Customer-obsessed science
Research areas
-
November 16, 202611 min readNew open-source tool turns existing test suites into sets of formal-verification tasks, which catch buggy solutions that tests alone would miss.
-
November 11, 20265 min read
-
-
-
Featured news
-
ICLR 2022 Workshop on Deep Generative Models for Highly Structured Data2022Performance of recommender systems (RecSys) relies heavily on the amount of training data available. This poses a chicken-and-egg problem for early-stage products, whose amount of data, in turn, relies on the performance of their RecSys. In this paper, we explore the possibility of zero-shot learning in RecSys, to enable generalization from an old dataset to an entirely new dataset. We develop, to the best
-
SIGIR 20222022Many IR collections contain forbidden documents (𝐹 -docs), i.e. documents that should not be retrieved to the searcher. In an ideal scenario 𝐹 -docs are clearly flagged, hence the ranker can filter them out, guaranteeing that no 𝐹 -doc will be exposed. However, in real-world scenarios, filtering algorithms are prone to errors. Therefore, an IR evaluation system should also measure filtering quality in
-
DesignCon 20222022Electrostatic discharge (ESD) events can result in soft and hard failures to an integrated circuit (IC). To protect the ICs from ESD, ESD protection structure is critical for chip-level design. Since chip-level internal ESD protection circuit information is often not released to the public, we propose a new modeling methodology using vector network analyzer (VNA), time domain reflectometer (TDR), source
-
ACL 20222022In conversational QA, models have to leverage information in previous turns to answer upcoming questions. Current approaches, such as Question Rewriting, struggle to extract relevant information as the conversation unwinds. We introduce the Common Ground (CG), an approach to accumulate conversational information as it emerges and select the relevant information at every turn. We show that CG offers a more
-
NAACL 20222022Even if recent Transformer-based architectures, such as BERT, achieved impressive results in semantic processing tasks, their fine-tuning stage still requires large scale training resources. Usually, Data Augmentation (DA) techniques can help to deal with low resource settings. In Text Classification tasks, the objective of DA is the generation of well-formed sentences that (i) represent the desired task
Collaborations
View allWhether you're a faculty member or student, there are number of ways you can engage with Amazon.
View all