-
1.发明公开公开(公告)号：US20230237275A1
公开(公告)日：2023-07-27
申请号：US17830889
申请日：2022-06-02
申请人： salesforce.com, inc.
发明人： Guangsen Wang , Samson Min Rong Tan , Shafiq Rayhan Joty , Gang Wu , Chu Hong Hoi , Ka Chun Au
IPC分类号： G06F40/35 , G06F40/40 , H04L51/02 , G06F40/186
CPC分类号： G06F40/35 , G06F40/40 , H04L51/02 , G06F40/186
摘要： Embodiments provide a software framework for evaluating and troubleshooting real-world task-oriented bot systems. Specifically, the evaluation framework includes a generator that infers dialog acts and entities from bot definitions and generates test cases for the system via model-based paraphrasing. The framework may also include a simulator for task-oriented dialog user simulation that supports both regression testing and end-to-end evaluation. The framework may also include a remediator to analyze and visualize the simulation results, remedy some of the identified issues, and provide actionable suggestions for improving the task-oriented dialog system.
-
公开(公告)号：US11615240B2
公开(公告)日：2023-03-28
申请号：US16581035
申请日：2019-09-24
申请人： salesforce.com, inc.
IPC分类号： G06F40/205
摘要： Embodiments described herein provide an attention-based tree encoding mechanism. Specifically, the attention layer receives as input the pre-parsed constituency tree of a sentence and the lower-layer representations of all nodes. The attention layer then performs upward accumulation to encode the tree structure from leaves to the root in a bottom-up fashion. Afterwards, weighted aggregation is used to compute the final representations of non-terminal nodes.
-
公开(公告)号：US20220164547A1
公开(公告)日：2022-05-26
申请号：US17150988
申请日：2021-01-15
申请人： salesforce.com, inc.
IPC分类号： G06F40/45 , G06N3/08 , G06F40/289 , G06F40/30
摘要： Embodiments described herein provide adversarial attacks targeting the cross-lingual generalization ability of massive multilingual representations, demonstrating their effectiveness on multilingual models for natural language inference and question answering. An efficient adversarial training scheme can thus be implemented with the adversarial attacks, which takes the same number of steps as standard supervised training and show that it encourages language-invariance in representations, thereby improving both clean and robust accuracy.
-
公开(公告)号：US11782686B2
公开(公告)日：2023-10-10
申请号：US17459968
申请日：2021-08-27
申请人： salesforce.com, inc.
发明人： Yue Wang , Weishi Wang , Shafiq Rayhan Joty , Chu Hong Hoi
CPC分类号： G06F8/427 , G06F18/214 , G06F40/20 , G06N3/047 , G06N3/084
摘要： Embodiments described herein a code generation and understanding model that builds on a Transformer-based encoder-decoder framework. The code generation and understanding model is configured to derive generic representations for programming language (PL) and natural language (NL) in code domain via pre-training on unlabeled code corpus, and then to benefit many code-related downstream tasks with fine-tuning. Apart from the denoising sequence-to-sequence objectives widely adopted for pre-training on natural language, identifier tagging and prediction pre-training objective is adopted to enable the model to better leverage the crucial token type information from PL, which specifically are the identifiers assigned by developers.
-
5.发明申请公开(公告)号：US20210375280A1
公开(公告)日：2021-12-02
申请号：US17014458
申请日：2020-09-08
申请人： salesforce.com, inc.
发明人： Weishi Wang , Shafiq Rayhan Joty , Chu Hong Hoi
摘要： Embodiments described herein provide a dynamic topic tracking mechanism that tracks how the conversation topics change from one utterance to another and use the tracking information to rank candidate responses. A pre-trained language model may be used for response selection in the multi-party conversations, which consists of two steps: (1) a topic-based pre-training to embed topic information into the language model with self-supervised learning, and (2) a multi-task learning on the pretrained model by jointly training response selection and dynamic topic prediction and disentanglement tasks.
-
公开(公告)号：US20210049236A1
公开(公告)日：2021-02-18
申请号：US16581035
申请日：2019-09-24
申请人： salesforce.com, inc.
IPC分类号： G06F17/27
摘要： Embodiments described herein provide an attention-based tree encoding mechanism. Specifically, the attention layer receives as input the pre-parsed constituency tree of a sentence and the lower-layer representations of all nodes. The attention layer then performs upward accumulation to encode the tree structure from leaves to the root in a bottom-up fashion. Afterwards, weighted aggregation is used to compute the final representations of non-terminal nodes.
-
公开(公告)号：US11755847B2
公开(公告)日：2023-09-12
申请号：US17150988
申请日：2021-01-15
申请人： salesforce.com, inc.
IPC分类号： G06F40/45 , G06F40/30 , G06F40/289 , G06N3/08
CPC分类号： G06F40/45 , G06F40/289 , G06F40/30 , G06N3/08
摘要： Embodiments described herein provide adversarial attacks targeting the cross-lingual generalization ability of massive multilingual representations, demonstrating their effectiveness on multilingual models for natural language inference and question answering. An efficient adversarial training scheme can thus be implemented with the adversarial attacks, which takes the same number of steps as standard supervised training and show that it encourages language-invariance in representations, thereby improving both clean and robust accuracy.
-
8.发明授权公开(公告)号：US11580975B2
公开(公告)日：2023-02-14
申请号：US17014458
申请日：2020-09-08
申请人： salesforce.com, inc.
发明人： Weishi Wang , Shafiq Rayhan Joty , Chu Hong Hoi
摘要： Embodiments described herein provide a dynamic topic tracking mechanism that tracks how the conversation topics change from one utterance to another and use the tracking information to rank candidate responses. A pre-trained language model may be used for response selection in the multi-party conversations, which consists of two steps: (1) a topic-based pre-training to embed topic information into the language model with self-supervised learning, and (2) a multi-task learning on the pretrained model by jointly training response selection and dynamic topic prediction and disentanglement tasks.
-
公开(公告)号：US20220108169A1
公开(公告)日：2022-04-07
申请号：US17162289
申请日：2021-01-29
申请人： salesforce.com, inc.
发明人： Amrita Saha , Shafiq Rayhan Joty , Chu Hong Hoi
摘要： Embodiments described herein provide systems and methods for a partially supervised training model for questioning answering tasks. Specifically, the partially supervised training model may include two modules—a query parsing module and a program execution module. The query parsing module parses queries into a grogram, and the program execution module execute the program to reach an answer through explicit reasoning and partial supervision. In this way, the partially supervised training model can be trained with answers as supervision, obviating the need for supervision by gold program operations and gold query-span attention at each step of the program.
-
公开(公告)号：US11256754B2
公开(公告)日：2022-02-22
申请号：US16869903
申请日：2020-05-08
申请人： salesforce.com, inc.
IPC分类号： G06F16/9032 , G06F40/284 , G10L15/18 , G10L15/16
摘要： Embodiments described herein provide systems and methods for generating an adversarial sample with inflectional perturbations for training a natural language processing (NLP) system. A natural language sentence is received at an inflection perturbation module. Tokens are generated from the natural language sentence. For each token that has a part of speech that is a verb, adjective, or an adverb, an inflected form is determined. An adversarial sample of the natural language sentence is generated by detokenizing inflected forms of the tokens. The NLP system is trained using the adversarial sample.
-
-
-
-
-
-
-
-
-
搜索结果
15 条记录 (耗时 0.013 秒)
