?Digital assistants have to respond quickly, but correctly—so researchers are studying how real humans navigate that trade-off, to design better machines.語音助手必須快速但正確地對主人做出回復(fù),因此研究人員正在研究真正的人類如何進(jìn)行這種權(quán)衡,從而設(shè)計(jì)出更好的機(jī)器。
? 撰文\播音:克里斯托弗·因塔利亞塔(Christopher Intagliata) 翻譯:陳美娟 校對:張藝簫
? If you've ever used a digital assistant like Siri or Alexa, you know the back and forth doesn't quite have the same rhythm as real human-to-human conversation. The pauses are just a little too long.? 如果你使用過像Siri或Alexa這樣的語音助手,你就會(huì)發(fā)現(xiàn)他們對話的前后節(jié)奏和真正的人與人之間的對話不太一樣。他們停頓的時(shí)間長一點(diǎn)。 "We feel this sort of awkward silence building up."?Sebastian Loth, a research psychologist at the University of Bielefeld in Germany. "If I ask you something and you just don't respond, it feels like, oh my god this silence is almost killing the room and you can feel it literally building up. So we try to avoid that. And that's the kind of effect that you're seeing with Siri taking a second to respond, you're kind of feeling odd about it."? 德國比勒菲爾德大學(xué)的心理學(xué)家塞巴斯蒂安·洛斯(Sebastian Loth)說:“我們感到這種尷尬的沉默正在形成。如果我問你一件事而你就是不回答,我會(huì)有就要窒息在房間里的感覺,并且會(huì)真實(shí)地感覺到尷尬的氛圍在加深。所以我們盡量避免這種情況。這就是Siri需要一秒鐘來回應(yīng)對話給人的感覺,有點(diǎn)奇怪。” To study how humans are able to have such fluent, sometimes even overlapping, conversations, Loth and his team set up what's called a "Ghost in the Machine" experiment, in a barroom situation. Real human customers bellied up to a bar, where a robot bartender was waiting. The robot was actually controlled by human operators behind the scenes, who could see and hear the customers through the robot's eyes and ears.? 為了研究人類是怎樣進(jìn)行如此流暢、有時(shí)甚至是雙方同時(shí)進(jìn)行的對話,洛斯和他的團(tuán)隊(duì)在酒吧里做了一個(gè)名為“機(jī)器中的幽靈”的實(shí)驗(yàn)。真人顧客蜂擁而至,酒吧里有一個(gè)機(jī)器人侍者在那里等著。機(jī)器人實(shí)際上是由臺(tái)后的操作人員控制的,操作人員可以通過機(jī)器人的眼睛和耳朵看到和聽到顧客的舉動(dòng)。 Then Loth and his team observed how the human operators behaved during a couple hundred orders. They found that when the customers started a phrase with "What," the human operators quickly triggered the robot to repeat the offerings of the bar, like "We have coke, orange juice and water," rather than waiting for customers to complete the sentence. But if the customers began a sentence with "I'd like" or "I want," the human operators tended to hesitate, to listen for what came next, rather than acting quickly—and perhaps incorrectly. 洛斯和他的團(tuán)隊(duì)觀察了人類操作員在幾百個(gè)命令中的行為。他們發(fā)現(xiàn),當(dāng)顧客開始說到“什么”時(shí),人類操作員迅速觸發(fā)機(jī)器人語音鍵鈕,讓機(jī)器人重復(fù)酒吧提供的東西,比如“我們有可樂、橙汁和水”,而不是等待顧客說完。但是,如果客戶以“我想”或“我想要”開頭,那么人工操作員傾向于猶豫,傾聽接下來會(huì)發(fā)生什么,而不是迅速采取行動(dòng)——不然也許會(huì)做錯(cuò)。 "What we found was that they distinguish between the type of request. And more specifically by the error or cost of that. If I misunderstand you and give you the wrong drink that is actually quite an awkward situation. I have to apologize, take the drink away from you, and replace it with the appropriate one. So it's a lot of action and maneuvering involved and it's quite embarrassing if the bartender gets it wrong." The details are in the journal?PLOS ONE. [Sebastian Loth et al.,?Confidence in uncertainty: Error cost and commitment in early speech hypotheses] “我們發(fā)現(xiàn)他們注意區(qū)分客戶需求的類型。特別是那些和錯(cuò)誤或成本有關(guān)的需求。如果我誤解了你的意思,給了你錯(cuò)的飲料,那其實(shí)是很尷尬的情況。我得道歉,把飲料拿走,然后換成正確的飲料。所以這涉及到很多行為和策略,如果調(diào)酒師弄錯(cuò)了,那會(huì)很尷尬。”該研究的更多細(xì)節(jié)發(fā)表在“PLOS ONE”雜志上。 Loth says cataloguing interactions like these might help future robots better navigate the continuum between certainty and time: to be able to act quickly on limited evidence, to provide speedy service, but without getting things wrong so often that it annoys the user.? 洛斯說,記錄這些交互能幫助未來的機(jī)器人更好地應(yīng)對準(zhǔn)確性和及時(shí)性之間的連貫性:使它們能夠根據(jù)有限的信息迅速采取行動(dòng),快速提供服務(wù),但不會(huì)因?yàn)轭l繁出錯(cuò)惹惱用戶。 And no, he doesn't really envision replacing human bartenders with robots. "What you'll probably see is that stuff like that will be incorporated in ticket machines, or in booking systems, or in request systems like Siri where you're asking for a route to be displayed on the phone." 當(dāng)然,他不是真的想用機(jī)器人代替人類調(diào)酒師。“您更可能會(huì)看到的是,這樣的機(jī)器會(huì)被并入售票機(jī)、預(yù)訂系統(tǒng)或像Siri這樣你能要求在電話上顯示路線的需求系統(tǒng)。” After all, he says, a real human bartender does a lot more than serve drinks.? 畢竟,洛斯說,真人酒吧招待為顧客提供的服務(wù)不只是倒酒。