[Music] service now is a plum company so we provide automation process as a product so if your product can do a little bit of emotional interaction with you having empathy towards your problem that only helps welcome to another episode of tech bites and I'm your host for this episode Bobby Brill but more importantly that is one of our guests on this episode me Dom Kim Senior linguist for generative AI here at service now and along with our other guests today Roberto bachchi and Ryan Dukes we are going to explore the importance of linguistics in making AI successful and the goal in making large language models more human-like and emotionally intelligent for customer interaction but to start us off and to get to know everyone as we are lucky enough to have three guests today Roberto why don't you go first and tell us a bit about your background yeah I'm Roberto Bachi I'm the manager of content development in atg at service now I manage a team of 16 linguist at the moment my background is in linguistics and foreign languages in literature with a ba from University of bologa in Italy and a PhD from Brown University so you are truly an expert in language I hope so me mam uh introduce yourself and tell us a little bit about your background here so hello my name is midam Kim I'm from originally from South Korea and I did my ba there uh St National University and also Masters both in linguistics and then I went to Northwestern University for my Linguistics PhD and my focus uh was always speech sounds and cognitive science and I also taught in the School of Business University of Kansas for eight years uh focusing on the communication between speech sounds and language and conversation and business because in my thoughts everything's Foundation is language and communication and that's how I was led to service now now trying to make bridges between different worlds and try to enhance customers experience with llm okay just how we sound how we present ourselves and how we talk really is that whole key to making us communicate better correct yeah how we sound what not just what we what we say but how we sound is very very important because it has lots of information that's not in the text that's not in the content but uh that kind of speech tones and your voice and how you raise your voice how you amplify your voice how even your gesture everything goes into your communication Ryan um last but not least introduce yourself and tell us how you came about the service now my name Brian dupes I've been at service now about two years prior to that I was a German Professor actually so I have my um PhD in German focusing on Linguistics as well I went to grad school at UT Austin but also lived in Germany a few times and you know wanted to do the transition from academic world service now my main task is working on the question answering the Q&A project to improve the search results and with the development of llms we are able to try to refine the results that people get from there when they when they search a query make something more advanced more user friendly more clear to the point to address what the what the user wants to know about so we are going to try to cover a lot in a short amount of time but Roberto can you give us an overview of what the world of linguistics looks like in Tech um I would say in a tech company linguist can range from a computational linguist who are basically a figure that is a mix of an engineer and a linguist to other linguist who are more similar to storytellers or play writes who write dialogues and are being like creative I would say like to boil it down there are B basically three main things that we do one is creating synthetic data so creating synthetic data is important because it is new data that does not contain Ain private information is not customer data it's creation is really creation basically from scratch the second thing that we do is labeling and leading labeling teams that is also evaluating assessing the data that that we have created and the third part we have not mentioned it yet but is also localization this is maybe kind of task that happens less often but we also localize and translate and adapt English data to other Nations for the creative aspect we create a variety of synthetic data can be dialogues can be isolated utterances can be knowledge based articles can be utterance Maps can be fake incidents or fake uh tickets so this this creative aspect is is is a very important aspect of our job together with another point which is our role as Bridges or intermediaries between on one hand engineers and data scientist and on the other hand for example labeling teams we are in between these two elements of the company so we very often also collaborate in creating guidelines in explaining complex Concepts in a way that is organized and and simple to absorb so just how important is linguistics to making AI successful it's called larged language model right so large language model or this language technology is a big part of the current AI boom and I think that is coming from all our human desire to communicate more effectively and efficiently with larger data and larger audiences from far away from where you are uh in a very convenient way so it is all from our desire to communicate better so in that way Linguistics and linguist and language uh are all very important you know when we're talking about Linguistics we can say like there's like the four seeds that we have so we're we're critical we're creative we're culturally aware and we're communicative in the sense where we can communicate between different teams between like the data and the product between you know the labelers and the engineers these they're so powerful that we need to you know use these more humanistic skills of communication cultural awareness in order to harness the power of llms and ensure that they meet service now's goals of being trustworthy accurate userfriendly and making work more effective yeah language seems to be where some of the pain points happen is that correct from a linguistic point of view yes okay from a Linguistics point of view well explain that explain the difference between that Roberto Linguistics and language and how is that separated or what do we really need to focus on in that aspect yeah we need to focus on on both I would say so language is a human complex communication system that can happen through speech through text or through science uh and linguistic is the scientific study of language and also the structure of the language there are many sub fields in