-
ACL 20232023NLP models often degrade in performance when real world data distributions differ markedly from training data. However, existing dataset drift metrics in NLP have generally not considered specific dimensions of linguistic drift that affect model performance, and they have not been validated in their ability to predict model performance at the individual example level, where such metrics are often used in
-
ACL 20232023Off-Policy reinforcement learning has been a driving force for the state-of-the-art conversational AIs leading to more natural humanagent interactions and improving the user satisfaction for goal-oriented agents. However, in large-scale commercial settings, it is often challenging to balance between policy improvements and experience continuity on the broad spectrum of applications handled by such system
-
ACL Findings 20232023Existing efforts on text synthesis for codeswitching mostly require training on codeswitched texts in the target language pairs, limiting the deployment of the models to cases lacking code-switched data. In this work, we study the problem of synthesizing codeswitched texts for language pairs absent from the training data. We introduce GLOSS, a model built on top of a pre-trained multilingual machine translation
-
ACL 20232023Language models have been shown to perform better with an increase in scale on a wide variety of tasks via the in-context learning paradigm. In this paper, we investigate the hypothesis that the ability of a large language model to in-context learn-perform a task is not uniformly spread across all of its underlying components. Using a 66 billion parameter language model (OPT-66B) across a diverse set of
-
ACL Findings 20232023Sequence-to-sequence state-of-the-art systems for dialogue state tracking (DST) use the full dialogue history as input, represent the current state as a list with all the slots, and generate the entire state from scratch at each dialogue turn. This approach is inefficient, especially when the number of slots is large and the conversation is long. In this paper, we propose Diable, a new task formalisation
Related content
-
August 15, 2022Data augmentation and post-editing strategies lift Amazon’s submission above competitors.
-
August 02, 2022With an encoder-decoder architecture — rather than decoder only — the Alexa Teacher Model excels other large language models on few-shot tasks such as summarization and machine translation.
-
August 01, 2022McKeown awarded IEEE Innovation in Societal Infrastructure Award and named a member of the American Philosophical Society.
-
July 28, 2022Donato Crisostomi talks about how his mother helped spark a love of knowledge that led him to two science internships at Amazon.
-
July 22, 2022New EMNLP workshop will feature talks, papers, posters, and a competition built around the 50-plus-language, million-utterance MASSIVE dataset.
-
July 15, 2022New method optimizes the twin demands of retrieving relevant content and filtering out bad content.