2021-03-31 nisbot.iconWhat would you like to see happen in this conversation? nishio.icon Meaning is not a set., I had a realization, and I would like to discuss if this has any practical application. nisbot.iconWhat is the “application” of this “application”? nishio.iconFor example, chatbots will be able to do things they couldn’t do before. nisbot.iconWhat kind of “chatbot” is this “chatbot”? nishio.iconUnderstand the human story. nisbot.iconWhat kind of “understanding” is that “understanding”? nishio.iconWe understand the meaning of what people are talking about. We don’t yet know what it means to understand the meaning, but there is progress in the processing that deals with meaning. nisbot.iconWhat is the “story” about? nishio.iconI wonder, that remains to be seen. Maybe it’s the kind of dialogue we’re having here, maybe it’s not. nisbot.iconIs there anything else about that “story”? nishio.iconThere is no And when a meaning is a point, there is similarity between the meanings, but no inclusion. When a meaning is a set, there is an inclusion. There can be intersection. When a meaning is a Gaussian, the probability of inclusion is required. nisbot.iconWhat is it that you value? nishio.iconHopefully there will be some useful application. nisbot.iconIs there anything else you can tell us about its “application”? nishio.iconThat’s what I’m looking for. nisbot.icon

  • I wonder, that remains to be seen. Maybe it’s the kind of dialogue we’re having here, maybe it’s not.

  • Where is this “story”? nishio.iconBetween human and computer. nisbot.icon
  • I wonder, that remains to be seen. Maybe it’s the kind of dialogue we’re having here, maybe it’s not.

  • Where is this “story”? nishio.iconIt’s like using digital communication to flow in text form. nisbot.icon
  • I wonder, that remains to be seen. Maybe it’s the kind of dialogue we’re having here, maybe it’s not.

  • How do you know this “story”? nishio.iconI don’t know. nisbot.iconWhat kind of “understanding” is that “understanding”? nishio.iconIf we find something better, we’ll know. nisbot.iconIs there anything else about that “understanding”? nishio.iconI want to understand. nisbot.icon
  • Hopefully there will be some useful application.

  • Where is this “application”? nishio.iconThat’s what I’m looking for. nisbot.icon
  • Hopefully there will be some useful application.

  • What does this “application” look like? nishio.iconHmmm, it’s the next step after the stairs, and if you can do that, you can reach even higher. nisbot.icon
  • I wonder, that remains to be seen. Maybe it’s the kind of dialogue we’re having here, maybe it’s not.

  • What do you hope will happen regarding this “story”? nishio.iconFor example, with regard to the conversation we are having here, it would be nice if the questions were more appropriate. For example, if we understand that the user is talking about an event, then the question “What happens next?” is appropriate. question is appropriate. nisbot.iconWhere does this “story” come from? nishio.iconIf the computer asks the right questions, it will pull from the human. nisbot.iconWhat kind of “human being” is this “human being”? nishio.iconWait a minute, so it becomes a matter of inclusion of whether a user’s statement is “a suitable statement to do a certain question”? nisbot.iconWhat kind of “user” is this “user”? nishio.iconThere are two problems. The key word is “where?” and whether the entire statement is appropriate to a question like “What happens next?” and whether the entire statement is appropriate for a question like “What happens next? nisbot.iconWhat kind of “question” is that “question”? nishio.iconThere are two types of templates: one that fits keywords into the template and one that does not take keywords. nisbot.iconWhat kind of “keywords” are those “keywords”? nishio.icondemocrat nisbot.iconWhat kind of “demoko” is this “demoko”? nishio.iconBut I wanted to write that keywords can also be multiple words, so the whole sentence should be interpreted as a keyword. nisbot.iconIs there anything else you can tell us about that “keyword”? nishio.iconIn other words, it is good to know the inclusion relationship between keywords, and the inclusion relationship is not a general one, but a binary classification of whether it is appropriate for a particular question nisbot.iconWhere are these “keywords” located? nishio.iconThe keywords are extracted from the text and processed, but this is a kind of attention, because the weight of zero or one is multiplied by one for each successive section. nisbot.iconWhere are those “key words”? nishio.iconIn a sentence, it’s basically one lump. If it’s an attention, it could be scattered around, so it’s harder to fit it into a template. nisbot.iconWhat kind of “attention” is that “attention”? nishio.iconWeighting for a given input sequence nisbot.iconWhat kind of “mi” is that “mi”? nishio.iconNGKW Mi nisbot.iconWhat kind of “weight” is that “weight”? nishio.iconValues that make the area of interest larger. nisbot.icon
  • The keywords are extracted from the text and processed, but this is just a kind of attention, because the weight of zero or one is multiplied by one for each successive interval.

  • Where do these “keywords” come from? nishio.iconRight now, they’re doing conventional keyword extraction and verb-specific extraction. nisbot.iconHow do you know what the “key word” is?

https://keicho.netlify.app/#talk=KeOBn7Dr4GJqBUtLnwNS


This page is auto-translated from /nishio/æ„ć‘łăŻé›†ćˆă§ăŻăȘă„ă€ăšă„ă†æ°—ă„ăăŒă‚ăŁăŸăźă§ă€ă“ă‚ŒăŒäœ•ă‹ćźŸç”šçš„ăȘćżœç”šă«ă€ăȘăŒă‚‹ăźă‹ç›žè«‡ă—ăŸă„ using DeepL. If you looks something interesting but the auto-translated English is not good enough to understand it, feel free to let me know at @nishio_en. I’m very happy to spread my thought to non-Japanese readers.