linguistics linguistic can include the study of uh sounds for example phonetics and phology uh it can study word and sentence structure so morphology and syntax it can study meaning so semantics it can study language use so pragmatics and the historical and social aspects of language so historical Linguistics or philology how it's still common to call it today especially in Europe they constantly evolve as technology evolves so this is a point of particular in for us we are in a period of extremely fast technological changes that of course have an impact on Linguistics and vice versa and also Linguistics changes and evolves also with interaction uh with other disciplines for example mid you have studied also cognitive Linguistics that can be a subfield of linguistics yeah so in cognitive Linguistics cognitive Linguistics is a study that explores a relationship between language and cognition and we researchers have been investigating how language reflects and shapes thought processes studying Concepts such just metaphoric concept of lending and the cognitive aspects of grammar for example so basically understanding language as a subart of cognition as we do in cognitive Linguistics is enabling us to study language from a variety of different perspectives including language acquisition language development language deterioration um and language communication sensory perception production neurological mechanisms and multimodal processing and and everything so this really enables uh language studies to so that it can blend into other stud in cognitive science when you're talking about cognitive science is this the idea of how people think or why people think and how does language plug into that all of them all of them so this is not this is not going to be an easy conversation this is a lot of stuff this yeah cognitive science is is a huge it's a it's a vast amount of study and cognitive Linguistics is part of it so this is how we learn with that right way okay soar how how our brain functions and develops and deteriorates um and use and interact uh with exteral environments so that makes a lot of sense if we're if we're constantly reading and listening to something and our entire day is based upon reading and writing if you're working on the Internet or working on anything Tech related or at this point we're talking with service now and talking a lot about you know help desk things and and really interacting with people via copy via text this plays directly into that concept of does the other person I'm interacting with and also the person who's doing the interacting do their minds meet at the same point is that correct it's about interplay of your mental model within yourself and with other people okay does it make sense that makes sense but that I heard you that makes so much sense but it's like wow that that seems very almost science fiction oh I mean that's what we're doing right now that's what I and you are doing right now okay so it's more science science realism then so H how do you apply these Linguistics and Ryan you you have some insight into this how how are we applying Linguistics into into what we're doing there's a lot of ways that uh Linguistics can be applied to very and various topics within academic field of linguistics they make a distinction between theoretical Linguistics and Applied Linguistics um and Applied Linguistics can cover all of kind of the main theoretical aspects of language structure you know the um the sounds the putting words together sentences together pragmatics but rather than focusing only on how language Works understanding how language Works uh in its own right uh Applied Linguistics tries to see how we can apply what we know about how language Works to real world problems um real world situations making making the world better traditionally mli Linguistics is relegated to thinking about like oh it's just language teaching language teacher training and you know how to get students to learn language better but there's really a lot of ways that language can Linguistics is applied um so the you know there um translation forensic Linguistics you know trying to solve Mysteries with it a lot of sociol linguistics issues trying to determine how language is used to Mark somebody's social standing interactional how they're interacting with different people and when it comes to large language models and Jer to AI you know they say Applied Linguistics as kind of like language teaching really what we're trying to do is get large language models to learn how to speak an a language that is more natural more humanlike than just reg kind of regurgitating data so how do we get that answer into a language that somebody can understand better over a chatbot or is that the correct way of thinking about it you know llms are initially created is just by a lot of just feeding it data usually text data that comes from the Internet or comes from just random texts and texts themselves are not humans you know really the things that midam was talking about how interacting the tollen is really um really plays a lot into how what you're trying to communicate because llms are just the way that they work is basically they're given a huge bunch of text and rather than actually understanding how to create language they take the text that they've been given and draw on the probability the statistical probability of what the next word is supposed to be of what the next proper response to a given question would be most likely and because of that they're very good at kind of the really structural parts of language being able to put together words to put together sentences knowing the grammar rules but the other fields of linguistics specifically semantics the study of meaning and pragmatics kind of the study of more interactional aspects of language those can't be gained just from statistical probabilities and those are like the essential parts of human communication so linguists are important because with kind of the base language models they're because they're only based on statistical probabilities they can spit out information that's either like untrue or it's not culturally sensitive and kind of generic so we need to use Linguistics to try to train them to better understand people and to communicate in a way that's more acceptable for normal human users and and Roberto you you you've got some insight into that because I want to ask you how do we get humanlike communication with all of this data so from a linguistic perspective humanizing for example an AI powered bot involves not only