-人工智能时代翻译技术研究「兼容并蓄博学笃行人工智能时代人类译者的使命」

2022年9月30日 0 By SDFJKOSD

人工智能时代翻译技术研究「兼容并蓄博学笃行人工智能时代人类译者的使命」

【语言文字】

作者:北京外国语大学英语学院副教授 王颖冲

今年,我在北外开设了“中文文学作品英译”课程。第一周,同学们当堂闭卷翻译了《围城》开篇一小段“红海早过了”。第二周我展示了两份译文供评析,同学们积极进行“自我批评”,指出“例文”在用词方面大大胜过自己。比如它们将“半透明”译成“translucent”,将“酡红”译为“flushedred”,将“海风”译为“seabreeze”,而不少同学只能大致译成“semi-transparent”“red”和“seawind”。也有人提出两则译文句式颇有特色,不符合语法常规,形成了陌生化的文学效果。

热烈讨论后我问大家:这两位优秀的译者是谁呢?答案揭晓:一个是百度翻译,一个是DeepL翻译。同学们面面相觑,这才回过神来,开始给“机翻”挑毛病:从最基本的语法问题,到衔接与连贯,再到文体风格等。这一戏剧性的反转引人深思。一方面,机器翻译发展迅猛,即便处理最具创造力的文学文本也能让读者基本读懂、可接受,翻译质量甚至超过了一部分学生。另一方面,普通的翻译学习者在评价译文质量时还缺乏辨识力。那么,人类译者会被取代吗?

如今,各大翻译引擎都可以提供免费即时翻译,不仅速度惊人,质量也基本能满足日常交际,尤其适合那些量大、时间紧、要求不高的翻译任务。若是重复性和规律性较高的文本,机器翻译比一些人工翻译还要精准。事实上,不少合同、咨询报告和畅销书的翻译都开始采取“机器翻译—人工译后编辑”模式,通过项目管理、人机交互来提高效率,降低成本。这一趋势给翻译工作者带来了无法回避的技术挑战和伦理问题。社会上关于“机器翻译能否取代人类译者”的论说此起彼伏,对群体身份的认同感和自豪感形成了冲击,一些译者和外语专业的学生开始为职业前景担忧。也有一些译者对新技术表现出抗拒,质疑机器翻译的质量,未能正视其在社会生活中的广泛应用和发展潜力。这除了源自传统译者对机辅翻译的不了解,恐怕也是出于对技术解构作用的恐慌。

在机器翻译飞速发展的时代,人类译者何去何从?我想,北外校训“兼容并蓄,博学笃行”极好地概括了当代译者的使命。历史上每一次文化和科技革命都离不开翻译浪潮。译者面对新思想、新知识、新技术,首先要有开放包容的心态,做一个虚心勤勉的学习者,然后才能“择当译之本”,并基于现实语境和具体目的来阐释和传播,完成这项复杂的、创造性的社会活动。在信息化、全球化时代,翻译需求激增,一味排斥机器翻译对于译者个人、社会发展和文明融通都没有益处。未来机辅翻译会像过去的辞书一样普遍。“翻译技术”已被纳入翻译专业的核心课程,而许多语言服务公司的招聘条件中也有“熟练使用翻译软件”这一条。

但同时,译者不能忘记自己“译”的本职。如果依赖机器,对译文的优劣对错缺乏鉴别力,或是明知机器翻译的版本不够好却无力改进,无法对译文终稿的质量负责。届时可能会引发职业伦理和知识产权方面的新问题。时至今日,读者在批评译著文理不通、表达生硬时依然会说“机翻痕迹严重”,而在褒奖优秀译著时则不会说“翻得像机器一样好”,足以证明大众对人类译者有着更高的认可与期待。据称,机器翻译的准确率可达90%,且不谈这一比率是如何测算出来的,即便如此,人类译者仍大有可为。越到最后完善起来就越困难。10%的差异足以构成本质区别,正如人与猫的基因相似度也高达90%,而人与香蕉的基因序列都有60%的相似度。意义的不确定性、翻译的目的性、特殊文类的创造性都决定了翻译是一系列复杂的选择,是人类智慧的结晶。要做好这最后10%,译者必须“博学笃行”。只有夯实母语和外语的基本功,深耕领域知识,才能根据情境做出合理判断和选择,并融入个性化的体验与灵感,创造出不仅仅是正确的,而且是精妙的、恰到好处的译文。

(光明日报记者肖人夫采访整理)

《光明日报》( 2021年10月24日05版)

