-
ACL 20232023Recent works show the effectiveness of cache-based neural coreference resolution models on long documents. These models incrementally process a long document from left to right and extract relations between mentions and entities in a cache, resulting in much lower memory and computation cost compared to computing all mentions in parallel. However, they do not handle cache misses when high-quality entities
-
ACL Findings 20232023Answering complex questions often requires reasoning over knowledge graphs (KGs). State-of-the-art methods often utilize entities in questions to retrieve local subgraphs, which are then fed into KG encoder, e.g. graph neural networks (GNNs), to model their local structures and integrated into language models for question answering. However, this paradigm constrains retrieved knowledge in local subgraphs
-
Interspeech 20232023Conformer-based end-to-end automatic speech recognition (ASR) models have gained popularity in recent years due to their exceptional performance at scale. However, there are significant computation, memory and latency costs associated with running inference on such models. With the aim of mitigating these issues, we evaluate the efficacy of pruning Conformer layers while fine-tuning only on 20% of the data
-
ACL Findings 20232023Recommending a diversity of product types (PTs) is important for a good shopping experience when customers are looking for products around their high-level shopping interests (SIs) such as hiking. However, the SI-PT connection is typically absent in e-commerce product catalogs and expensive to construct manually due to the volume of potential SIs, which prevents us from establishing a recommender with easily
-
Interspeech 20232023We propose a methodology for information aggregation from the various transformer layer outputs of a generic speech Encoder (e.g. WavLM, HuBERT) for the downstream task of Speech Emotion Recognition (SER). The proposed methodology significantly reduces the dependency of model predictions on linguistic content, while leading to competitive performance without requiring costly Encoder re-training. The proposed
Related content
-
August 25, 2020ACL 2020 keynote presentation given by Amazon Scholar and Columbia University professor Kathleen McKeown.
-
August 21, 2020Watch the recording of Marcu's live interview with Alexa evangelist Jeff Blankenburg.
-
August 20, 2020The team’s non-real-time system is the top performer, while its real-time system finishes third overall and second among real-time systems — despite using only 4% of a CPU core.
-
August 18, 2020New approach scales manageably while achieving state-of-the-art results.
-
August 10, 2020Detecting comic product-related questions could improve customer engagement and Amazon recommendations.
-
August 04, 2020A judge and some of the finalists from the Alexa Prize Grand Challenge 3 talk about the competition, the role of COVID-19, and the future of socialbots.