-
ASRU 20212021End-to-end automatic speech recognition (ASR) systems are increasingly popular due to their relative architectural simplicity and competitive performance. However, even though the average accuracy of these systems may be high, the performance on rare content words often lags behind hybrid ASR systems. To address this problem, second-pass rescoring is often applied leveraging upon language modeling (LM).
-
ACL-IJCNLP 20212021In open-domain question answering, questions are highly likely to be ambiguous because users may not know the scope of relevant topics when formulating them. Therefore, a system needs to find possible interpretations of the question, and predict one or multiple plausible answers. When multiple plausible answers are found, the system should rewrite the question for each answer to resolve the ambiguity. In
-
NeurIPS 2021 Workshop on Data-Centric AI2021All-neural end-to-end (E2E) Spoken Language Understanding (SLU) models can improve performance over traditional compositional SLU models, but have the challenge of requiring high-quality training data with both audio and annotations. In particular they struggle with performance on “golden utterances”, which are essential for defining and supporting features, but may lack sufficient training data. In this
-
IEEE BigData 20212021Knowledge graph enhanced information retrieval systems have attracted considerable attention due to their ability to improve performance and provide additional explainability. As the knowledge graphs usually include fruitful facts, they are also good sources of side information. However, recent studies have shown that the usefulness of knowledge graphs depends highly on their representation, e.g., the embeddings
-
EMNLP 2021 Workshop on Novel Ideas in Learning-to-Learn through Interaction2021Language-guided robots performing home and office tasks must navigate in and interact with the world. Grounding language instructions against visual observations and actions to take in an environment is an open challenge. We present Embodied BERT (EmBERT), a transformer-based model which can attend to high-dimensional, multi-modal inputs across long temporal horizons for language-conditioned task completion
Related content
-
October 16, 2025Amazon vice president and distinguished engineer Marc Brooker explains how agentic systems work under the hood — and how AWS’s new AgentCore framework implements their essential components.
-
October 15, 2025The collaboration will advance research in generative AI, robotics, natural-language processing and cloud computing while fostering innovation in foundational and emerging technologies.
-
September 11, 2025The language AI agents might speak, sharing context without compromising privacy, modeling agentic negotiations, and understanding users’ commonsense policies are some of the open scientific questions that researchers in agentic AI will need to grapple with.
-
August 8, 2025A new philosophy for developing LLM architectures reduces energy requirements, speeds up runtime, and preserves pretrained-model performance.
-
August 4, 2025Translating from natural to structured language, defining truth, and definitive reasoning remain topics of central concern in automated reasoning, but Amazon Web Services’ new Automated Reasoning checks help address all of them.
-
July 31, 2025Using ensembles of agents to generate and refine interactions annotated with chains of thought improves performance on a battery of benchmarks by an average of 29%.