来源: 光明网-《光明日报》

人工智能化时代演讲稿

信息的智能化加工:指利用人工智能技术加工信息。
人工智能:人造的智能,主要是对人脑思维机理的模拟。
智能化加工所要解决的问题是如何让计算机更加自主地加工信息,减少人的参与,进一步提高信息加工的效率和人性化程度。
智能应用软件处理信息的一般过程:确定信息加工的类型、选择智能软件的类别、选择合适的软件、应用处理、信息的输出和存储。
专家系统:指模仿人类专家来解决专门领域问题的软件系统。专家系统根据某领域一个或多个专家提供的知识和经验,进行推理和判断,模拟人类专家的决策过程,解决那些需要人类专家处理的复杂问题。
模式识别:是指对表征事物或现象的各种形式的(数值、文字、图像和逻辑关系等)信息进行处理和分析,以对事物或现象进行描述、辨认、分类和解释的过程,是信息科学和人工智能的重要组成部分。
机器翻译:利用计算机把一种自然语言转换成另一种自然语言。常见的语言翻译软件有:金山快译、译星、万能对译、Google在线翻译等。
其它应用:智能机器人、计算机博弈、智能代理、机器证明、数据挖掘等。

求英文演讲稿 主题 人工智能 (高中水平) 10分钟演讲的样子

本文 仅供参考, 请自行修改
10 Examples of Artificial Intelligence You’re Using in Daily Life
Internet Tech
Artificial intelligence (AI) might seem like the realm of
science fiction, but you might be surprised to find out that you’re
already using it. AI has a huge effect on your life, whether you’re
aware of it or not, and its influence is likely to grow in the coming
years. Here are 10 examples of artificial intelligence that you’re
already using every day.
Virtual Personal Assistants
Siri, Google Now, and Cortana
are all intelligent digital personal assistants on various platforms
(iOS, Android, and Windows Mobile). In short, they help find useful
information when you ask for it using your voice; you can say “Where’s
the nearest Chinese restaurant?”, “What’s on my schedule today?”,
“Remind me to call Jerry at eight o’clock,” and the assistant will
respond by finding information, relaying information from your phone, or
sending commands to other apps.
AI is important in these apps, as they collect information on your
requests and use that information to better recognize your speech and
serve you results that are tailored to your preferences. Microsoft says
that Cortana “continually learns about its user” and that it will
eventually develop the ability to anticipate users’ needs. Virtual
personal assistants process a huge amount of data from a variety of
sources to learn about users and be more effective in helping them
organize and track their information.
Video Games
One of the instances of AI that most people are probably familiar
with, video game AI has been used for a very long time—since the very
first video games, in fact. But the complexity and effectiveness of that
AI has increased exponentially over the past several decades, resulting
in video game characters that learn your behaviors, respond to stimuli,
and react in unpredictable ways. 2014’s Middle Earth: Shadow of Mordor
is especially notable for the individual personalities given to each
non-player character, their memories of past interaction, and their
variable objectives.
First-person shooters like Far Cry and Call of Duty
also make significant use of AI, with enemies that can analyze their
environments to find objects or actions that might be beneficial to
their survival; they’ll take cover, investigate sounds, use flanking
maneuvers, and communicate with other AIs to increase their chances of
victory. As far as AI goes, video games are somewhat simplistic, but
because of the industry’s huge market, a great deal of effort and money
are invested every year in perfecting this type of AI.
Smart Cars
You probably haven’t seen someone reading the newspaper while driving
to work yet, but self-driving cars are moving closer and closer to
reality; Google’s self-driving car project and Tesla’s “autopilot”
feature are two examples that have been in the news lately. Earlier this
year, the Washington Post reported
on an algorithm developed by Google that could potentially let
self-driving cars learn to drive in the same way that humans do: through
experience.
The AI detailed in this article learned to play simple video games,
and Google will be testing that same intelligence in driving
games before moving onto the road. The idea is that, eventually, the car
will be able to “look” at the road ahead of it and make decisions based
on what it sees, helping it learn in the process. While Tesla’s
autopilot feature isn’t quite this advanced, it’s already being used on
the road, indicating that these technologies are certainly on their way
in.
Purchase Prediction
Large retailers like Target and Amazon stand to make a lot of money
if they can anticipate your needs. Amazon’s anticipatory shipping
project hopes to send you items before you need them,
completely obviating the need for a last-minute trip to the online
store. While that technology isn’t yet in place, brick-and-mortar
retailers are using the same ideas with coupons; when you go to the
store, you’re often given a number of coupons that have been selected by
a predictive analytics algorithm.
This can be used in a wide variety of ways, whether it’s sending you
coupons, offering you discounts, targeting advertisements, or stocking
warehouses that are close to your home with products that you’re likely
to buy. As you can imagine, this is a rather controversial use of AI,
and it makes many people nervous about potential privacy violations from
the use of predictive analytics.
Fraud Detection
Have you ever gotten an email or a letter asking you if you made a
specific purchase on your credit card? Many banks send these types of
communications if they think there’s a chance that fraud may have been
