excellent translation results returned to the user. 本发明引入了频次作为评价依据,无需分析语句的语言结构,能够快速有效地得到最优翻译结果,通过这种系统性的方法,对多个引擎的翻译质量,进行自动化的实时的质量评估,对于不同的翻译语句,给出最优的翻译引擎结果。 The present invention introduces frequency as an evaluation basis, without having to analyze the structure of language statements, can quickly and efficiently get the best translation result, this systematic approach to translation quality multiple engines, real-time automated quality assessment, for different sentence translation, translation engine gives the best results.

[0011] 作为优选,在完成步骤3后,更新所述最优翻译引擎下对用户所发起的该语句的翻译频次,提起该语句翻译请求的用户在使用翻译结果的后续行为,作为日志发送给质量评估数据库,用于后续的评价和对选择最优翻译引擎的动态修正。 [0011] Advantageously, after the completion of step 3, the update frequency translation of the statement of the user initiated the optimal translation engine, the subsequent behavior of the user lifting the statement translation request using the translation results, as transmitted to the log quality assessment database for subsequent evaluation and dynamic correction to choose the best translation engines.

[0012] 作为优选,质量评估数据库根据上报的日志信息,并采集用户的位置信息来判断用户所在地及是否在国外,结合用户地理位置情况作为衡量翻译质量的辅助因素,便可设定区域范围,得到该区域范围的最优翻译引擎。 [0012] Preferably, the quality evaluation information database according to the reported log, and a collection position information of the user and determines whether the user is located in a foreign country, the case with the user location as an auxiliary factor measures the quality of the translation, the range can be set region, get the best of the region-wide translation engine. 叠加了位置信息后,更能精确反映翻译引擎的翻译质量,因为翻译的质量往往跟语句的使用场景有关。 After superimposed location information more accurately reflect the quality of the translation engine of the translation, because the quality of the translation is often associated with the use of scenarios statement.

[0013] 作为优选,针对不同用户的相同翻译请求,不同用户使用不同引擎获得翻译结果, 并通过分析处理后续用户对翻译结果在不同时间、不同地域的使用方式与频次,量化评估不同翻译引擎对此语句的翻译质量,从而为其他用户提供此语句的最好的翻译结果。 [0013] Advantageously, for the same translation request different users, different users use different engine obtains a translation result, and by evaluating a subsequent user of the translation at a different time, use different regions of the frequency, quantitative assessment of different translation engines the quality of translation of this statement in order to provide the best translation of this statement for other users. 通过这种综合分析和评估的方式,能够获得更优的翻译结果。 By way of this comprehensive analysis and assessment, we can get better translation results. 附图说明 BRIEF DESCRIPTION

[0014] 图1为翻译质量实时评价方法的步骤示意图;具体实施方式 [0014] FIG. 1 is a method for real-time evaluation of the quality of translation schematic step; DETAILED DESCRIPTION

[0015] 下面结合附图和具体实施例对本发明作进一步说明,但本发明并不仅仅限于这些实施例。 [0015] conjunction with the accompanying drawings and the following specific embodiments of the present invention is further illustrated, but the present invention is not limited to these examples.

[0016] 本发明涵盖任何在本发明的精髓和范围上做的替代、修改、等效方法以及方案。 [0016] The present invention encompasses in any of the spirit and scope of the present invention have alternatives, modifications, equivalents method and program. 为了使公众对本发明有彻底的了解,在以下本发明优选实施例中详细说明了具体的细节,而对本领域技术人员来说没有这些细节的描述也可以完全理解本发明。 In order for the public to have a thorough understanding of the present invention, described in detail in specific details described in the preferred embodiment of the present invention hereinafter, but these details are not described may be fully understood that the present disclosure the skilled artisan.

