-
公开(公告)号：US20200285705A1
公开(公告)日：2020-09-10
申请号：US16399871
申请日：2019-04-30
Applicant: salesforce.com, inc.
Inventor： Stephan ZHENG , Wojciech KRYSCINSKI , Michael SHUM , Richard SOCHER , Caiming XIONG
Abstract: Approaches for determining a response for an agent in an undirected dialogue are provided. The approaches include a dialogue generating framework comprising an encoder neural network, a decoder neural network, and a language model neural network. The dialogue generating framework generates a sketch sentence response with at least one slot. The sketch sentence response is generated word by word and takes into account the undirected dialogue and agent traits of the agent making the response. The dialogue generating framework generates sentence responses by filling the slot with words from the agent traits. The dialogue generating framework ranks the sentence responses according to perplexity by passing the sentence responses through a language model and selects a final response which is a sentence response that has a lowest perplexity.
-
公开(公告)号：US20200184020A1
公开(公告)日：2020-06-11
申请号：US16264392
申请日：2019-01-31
Applicant: salesforce.com, inc.
Inventor： Kazuma HASHIMOTO , Raffaella BUSCHIAZZO , James BRADBURY , Teresa MARSHALL , Caiming XIONG , Richard SOCHER
IPC: G06F17/28
Abstract: Approaches for the translation of structured text include an embedding module for encoding and embedding source text in a first language, an encoder for encoding output of the embedding module, a decoder for iteratively decoding output of the encoder based on generated tokens in translated text from previous iterations, a beam module for constraining output of the decoder with respect to possible embedded tags to include in the translated text for a current iteration using a beam search, and a layer for selecting a token to be included in the translated text for the current iteration. The translated text is in a second language different from the first language. In some embodiments, the approach further includes scoring and pointer modules for selecting the token based on the output of the beam module or copied from the source text or reference text from a training pair best matching the source text.
-
公开(公告)号：US20180143966A1
公开(公告)日：2018-05-24
申请号：US15817153
申请日：2017-11-17
Applicant: salesforce.com, inc.
Inventor： Jiasen LU , Caiming XIONG , Richard SOCHER
Abstract: The technology disclosed presents a novel spatial attention model that uses current hidden state information of a decoder long short-term memory (LSTM) to guide attention and to extract spatial image features for use in image captioning. The technology disclosed also presents a novel adaptive attention model for image captioning that mixes visual information from a convolutional neural network (CNN) and linguistic information from an LSTM. At each timestep, the adaptive attention model automatically decides how heavily to rely on the image, as opposed to the linguistic model, to emit the next caption word. The technology disclosed further adds a new auxiliary sentinel gate to an LSTM architecture and produces a sentinel LSTM (Sn-LSTM). The sentinel gate produces a visual sentinel at each timestep, which is an additional representation, derived from the LSTM's memory, of long and short term visual and linguistic information.
-
14.发明申请公开(公告)号：US20180121788A1
公开(公告)日：2018-05-03
申请号：US15421424
申请日：2017-01-31
Applicant: salesforce.com, inc.
Inventor： Kazuma HASHIMOTO , Caiming XIONG , Richard SOCHER
CPC classification number: G06N3/04 , G06F17/20 , G06F17/2705 , G06F17/2715 , G06F17/274 , G06F17/277 , G06F17/2785 , G06N3/0445 , G06N3/0454 , G06N3/0472 , G06N3/063 , G06N3/08 , G06N3/084 , G10L15/16 , G10L15/18 , G10L25/30
Abstract: The technology disclosed provides a so-called “joint many-task neural network model” to solve a variety of increasingly complex natural language processing (NLP) tasks using growing depth of layers in a single end-to-end model. The model is successively trained by considering linguistic hierarchies, directly connecting word representations to all model layers, explicitly using predictions in lower tasks, and applying a so-called “successive regularization” technique to prevent catastrophic forgetting. Three examples of lower level model layers are part-of-speech (POS) tagging layer, chunking layer, and dependency parsing layer. Two examples of higher level model layers are semantic relatedness layer and textual entailment layer. The model achieves the state-of-the-art results on chunking, dependency parsing, semantic relatedness and textual entailment.
-
15.发明申请公开(公告)号：US20180121787A1
公开(公告)日：2018-05-03
申请号：US15421407
申请日：2017-01-31
Applicant: salesforce.com, inc.
Inventor： Kazuma HASHIMOTO , Caiming XIONG , Richard SOCHER
CPC classification number: G06N3/04 , G06F17/20 , G06F17/2705 , G06F17/2715 , G06F17/274 , G06F17/277 , G06F17/2785 , G06N3/0445 , G06N3/0454 , G06N3/0472 , G06N3/063 , G06N3/08 , G06N3/084 , G10L15/16 , G10L15/18 , G10L25/30
Abstract: The technology disclosed provides a so-called “joint many-task neural network model” to solve a variety of increasingly complex natural language processing (NLP) tasks using growing depth of layers in a single end-to-end model. The model is successively trained by considering linguistic hierarchies, directly connecting word representations to all model layers, explicitly using predictions in lower tasks, and applying a so-called “successive regularization” technique to prevent catastrophic forgetting. Three examples of lower level model layers are part-of-speech (POS) tagging layer, chunking layer, and dependency parsing layer. Two examples of higher level model layers are semantic relatedness layer and textual entailment layer. The model achieves the state-of-the-art results on chunking, dependency parsing, semantic relatedness and textual entailment.