committed on your account, and want to make sure that you approve the
purchase before sending money over to another company. Artificial
intelligence is often the technology deployed to monitor for this type
of fraud.
In many cases, computers are given a very large sample of fraudulent
and non-fraudulent purchases and asked to learn to look for signs that a
transaction falls into one category or another. After enough training,
the system will be able to spot a fraudulent transaction based on the
signs and indications that it learned through the training exercise.
Online Customer Support
Many websites now offer customers the opportunity to chat with a
customer support representative while they’re browsing—but not every
site actually has a live person on the other end of the line. In many
cases, you’re talking to a rudimentary AI. Many of these chat support
bots amount to little more than automated responders, but some of them
are actually able to extract knowledge from the website and present it
to customers when they ask for it.
Perhaps most interestingly, these chat bots need to be adept at
understanding natural language, which is a rather difficult proposition;
the way in which customers talk and the way in which computers talk is
very different, and teaching a machine to translate between the two
isn’t easy. But with rapid advances in natural language processing
(NLP), these bots are getting better all the time.
News Generation
Did you know that artificial intelligence programs can write news stories? According to Wired,
the AP, Fox, and Yahoo! all use AI to write simple stories like
financial summaries, sports recaps, and fantasy sports reports. AI isn’t
writing in-depth investigative articles, but it has no problem with
very simple articles that don’t require a lot of synthesis. Automated
Insights, the company behind the Wordsmith software,
says that e-commerce, financial services, real estate, and other
“data-driven” industries are already benefitting from the app.
Of course, Wordsmith still needs quite a bit of help from an actual
author to get setup and give it the matrix article that data is placed
into. However, the concept has been proven, and it’s likely that we’ll
see more and more reports generated by these means. Moving beyond
data-driven fields will require major leaps in technology, but the
groundwork has been laid, and it seems like it’s only a matter of time
until fully automated reporters become a reality.
Security Surveillance
A single person monitoring a number of video cameras isn’t a very
secure system; people get bored easily, and keeping track of multiple
monitors can be difficult even in the best of circumstances. Which is
why training computers to monitor those cameras makes a great deal of
sense. With supervised training exercises, security algorithms can take
input from security cameras and determine whether there may be a
threat—if it “sees” a warning sign, it will alert human security
officers.
Of course, the number of things that these computers can catch is currently pretty limited—Wired talks about
seeing flashes of color that may indicate an intruder or someone
loitering around a schoolyard. Identifying actions that might imply a
thief in a store are likely beyond the current technological
limitations, but don’t be surprised if this sort of technology debuts in
the near future.
Music and Movie Recommendation Services
While they’re rather simple when compared to other AI systems, apps like Spotify,
Pandora, and Netflix accomplish a useful task: recommending music and
movies based on the interests you’ve expressed and judgments you’ve made
in the past. By monitoring the choices you make and inserting them into
a learning algorithm, these apps make recommendations that you’re
likely to be interested in.
Much of this functionality is dependent on human-assigned factors.
For example, a song might have “driving bass,” “dynamic vocals,” and
“guitar riffs” listed as characteristics; if you like that song, you’ll
probably like other songs that include the same characteristics. This is
the basis of many recommendation services; and while it’s not
futuristically advanced, it does do a pretty good job of helping you
discover new music and movies.
Smart Home Devices
Many smart home devices now include the ability to learn your
behavior patterns and help you save money by adjusting the settings on
your thermostat or other appliances in an effort to increase convenience
and save energy. For example, turning your oven on when you leave work
instead of waiting to get home is a very convenient ability. A
thermostat that knows when you’re home and adjusts the temperature
accordingly can help you save money by not heating the house when you’re
out.
Lighting is another place where you might see basic artificial
intelligence; by setting defaults and preferences, the lights around
your house (both inside and outside) might adjust based on where you are
and what you’re doing; dimmer for watching TV, brighter for cooking,
and somewhere in the middle for eating, for example. The uses of AI in
smart homes are limited only by our imagination.