[0017] 如图1所示,本发明的一种翻译质量实时评价方法,包括以下步骤: [0017] As shown in FIG 1 A real-time translation quality evaluation method of the present invention, comprising the steps of:

[0018] 步骤1:根据用户的翻译请求,接收用户所发起的语句; [0018] Step 1: The translation request user, receiving a user-initiated statement;

[0019] 步骤2:集成的多个翻译引擎均接收到所述用户发起的语句,根据统计不同引擎的各自的总翻译次数及用户所收藏该语句、播放该语句的频次,计算相应翻译引擎的翻译结果的加权使用频次和计算人均使用频次作为质量分,并以质量分占所有引擎的质量分加和的比例为概率,概率最高的翻译引擎则作为本次语句请求的最优翻译引擎; [0019] Step 2: Integrated plurality of translation engines are receiving the user-initiated statement, which is the total collection in accordance with the respective user statistics and the number of different translation engines, play the statement frequency, calculate the corresponding translation engine weighted using the translation results of frequency and calculate per capita frequency of use as a mass fraction, and the quality of sub-accounts for the quality of all engine points plus and a ratio of probability, the best translation engines highest probability translation engine is as this statement is requested;

[0020] 步骤2中,可以设定数据量、质量的阈值,达到后,不再根据概率返回最优翻译引擎,因为已经得到可靠的结果,则不需要每次重复,提高响应速度。 In [0020] Step 2, to set a threshold amount of data, quality, is reached, according to the translation engine does not return the best probability, because reliable results already obtained, each repetition is not required, increase the response speed.

[0021] 步骤3:将上述的得到的最优翻译引擎作为请求此语句的优先使用引擎,调度该翻译引擎来翻译用户所请求的语句,得到翻译结果,返回给用户。 [0021] Step 3: The above obtained optimal translation engine as a request statement is preferably used for this engine, the translation engine to schedule sentence translation requested by the user, to obtain the translation result to the user. [〇〇22]在完成步骤3后,更新所述最优翻译引擎下对用户所发起的该语句的翻译频次,提起该语句翻译请求的用户在使用翻译结果的后续行为,作为日志发送给质量评估数据库,用于后续的评价和对选择最优翻译引擎的动态修正。 [〇〇22] After completion of step 3, the update statement at the optimal translation engine to a user-initiated translation frequency, the subsequent behavior of the user lifting the statement translation request using the translation result is sent to the mass of the log assessment database for subsequent evaluation and dynamic correction to choose the best translation engines.

[0023] 质量评估数据库根据上报的日志信息,并采集用户的位置信息来判断用户所在地及是否在国外,结合用户地理位置情况作为衡量翻译质量的辅助因素,便可设定区域范围, 得到该区域范围的最优翻译引擎。 [0023] The log information database quality assessment reported, and a collection position information of the user and determines whether the user is located in a foreign country, the case with the user location as an auxiliary factor measures the quality of the translation, the range can be set region, the region to give optimal translation engine range. 叠加了位置信息后,更能精确反映翻译引擎的翻译质量, 因为翻译的质量往往跟语句的使用场景有关,使用场景和地理位置往往决定了使用习惯, 也就存在不同的表达习惯。 After superimposed location information more accurately reflect the quality of the translation engine of the translation, because the quality of the translation is often the scene with the use of statements related to the use of scenarios and geographical location often determines the habits, also there are different habits of expression.

[0024] 针对不同用户的相同翻译请求,不同用户使用不同引擎获得翻译结果,并通过分析处理后续用户对翻译结果在不同时间、不同地域的使用方式与频次,量化评估不同翻译引擎对此语句的翻译质量,从而为其他用户提供此语句的最好的翻译结果。 [0024] for the same translation request different users, different users use different engine obtains a translation result, and by evaluating a subsequent user of the translation at a different time, different regions of use and frequency, quantitative assessment of different translation engines this sentence translation quality to provide the best translation of this statement for other users. 通过这种综合分析和评估的方式,能够获得更优的翻译结果。 By way of this comprehensive analysis and assessment, we can get better translation results.

[0025] 需要注意的是,以上所提及的质量评估数据库均指的是图1中的质量评估库。 [0025] It should be noted that the above-mentioned quality evaluation database refer to FIG. 1 in the quality evaluation libraries.

