Square Enix is bringing back the old Dragon Quest Creator game for a free preview of its AI technology
Today Square Enix had a surprise to share in the form of an investigative adventure game titled The Portopia Serial Murder Case.
The name is likely to be familiar to longtime fans of the Enix brand, as it is the return of a 1983 title from dragon quest creator Yuji Horii. It will be released for free. on Steam April 23th.
However, this is not quite the same game as some may remember, as the developer injected modern AI technology into it, including natural language processing, natural language understanding, speech-to-text conversion, and text generation. natural language.
This allows the player to give instructions to the characters in the game using natural language instead of predetermined controls. If you have the required hardware, you can even do it via voice instead of text.
The announcement was accompanied by a trailer, which you can watch below.
This is how Square Enix describes the game.
This software is an educational demonstration of Natural Language Processing (NLP), an artificial intelligence technology, applied to the adventure game “The Portopia Serial Murder Case” (created by Yuji Horii and first published in Japan in 1983). At the time of the game’s original release, most adventure games were played with a “command input” system, in which the player was required to type text to decide their character’s actions. Free text input systems like these allowed players to feel a great deal of freedom. However, they came with a common source of frustration: players knew what action they wanted to take but couldn’t do it because they couldn’t find the correct wording. This issue was caused by PC performance limitations and NLP technology at the time.
40 years have passed since then and PC performance has improved dramatically, as have the capabilities of NLP technology. Using “The Portopia Serial Murder Case” as a test case, we would like to show you the capabilities of modern NLP and the impact it can have on adventure games, as well as deepen your understanding of NLP technologies.
Natural Language Processing (NLP)
Natural language processing is a technology that allows computers to derive meaning from natural language, the kind of language we use in everyday communication. Deep learning performed on a large text dataset makes it possible for the system to understand complex text input (NLU) and generate responses comparable to those typed by humans (NLG).
Natural Language Understanding (NLU)
In order to interact with computers using natural language, the computer needs to understand what its human partner is trying to tell it, regardless of the words it chooses. Natural language understanding is an area of NLP research that aims to make computers correctly understand natural language, where the meaning can often be ambiguous. In this tech preview, NLU is used to help the Junior Detective understand the player’s instructions.
Voice to Text (STT)
Speech-to-Text, or Automatic Speech Recognition (ASR), makes it possible to convert voice input into written text. Using this technology, players can give instructions using their own voices instead of a keyboard. Note that a CUDA-capable GPU and a large amount of VRAM are necessary for a satisfactory experience.
Natural Language Generation (NLG)
The automatic generation of natural text is one of the most important research topics in the field of NLP. For example, research is being done on AI engines that can answer questions instead of human operators, as well as AI-powered chatbots, both of which are expected to have a wide variety of real-world applications. This technology preview originally included a feature based on natural language generation technology, where the system would generate natural responses to questions that did not have a prewritten answer. However, the NLG feature is omitted in this release because there is still a risk of the AI generating unethical responses. Thanks for your understanding. We will consider reintroducing this feature as soon as our research is successful in creating an environment where players can enjoy the experience in peace.