Asapp, Inc.

Yi Yang

Hugh Nicholas Perkins

Michael Griffiths

Hui Dai

Tao Ma

David Sontag

Sean Adler

Yada Pruksachatkun

Jennifer Marie Seale

Keunwoo Peter Yu

Jordan Louis Swartz

Theodore David Burke

Arzoo Katiyar

Connor Daniel McNabb

Thomas Gregory McKelvey, Jr

A communications session with a user may be automated using a language model. The language model may be instructed to select a next action to be performed where the next action may include transmitting a responsive communication to the user or performing an API call. The prompt used to query the language model may include one or more of the following: a representation of text of the communications session, a list of available API calls, instructions to select a next action, a representation of API calls performed, or a representation of API call responses received. The language model may be sequentially queried to continue the communications session by transmitting responsive communications or performing API calls. In some implementations, a prompt template may be used to generate the prompt and a prompt template may be selected using text of the communications session.

Prompting language models to select API calls

Medical records may be analyzed to identify important items in the text of the medical record. Actionable content may be identified and may be emphasized or extracted from the medical record. Actionable content may be categorized into one or more categories. Identification may include processing using trained models that use contextual information and position information to determine sentence labels.

Extracting clinical follow-ups from discharge summaries

A first named entity recognition (NER) system may be adapted to create a second NER system that is able to recognize a new named entity using few-shot learning. The second NER system may process support tokens that provide one or more examples of the new named entity and may process input tokens that may contain the new named entity. The second NER system may use a classifier of the first NER system to compute support token embeddings from the support tokens and input token embeddings from the input tokens. The second NER system may then recognize the new named entity in the input tokens using abstract tag transition probabilities and/or distances between the support token embeddings and the input token embeddings.

Few-shot named-entity recognition

The present disclosure describes a system, method, and computer program for automatically discovering goals from conversations using neural networks and deep multi-view clustering. A dataset of conversations is partitioned into two views. Vector representations of each view are then generated and clustered in an alternating fashion between views for a number of iterations (i.e., the system alternates between views in generating and clustering vector representations of a view). A first neural network encoder generates the vector representations for the first view, and a second neural network encoder generates the vector representations for the second view. With each semi-iteration, cluster assignments from one view are used to update the encoder for the other view, thus encouraging the two neural network encoders to yield similar cluster assignments. After all the iterations are complete, a user interface enables a user to label each first-view cluster with a goal, where a subset of example utterances is displayed for each cluster.

Automated conversation goal discovery using neural networks and deep multi-view clustering

The present disclosure sets forth a marginal distillation approach to obtaining a unified name-entity recognition (NER) student model from a plurality of pre-trained teacher NER models with different tag sets. Knowledge from the teacher models is distilled into a student model without requiring access to the annotated training data used to train the teacher models. In particular, the system receives a tag hierarchy that combines the different teacher tag sets. The teacher models and the student model are applied to a set of input data sequence to obtain tag predictions for each of the models. A distillation loss is computed between the student and each of the teacher models. If teacher's predictions are less fine-grained than the student's with respect to a node in the tag hierarchy, the student's more fine-grained predictions for the node are marginalized in computing the distillation loss. The overall loss is minimized, resulting in the student model acquiring the collective predictive capabilities of the teacher models.

System, method, and computer program for obtaining a unified named entity recognition model with the collective predictive capabilities of teacher models with different tag sets using marginal distillation

Growing community of inventors

New York, NY, United States of America

Yi Yang