Amazon Technologies, Inc.

Ramesh M Nallapati

Bing Xiang

Sudipta Sengupta

Zhiguo Wang

Patrick Ng

Stephen Michael Ash

Atul Deo

Andrew Oliver Arnold

Sharanabasappa Parashuram Revadigar

Timothy Jones

Parminder Bhatia

Henghui Zhu

Srinivas Iragavarapu

Hanbo Li

Jun Wang

Rama Krishna Sandeep Pokkunuri

Matthew Lee

Yuchen Tian

Yung Haw Wang

Gregory David Adams

Ankur Deepak Desai

Praphruetpong Athiwaratkun

Xiaofei Ma

Dejiao Zhang

Peng Xu

Mukul Vijay Karnik

Cicero Nogueira Dos Santos

Douglas Scott Cerny

Anuroop Arora

Nanyan Li

Jiarong Jiang

Zijian Wang

Stephanie Weeks

Yanitsa Donchev

Rishav Chakravarti

Donald Harold Rivers Weidner

Deepak Shantha Murthy

Zhiheng Huang

Vamshidhar Krishnamurthy Dantu

Wei Xiao

Alexander Johannes Smola

Dimitrios Soulios

Saurabh Kumar Singh

Yong Yuan

Yifan Gao

Qiang Yu

Sujan Kumar Gonugondla

Krishnakumar Rajagopalan

Dong Wang

Anuj Chauhan

Jiacheng Guo

Sri Ranga Akhilesh Bontala

Ankit Sultania

Arvind Arikatla

Feng Nan

Wuwei Lan

Kaustubh Kishor Khanke

Xiaokai Wei

Bohan Yao

Wei Fang

Lei Gao

Milan Saini

Venkat Rakshith Reddy Swamireddy

Sathish Arumugam Selvaraj

Wasi Uddin Ahmad

Hantian Ding

Ramana Keerthi

Zixuan Lin

Mingyue Shang

Jean-Pierre Dodel

Srikanth Prabala

Haifeng Qian

Sai Bharadwaj Kanduri

Code completion suggestions may be proactively obtained and validated. An event that triggers obtaining a code completion suggestion for inclusion in a code file being edited using an integrated development environment may be detected. The code completion suggestion may be obtained. The characters of the code completion suggestion may be compared with characters added to the code file after the detection of the event that triggered obtaining the code completion suggestion to determine whether the code completion suggestion is valid. A valid code completion suggestion may then be displayed.

Validating and providing proactively generated code completion suggestions for code development

Techniques for using a quantized and/or fused model are described. In some examples, a service is to receive a request to use a trained model, the request including input data; apply a trained model to the input data, the application of the trained model includes fusing one or more matrix multiplication operations with element-wise operations; and output a result from the trained model.

Large language models utilizing element-wise operation-fusion

Systems and methods develop and apply one or more extractive summarization models for locating contact center conversation details in a transcript, extracting pertinent verbiage, and, in a transformation of the communication details, automatically generating summaries at one or more levels of abstraction, the summaries in full sentences, in a manner that a contact center agent understands. The models are trained using machine learning algorithms.

Systems and methods for automated communication summarization

A schema and cell value aware Named Entity Recognition (NER) model is used to perform natural language queries. Natural language queries may be received via an interface of a natural language query processing system. A fuzzy search may be performed that allows non-exact matches for column names or cell values of data sets potentially used to answer the natural language query. An NER model that adds a type embedding for an exact match of a column name or cell found in the fuzzy search that corresponds to a span of one or more words may be applied as part of generating the entity prediction for the natural language query. One or more queries to at least one of the data sets may be performed to return a result to the natural language query using the entity prediction generated by the NER machine learning model.

Schema and cell value aware named entity recognition model for executing natural language queries

Techniques for handling natural language query processing are described. In some examples, a sequence-to-sequence model is used to handle a natural language query. Post-processing of a result of the sequence-to-sequence model utilizes fine-grained information from an entity linker. In some examples, the sequence-to-sequence model and aspects of a natural language query pipeline are used to handle a natural language query.

Natural language query processing

Techniques for predicting an answer to a question using a machine learning model are described. In some examples, the model predicts one or more answers to the question by: predicting at least two answers to the question using a first component of the question-answer model from a set of passages, generating, using a second component of the question-answer model, at least one question for each of the predicted at least two answers, and performing roundtrip predictions until each generated question only has one answer.

Questions disambiguation using generative evidence fusion and round-trip prediction

Evaluation data sets may be programmatically generated for code generation models. An evaluation data set is obtained that includes items that correspond to different evaluation tests for a code generation system. The individual items of the evaluation data set maybe converted, including the conversion of a function signature for the items, the test statements for the items and using a code generation system to generate the body of the function.

Programmatically generating evaluation data sets for code generation models

Systems and methods to detect themes in contacts data. Contacts data may be encoded as text (e.g., chat logs), audio (e.g., audio recordings), and various other modalities. Text-based transcripts of contacts data may be parsed into turns, an issue turn may be detected using a machine learning model, a key phrase may be extracted from the issue turn. Key phrases from across multiple contacts data may be clustered to identify themes.

Programmatic theme detection in contacts analytics service

Pre-fix matching may constrain the generation of next token predictions. Input text to perform a next token prediction may be received. Multiple tokens may be determined from the input text, including a partial token. From possible tokens, one or more matching possible tokens with the partial token may be identified. Next token predictions may then be filtered using the identified possible tokens in order to ensure that the partial token is matched.

Constrained prefix matching for generating next token predictions

Interactive assistances for executing natural language queries to data sets may be performed. A natural language query may be received. Candidate entity linkages may be determined between an entity recognized in the natural language query and columns in data sets. The candidate linkages may be ranked according to confidence scores which may be evaluated to detect ambiguity for an entity linkage. Candidate entity linkages may be provided to a user via an interface to select an entity linkage to use as part of completing the natural language query.

Interactive assistance for executing natural language queries to data sets

Multiple stage filtering may be implemented for natural language query processing pipelines. Natural language queries may be received at a natural language query processing system and processed through a query language processing pipeline. The query language processing pipeline may filter candidate linkages for a natural language query before performing further filtering of the candidate linkages in the natural language query processing pipeline as part of generating an intermediate representation used to execute the natural language query.

Multiple stage filtering for natural language query processing pipelines

Query restatements may be provided for explaining natural language query results. A natural language query is received at a natural language query processing system. An intermediate representation of the natural language query is generated for executing the natural language query. The intermediate representation is translated into a natural language restatement of the natural language query. The natural language restatement is provided with a result of the natural language query via an interface of the natural language query processing system.

Providing query restatements for explaining natural language query results

Techniques for displaying a search are described. An exemplary method includes receiving a search query, performing the search query on a plurality of documents, the documents including text passages, to generate a search query result, determining an aspect of the search query result that has a confidence value that exceeds a first confidence threshold with respect to its relevance to the search query; and, displaying the search result including an emphasis on the aspect of the result exceeds the first confidence threshold.

Systems, apparatuses, and methods for providing emphasis in query results

Growing community of inventors

New Canaan, CT, United States of America

Ramesh M Nallapati