公开(公告)号：US08364485B2

公开(公告)日：2013-01-29

申请号：US11845462

申请日：2007-08-27

Applicant: Tetsuya Nasukawa ,  Diwakar Punjani ,  Shourya Roy ,  L. Venkata Subramaniam ,  Hironori Takeuchi

Inventor： Tetsuya Nasukawa ,  Diwakar Punjani ,  Shourya Roy ,  L. Venkata Subramaniam ,  Hironori Takeuchi

IPC: G10L15/04

CPC classification number: G10L15/26

Abstract: Sentence boundaries in noisy conversational transcription data are automatically identified. Noise and transcription symbols are removed, and a training set is formed with sentence boundaries marked based on long silences or on manual markings in the transcribed data. Frequencies of head and tail n-grams that occur at the beginning and ending of sentences are determined from the training set. N-grams that occur a significant number of times in the middle of sentences in relation to their occurrences at the beginning or ending of sentences are filtered out. A boundary is marked before every head n-gram and after every tail n-gram occurring in the conversational data and remaining after filtering. Turns are identified. A boundary is marked after each turn, unless the turn ends with an impermissible tail word or is an incomplete turn. The marked boundaries in the conversational data identify sentence boundaries.

Abstract translation: 嘈杂会话转录数据中的句子边界自动识别。 删除噪声和转录符号，并且形成一个训练集，其中以基于长期沉默或手写标记的转录数据标记的句子边界。 从训练集确定在句子的开头和结尾出现的头和尾n-gram的频率。 在句子中间出现相当于句子开头或结尾的出现次数的N-gram被过滤掉。 在每个头n-gram之前和之后的每个尾部n-gram出现在对话数据中并且在过滤之后保留边界。 确认车辙。 每转后，边界都会被标记出来，除非转弯以不允许的尾字结束，或者是不完整的转弯。 会话数据中的标记边界识别句子边界。

公开(公告)号：US20240356873A1

公开(公告)日：2024-10-24

申请号：US18639447

申请日：2024-04-18

Applicant: Jason Brewer ,  Wenxiang Chen ,  Michael James Cunningham ,  Dmytro Ishchenko ,  Tanvi Motwani ,  Diwakar Punjani

Inventor： Jason Brewer ,  Wenxiang Chen ,  Michael James Cunningham ,  Dmytro Ishchenko ,  Tanvi Motwani ,  Diwakar Punjani

IPC: H04L51/02 ,  H04L51/216

CPC classification number: H04L51/02 ,  H04L51/216

Abstract: A chatbot system for an interactive platform. The chatbot system receives a prompt from a user and determines an intent of the user using the prompt. If the chatbot system can't determine an intent, the chatbot communicates the prompt as a personality prompt to a generative AI model. If the chatbot system can determine an intent from the prompt, the chatbot system generates an API call to an additional service using the intent. The chatbot system uses values returned by the additional service to generate a hint prompt that is communicated to the generative AI model. The chatbot system receives a response from the generative AI model to the personality prompt or hint prompt and communicates the response to the user.

公开(公告)号：US20090063150A1

公开(公告)日：2009-03-05

申请号：US11845462

申请日：2007-08-27

Applicant: Tetsuya Nasukawa ,  Diwakar Punjani ,  Shourya Roy ,  L. Venkata Subramaniam ,  Hironori Takeuchi

Inventor： Tetsuya Nasukawa ,  Diwakar Punjani ,  Shourya Roy ,  L. Venkata Subramaniam ,  Hironori Takeuchi

IPC: G10L15/04

CPC classification number: G10L15/26

Abstract: Sentence boundaries in noisy conversational transcription data are automatically identified. Noise and transcription symbols are removed, and a training set is formed with sentence boundaries marked based on long silences or on manual markings in the transcribed data. Frequencies of head and tail n-grams that occur at the beginning and ending of sentences are determined from the training set. N-grams that occur a significant number of times in the middle of sentences in relation to their occurrences at the beginning or ending of sentences are filtered out. A boundary is marked before every head n-gram and after every tail n-gram occurring in the conversational data and remaining after filtering. Turns are identified. A boundary is marked after each turn, unless the turn ends with an impermissible tail word or is an incomplete turn. The marked boundaries in the conversational data identify sentence boundaries.

Abstract translation: 嘈杂会话转录数据中的句子边界自动识别。 删除噪声和转录符号，并且形成一个训练集，其中以基于长期沉默或手写标记的转录数据标记的句子边界。 从训练集确定在句子的开头和结尾出现的头和尾n-gram的频率。 在句子中间出现相当于句子开头或结尾的出现次数的N-gram被过滤掉。 在每个头n-gram之前和之后的每个尾部n-gram出现在对话数据中并且在过滤之后保留边界。 确认车辙。 每转后，边界都会被标记出来，除非转弯以不允许的尾字结束，或者是不完整的转弯。 会话数据中的标记边界识别句子边界。