-
Patent Agency Ranking
公开(公告)号：US20210141781A1
公开(公告)日：2021-05-13
申请号：US16680302
申请日：2019-11-11
Applicant: salesforce.com, inc.
Inventor： Ankit CHADHA , Zeyuan CHEN , Caiming XIONG , Ran XU , Richard SOCHER
Abstract: Embodiments described herein provide unsupervised density-based clustering to infer table structure from document. Specifically, a number of words are identified from a block of text in an noneditable document, and the spatial coordinates of each word relative to the rectangular region are identified. Based on the word density of the rectangular region, the words are grouped into clusters using a heuristic radius search method. Words that are grouped into the same cluster are determined to be the element that belong to the same cell. In this way, the cells of the table structure can be identified. Once the cells are identified based on the word density of the block of text, the identified cells can be expanded horizontally or grouped vertically to identify rows or columns of the table structure.
-
公开(公告)号：US20210103816A1
公开(公告)日：2021-04-08
申请号：US17122894
申请日：2020-12-15
Applicant: salesforce.com, inc.
Inventor： James BRADBURY , Stephen Joseph MERITY , Caiming XIONG , Richard SOCHER
Abstract: The technology disclosed provides a quasi-recurrent neural network (QRNN) encoder-decoder model that alternates convolutional layers, which apply in parallel across timesteps, and minimalist recurrent pooling layers that apply in parallel across feature dimensions.
-
公开(公告)号：US20200272940A1
公开(公告)日：2020-08-27
申请号：US16398757
申请日：2019-04-30
Applicant: salesforce.com, inc.
Inventor： Lichao Sun , Caiming XIONG , Jia LI , Richard SOCHER
Abstract: Approaches for private and interpretable machine learning systems include a system for processing a query. The system includes one or more teacher modules for receiving a query and generating a respective output, one or more privacy sanitization modules for privacy sanitizing the respective output of each of the one or more teacher modules, and a student module for receiving a query and the privacy sanitized respective output of each of the one or more teacher modules and generating a result. Each of the one or more teacher modules is trained using a respective private data set. The student module is trained using a public data set. In some embodiments, human understandable interpretations of an output from the student module is provided to a model user.
-
公开(公告)号：US20200084465A1
公开(公告)日：2020-03-12
申请号：US16687405
申请日：2019-11-18
Applicant: Salesforce.com, inc.
Inventor： Yingbo ZHOU , Luowei ZHOU , Caiming XIONG , Richard SOCHER
IPC: H04N19/46 , H04N19/132 , H04N19/126 , H04N19/33 , H04N21/81 , H04N19/187 , H04N19/60 , H04N19/44
Abstract: Systems and methods for dense captioning of a video include a multi-layer encoder stack configured to receive information extracted from a plurality of video frames, a proposal decoder coupled to the encoder stack and configured to receive one or more outputs from the encoder stack, a masking unit configured to mask the one or more outputs from the encoder stack according to one or more outputs from the proposal decoder, and a decoder stack coupled to the masking unit and configured to receive the masked one or more outputs from the encoder stack. Generating the dense captioning based on one or more outputs of the decoder stack. In some embodiments, the one or more outputs from the proposal decoder include a differentiable mask. In some embodiments, during training, error in the dense captioning is back propagated to the decoder stack, the encoder stack, and the proposal decoder.
-
公开(公告)号：US20180144248A1
公开(公告)日：2018-05-24
申请号：US15817165
申请日：2017-11-18
Applicant: salesforce.com, inc.
Inventor： Jiasen LU , Caiming XIONG , Richard SOCHER
Abstract: The technology disclosed presents a novel spatial attention model that uses current hidden state information of a decoder long short-term memory (LSTM) to guide attention and to extract spatial image features for use in image captioning. The technology disclosed also presents a novel adaptive attention model for image captioning that mixes visual information from a convolutional neural network (CNN) and linguistic information from an LSTM. At each timestep, the adaptive attention model automatically decides how heavily to rely on the image, as opposed to the linguistic model, to emit the next caption word. The technology disclosed further adds a new auxiliary sentinel gate to an LSTM architecture and produces a sentinel LSTM (Sn-LSTM). The sentinel gate produces a visual sentinel at each timestep, which is an additional representation, derived from the LSTM's memory, of long and short term visual and linguistic information.
-
-
-
-
-
-
-
-
-
Search Results
31
records
(took 0.014 seconds)