[0026] 本发明的具体原理步骤如下:尤其是针对身处国外旅行的人,向客户端发起语句翻译的请求,获取其地理位置信息,根据在该地区的使用习惯,并结合对相应请求语句的翻译频次以及用户的后续行为,为用户提供最优的翻译引擎,获得最优的翻译结果,并在多因素的综合下,可对翻译引擎的选择进行动态修正。 [0026] Specific steps of the principles of the present invention are as follows: especially for people living in traveling abroad, the statement translation initiation request to the client obtain its location information, according to usage in the region, combined with the corresponding request statement the frequency translation and the subsequent behavior of the user, to provide users with the best translation engine for optimal translation results, and in a comprehensive multi-factor, the choice of translation engines can be dynamically corrected. [〇〇27] 本发明的更具体的应用场景如下(通过移动终端APP实现): [〇〇27] more specific application scenario of the present invention is as follows (APP achieved by a mobile terminal):

[0028] 步骤1:客户端发起语句的翻译请求。 [0028] Step 1: The client sends a request to the translation of the statement.

[0029] 步骤2:翻译引擎调度请求此语句的优先使用引擎。 [0029] Step 2: translation engine using engine priority scheduling request this statement.

[0030] 步骤3:质量评估库根据统计不同引擎的各自的总翻译次数及后续用户国外进行的收藏语句、播放语句的频次,计算此翻译结果的加权使用频次计算人均使用频次作为质量分,并以质量分占所有引擎的质量分加和的比例为概率,返回给翻译引擎调度分者对应的引擎,并更新下此引擎对此语句的翻译频次。 [0030] Step 3: quality assessment database engine of their total number translation and collectibles statements subsequent users abroad, the player statement frequency, weighted this translation results using the frequency depending on the statistical calculations per capita frequency of use as a mass fraction, and Share of the quality of the quality of all engines plus points and the proportion of probability, return to the translation engine dispatcher who points out to the engine, and this engine update frequency translation of this statement. [0031 ]步骤4:根据返回引擎,请求对应引擎的翻译结果。 [0031] Step 4: Return engine, translation results corresponding to the request in accordance with the engine. [〇〇32] 步骤5:对应引擎返回翻译结果给翻译引擎调度。 [〇〇32] Step 5: results corresponding to the translation engine returns to the translation engine scheduling.

[0033] 步骤6:翻译引擎调度将翻译结果返回给客户端。 [0033] Step 6: scheduling translation engine to translate results returned to the client.

[0034] 步骤7:用户在客户端使用翻译结果的后续行为,作为日志发送给质量评估引擎。 [0034] Step 7: the user uses the client translation results in subsequent behavior, to a quality evaluation engine as a log.

[0035] 步骤8:质量评估引擎根据客户端上报的日志信息,计算用户所在地及是否在国夕卜,并添加此日志到质量评估库,并计算用户使用频次数据 [0035] Step 8: quality assessment engine according to the log information reported by the client, to calculate the location of the user and whether the country Xi Bu and add this log to assess the quality of the library, and calculate the frequency of use user data

[0036] 以上仅就本发明较佳的实施例作了说明,但不能理解为是对权利要求的限制。 [0036] Far more preferred embodiment of the present invention has been described, but should not be construed as limiting the claim. 本发明不仅局限于以上实施例,其具体结构允许有变化。 The present invention is not limited to the above embodiments, the specific structure allows changes. 总之,凡在本发明独立权利要求的保护范围内所作的各种变化均在本发明的保护范围内。 In short, where the variations made within the scope of the independent claims of the invention are within the scope of the present invention.

Claims (4)

