Recent publications
-
2023We present HumanEvalX and MBXP, execution-based code completion benchmarks in 10+ programming languages. These datasets are generated by our conversion framework that transpiles prompts and test cases from original datasets (HumanEval and MBPP) to the corresponding data in a target language. Based on these benchmarks, we are able to evaluate code generation models in a multilingual fashion, and in particular
-
EACL 20232023Aspect-based sentiment analysis (ABSA) has attracted broad attention due to its commercial value. Natural Language Generation-based (NLG) approaches dominate the recent advance in ABSA tasks. However, current NLG practices are inefficient because most of them directly employ an autoregressive generation framework that cannot efficiently generate location information and semantic representations of ABSA
-
The joint intent classification and slot filling task seeks to detect the intent of an utterance and extract its semantic concepts. In the zeroshot cross-lingual setting, a model is trained on a source language and then transferred to other target languages through multi-lingual representations without additional training data. While prior studies show that pre-trained multilingual sequence-to-sequence
-
EACL 20232023We explore zero-shot adaptation, where a general-domain model has access to customer or domain specific parallel data at inference time, but not during training. We build on the idea of Retrieval Augmented Translation (RAT) where top-k in-domain fuzzy matches are found for the source sentence, and target-language translations of those fuzzy-matched sentences are provided to the translation model at inference
-
2023Query Rewriting (QR) plays a critical role in large-scale dialogue systems for reducing frictions. When there is an entity error, it imposes extra challenges for a dialogue system to produce satisfactory responses. In this work, we propose KG-ECO: Knowledge Graph enhanced Entity COrrection for query rewriting, an entity correction system with corrupt entity span detection and entity retrieval/re-ranking
Related content
-
March 13, 2023Learn how Amazon uses machine-learning techniques to modify different aspects of speech — tone, phrasing, intonation, expressiveness, and accent — to create unique Alexa responses.
-
February 21, 2023University teams are competing to develop a bot that best responds to customer commands in a virtual world.
-
February 15, 2023Second iteration features five new teams.
-
February 09, 2023The collaboration includes Amazon funding for faculty research projects, with an initial focus on machine learning and natural-language processing.
-
February 07, 2023Parmida Beigi, an Amazon senior research scientist, shares a lifetime worth of experience, and uses her skills to help others grow into machine learning career paths.
-
February 06, 2023Methods for controlling the outputs of large generative models and integrating symbolic reasoning with machine learning are among the conference’s hot topics.
-
January 23, 2023Two Alexa AI papers present novel methodologies that use vision and language understanding to improve embodied task completion in simulated environments.
-
January 20, 2023Prompt engineering enables researchers to generate customized training examples for lightweight “student” models.
-
January 18, 2023On natural-language-understanding tasks, student models trained only on task-specific data outperform those trained on a mix that includes generic data.
-
January 13, 2023Using lists of rare or out-of-vocabulary words to bias connectionist temporal classification models enables personalization.
-
January 11, 2023Private aggregation of teacher ensembles (PATE) leads to word error rate reductions of more than 26% relative to standard differential-privacy techniques.
-
January 06, 2023Quantization with self-adjustable centroids, contrastive predictive coding for transfer learning, teacher ensembles for differential privacy, and more — Amazon’s speech research features a battery of cutting-edge machine learning techniques.
-
December 23, 2022Program focuses on diversifying tech-industry talent.
-
December 22, 2022A system built on Amazon Translate reduces the workload of human translators.
-
December 21, 2022Fifth challenge adds new elements and features four new competitors for the $1 million research grant.
-
December 20, 2022Ariadna Sanchez, a scientist who works in polyglot text to speech, draws on her musical background to help find novel solutions.
-
December 19, 2022Transfer learning using limited contrastive data improves formality accuracy without compromising performance.
-
December 14, 2022EMNLP papers examine constrained generation of rewrite candidates and automatic selection of information-rich training data.
-
December 13, 2022Learn what goes into Amazon's effort to develop human-like reasoning for Alexa.
-
December 13, 2022Amazon Machine Learning Fellow Jiao Sun works on strategies to control text generation.
-
December 08, 2022Test set includes 1,150 text segments, each in nine languages.