mimicking the language patterns of human communication but also understanding and responding to the emotional and cultural uh nuances that are inherent to human communication we don't only communicate words but we we also communicate emotions and uh also our culture so there are several ways an AI powered bot can be humanized one of them for example is natural language generation or nlg so the nlg techniques allow the AI bot to generate responses that mimic natural human language in many ways like AI models can be compared to imitators impersonators mimics they are very good at mimicking the language of humans so energy involves also incorporating variations colloquialisms and conversational tone to make interactions uh feel more human and less robotic another way is the recognition emotional recognition and expression how to express and recognize emotions this enables AI to understand and to respond appropriately to the emotional cues of the user so the model needs to be able to catch to understand the the subtle emotional uh signal that the user is sending this can involve using emotive language language expressing feelings adapting the responses of AI basing them on a detected sentiment and after identifying making the interaction uh resonant emotionally resonant with that sentiment what are some some things that you're seeing or or give us some insight into that process of finding emotion within within the AI uh there can be for example when we create synthetic data for for AI we can take into consideration different personalities if let's say we are recreating dialogues between a US user and AI we can have we can imagine different types of users um they can have like different attitudes toward the Bots um another aspect related to this is that of politeness and empathy basically we need to develop algorithms that simulate empathies empathy and politeness in order that the conversation is on both side respectful and considered of the side of the AI but Al on the side of the user for example I encountered in my career in in different companies let's say when a human interact with a bot for example sometimes the interaction can be very very rude from The Human Side like people if you think of of uh assistants even outside of service now like Alexa or Siri or Google Assistant people may talk to these assistants like servants you know do this for me you know I need the new computer uh I uh you know right we've all been an aggressive user with this type of Technology at some point this is not the case of service now but in other companies many of the devices are also used by children for example what if a child ask a question in a very rude way using bad words like should we actually should a bot actually answer or should the B have a different Behavior Uh similar to to this is uh you know should a user should a polite user be rewarded for asking politely to the bot compared to a rude user I know sure that that's almost even more humanlike that if you're a nice person then I'm going to help you even better like a good a good waiter is a better waiter because his customer is a nicer person exactly is being nice and making people happy what we always want midam you've got I know you've got an opinion on this I guess always because we always want nice people to talk to right um there can be different types of use cases in different types of industry or different types of customers who might want different degrees of this kind of friendliness or warmth uh I did a presentation on my research on that to the um internal engineers at service now and also externally in a conference and their response was that I actually don't need that I don't need that much of friendliness or niceness because I I focus more on the accuracy of the responses of the model so different people might need different levels of friendliness but I guess overall as a conversational partner you have to be nice otherwise the the the other party will not listen to you well well that's an interesting thing you brought up where a a polite interaction May in some cases may slow down down the process is that the right way of looking at it yeah that is possible that is very possible one example I got from my interaction with an engineer was actually that so you have an emergency you like cut your hair cut your hand or whatever I mean it's it's a very very uh emerging situation you just need the an answer me you asked the the question to the LM and then it says H nice to meet you how can I help you then you get so irritated just give me an answer right right right that is possible too this idea of empathy and emotion emotional recognition and expression where we're actually helping our customers is the empathy and emotion um something we're finding that is really important I think so I think so because service now is a platform company so we provide automation process as a product many of the customer facing points or chat Bots it's around uh language and communication all the time that's how customers are experiencing our products when would you use uh uh llm or or any of our products when would you use that yeah you have a problem got a solve my problem you are stressed you are nervous you are mad right so you have this negative feeling and you are full of feeling then if the chat butt is so dry and not really addressing my emotion then then that is just at least not helpful so if your product can do a little bit of emotional interaction with you having empathy towards your problem that only helps so if I can add something to this we are talking of humanizing AI Bots and one thing that service now cares a lot about is trust okay so how is trust built and measured I think having BS and a virtual assistance that are not offensive are of course helpful but also they are sensitive to customers for example in different regions they don't provide harmful answers to the questions of the of the users that's a very important Point trust is measured in how helpful is is my is the solution that I'm giv to you but is also measured the same as a person is a person polite and helping you or is the person offensive and harmful to you so what we are saying here about language also has to do a lot about with trust so there you have it a quick primer on the world of linguistics and generative Ai and if you like what you're hearing please hit subscribe on whatever platform you're listening on so you never miss an episode and for more information you can check out our newly designed docs website docs. servicenow.com I'm Bobby bril thanks for [Music] listening