  1. 1.一种翻译质量实时评价方法,包括以下步骤:步骤1:根据用户的翻译请求,接收用户所发起的语句;步骤2:集成的多个翻译引擎均接收到所述用户发起的语句,根据统计不同引擎的各自的总翻译次数及用户所收藏该语句、播放该语句的频次,计算相应翻译引擎的翻译结果的加权使用频次和计算人均使用频次作为质量分,并以质量分占所有引擎的质量分加和的比例为概率,概率最高的翻译引擎则作为本次语句请求的最优翻译引擎;步骤3:将上述的得到的最优翻译引擎作为请求此语句的优先使用引擎,调度该翻译引擎来翻译用户所请求的语句,得到翻译结果,返回给用户。 A real-time translation quality evaluation method, comprising the following steps: Step 1: The translation request user, receiving a user-initiated statement; Step 2: Integrated plurality of translation engines are receiving the user-initiated statement, in accordance with statistical their total translation number and users of different engines that the statement collection, playback frequency of the statement, weighted corresponding translation translation engines use frequency and calculate per capita frequency of use as a mass fraction, and the quality of sub-accounts for all engines and adding a mass fraction ratio of probability, the optimal translation engine of the translation engine with the highest probability as the present request statement; step 3: the above obtained optimal translation engine using the engine as a priority request this statement, the schedule translation engine to translate the statement requested by the user to obtain a translation result, returned to the user. 在完成步骤3后,更新所述最优翻译引擎下对用户所发起的该语句的翻译频次,提起该语句翻译请求的用户在使用翻译结果的后续行为,作为日志发送给质量评估数据库,用于后续的评价和对选择最优翻译引擎的动态修正。 After the completion of step 3, the update frequency translation of the statement of the user initiated the optimal translation engine, the subsequent behavior of the user lifting the statement is translated using the translation request, and transmits the log to the database as a quality assessment for subsequent amendments to the dynamic evaluation and choose the best translation engines.
  2. 2.根据权利要求1所述的一种翻译质量实时评价方法,其特征在于:在完成步骤3后,更新所述最优翻译引擎下对用户所发起的该语句的翻译频次,提起该语句翻译请求的用户在使用翻译结果的后续行为,作为日志发送给质量评估数据库,用于后续的评价和对选择最优翻译引擎的动态修正。 2. According to a translation in real time quality evaluation method according to claim 1, wherein: after completion of step 3, the update frequency translation at the optimal translation engine for the user initiated the statement, the statement filed Translation requested by the user using the translation results subsequent behavior, as a log to a transmission quality assessment database for subsequent evaluation and selection of the optimal dynamic correction of the translation engine.
  3. 3.根据权利要求1或2所述的一种翻译质量实时评价方法,其特征在于:质量评估数据库根据上报的日志信息,并采集用户的位置信息来判断用户所在地及是否在国外,结合用户地理位置情况作为衡量翻译质量的辅助因素,便可设定区域范围,得到该区域范围的最优翻译引擎。 3. According to a real-time translation quality evaluation method according to claim 1, characterized in that: quality evaluation information database according to the reported log, and a collection position information of the user and determines whether the user is located in a foreign country, the user geographic binding location cases as a secondary factor to measure the quality of translations, you can set the area range to give the region-wide optimal translation engine.
  4. 4.根据权利要求1所述的一种翻译质量实时评价方法,其特征在于:针对不同用户的相同翻译请求,不同用户使用不同引擎获得翻译结果,并通过分析处理后续用户对翻译结果在不同时间、不同地域的使用方式与频次,量化评估不同翻译引擎对此语句的翻译质量,从而为其他用户提供此语句的最好的翻译结果。 4. According to a translation in real time quality evaluation method according to claim 1, wherein: for the same translation request different users, different users get different translation engines, and subsequent analysis by the user at different times of the translation , use of the frequency of different regions, different quantitative assessment of translation quality translation engine of this statement in order to provide the best translation of this statement for other users. 通过这种综合分析和评估的方式,能够获得更优的翻译结果。 By way of this comprehensive analysis and assessment, we can get better translation results.
CN 201610272936 2016-04-29 2016-04-29 One kind of real-time translation quality evaluation method CN106021239B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN 201610272936 CN106021239B (en) 2016-04-29 2016-04-29 One kind of real-time translation quality evaluation method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN 201610272936 CN106021239B (en) 2016-04-29 2016-04-29 One kind of real-time translation quality evaluation method

Publications (2)

Publication Number Publication Date
CN106021239A true true CN106021239A (en) 2016-10-12
CN106021239B CN106021239B (en) 2018-10-26

Family

ID=57081012

Family Applications (1)

Application Number Title Priority Date Filing Date
CN 201610272936 CN106021239B (en) 2016-04-29 2016-04-29 One kind of real-time translation quality evaluation method

Country Status (1)

Country Link
CN (1) CN106021239B (en)

Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1465018A (en) * 2000-05-11 2003-12-31 南加利福尼亚大学 Machine translation mothod
CN1530861A (en) * 2003-02-24 2004-09-22 微软公司 Language translating method and system
WO2010052696A1 (en) * 2008-11-05 2010-05-14 Ubstream Ltd. Session initiation protocol in multi-cast/unicast system for connection between users behind nat and connection between server and users behind nat
CN102253930A (en) * 2010-05-18 2011-11-23 腾讯科技(深圳)有限公司 Method and device for translating text
CN102446169A (en) * 2010-10-13 2012-05-09 张龙哺 Translation system by utilizing online translation services
CN103914446A (en) * 2013-01-08 2014-07-09 崴强科技股份有限公司 Translation method and system
CN104011712A (en) * 2011-06-24 2014-08-27 谷歌公司 Evaluating query translations for cross-language query suggestion
CN104090870A (en) * 2014-06-26 2014-10-08 武汉传神信息技术有限公司 Pushing method of online translation engines
CN105051728A (en) * 2013-01-03 2015-11-11 时新公司 Data base query translation system

Patent Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1465018A (en) * 2000-05-11 2003-12-31 南加利福尼亚大学 Machine translation mothod
CN1530861A (en) * 2003-02-24 2004-09-22 微软公司 Language translating method and system
WO2010052696A1 (en) * 2008-11-05 2010-05-14 Ubstream Ltd. Session initiation protocol in multi-cast/unicast system for connection between users behind nat and connection between server and users behind nat
CN102253930A (en) * 2010-05-18 2011-11-23 腾讯科技(深圳)有限公司 Method and device for translating text
CN102446169A (en) * 2010-10-13 2012-05-09 张龙哺 Translation system by utilizing online translation services
CN104011712A (en) * 2011-06-24 2014-08-27 谷歌公司 Evaluating query translations for cross-language query suggestion
CN105051728A (en) * 2013-01-03 2015-11-11 时新公司 Data base query translation system
CN103914446A (en) * 2013-01-08 2014-07-09 崴强科技股份有限公司 Translation method and system
CN104090870A (en) * 2014-06-26 2014-10-08 武汉传神信息技术有限公司 Pushing method of online translation engines

Also Published As

Publication number Publication date Type
CN106021239B (en) 2018-10-26 grant

Similar Documents

Publication Publication Date Title
Moyers et al. Client language as a mediator of motivational interviewing efficacy: Where is the evidence?
Weyuker et al. Experience with performance testing of software systems: issues, an approach, and case study
Kauffman et al. International diffusion of digital mobile technology: A coupled-hazard state-based approach
Czernich et al. Broadband infrastructure and economic growth
Chanda et al. Dual economies and international total factor productivity differences: Channelling the impact from institutions, trade, and geography
Mazzanti et al. Examining the factors influencing environmental innovations
Bethem et al. Establishing the fitness for purpose of mass spectrometric methods
US20140214880A1 (en) System and methods for Predicting Query Execution Time for Concurrent and Dynamic Database Workloads
CN101128007A (en) Testing method for mobile communication terminal
CN102413489A (en) Automatic test method for WiFi (Wireless Fidelity) network connection of mobile phone
Herzer et al. FDI and Income Inequality—Evidence from L atin A merican Economies
JP2006101160A (en) Scenario forming device, false base station, and scenario forming program, and recording medium
CN103152599A (en) Mobile video service user experience quality evaluation method based on ordinal regression
Dutta et al. Benchmarking European software management practices
Klein et al. Performance evaluation of NoSQL databases: a case study
US20130067440A1 (en) System and method for sql performance assurance services
CN101110089A (en) Method and system for data digging and model building
CN103685502A (en) Message pushing method, device and system
US20140358605A1 (en) Methods and systems for crowdsourcing a task
Terziev Social technology as a method for management of the social processes
CN101998472A (en) Complaint pre-treatment method as well as complaint treatment method, device and system
CN103647671A (en) Gur Game based crowd sensing network management method and system
Jeners et al. Harmonizing software development processes with software development settings–a systematic approach
De Moor et al. Linking users' subjective QoE evaluation to signal strength in an IEEE 802.11 b/g wireless LAN environment
CN104572444A (en) Cloud testing platform for game performance and testing method for cloud testing platform

Legal Events

Date Code Title Description
C06 Publication
C10 Entry into substantive examination
CB03
GR01