-
ACL 20232023Recent work has shown that large-scale annotated datasets are essential for training state-of-the-art Question Answering (QA) models. Unfortunately, creating this data is expensive and requires a huge amount of annotation work. An alternative and cheaper source of supervision is given by feedback data collected from deployed QA systems. This data can be collected from tens of millions of user with no additional
-
Quantization-aware and tensor-compressed training of transformers for natural language understandingInterspeech 20232023Fine-tuned transformer models have shown superior performances in many natural language tasks. However, the large model size prohibits deploying high-performance transformer models on resource-constrained devices. This paper proposes a quantization-aware tensor-compressed training approach to reduce the model size, arithmetic operations, and ultimately runtime latency of transformer-based models. We compress
-
SIGIR 2023 Workshop on eCommerce2023Pre-trained language models (PLM) excel at capturing semantic similarity in language, while in e-commerce, customer shopping behavior data (e.g., clicks, add-to-cart, purchases) helps establish connections between similar queries based on behavior on products. This work addressed the challenges of using sparse behavior data to build a robust query-to-query similarity prediction model and apply it to a product
-
IJCAI 2023 Workshop on Generalizing from Limited Resources in the Open World2023Unsupervised performance estimation, or evaluating how well models perform on unlabeled data is a difficult task. Recently, a method was proposed by Garg et al. [2022] which performs much better than previous methods. Their method relies on having a score function, satisfying certain properties, to map probability vectors outputted by the classifier to the reals, but it is an open problem which score function
-
ACL 2023 Workshop on Natural Language Reasoning and Structured Explanations2023Most benchmarks for question answering on knowledge bases (KBQA) operate with the i.i.d. assumption. Recently, the GrailQA dataset was established to evaluate zero-shot generalization capabilities of KBQA models. Reasonable performance of current KBQA systems on the zero-shot GrailQA split hints that the field might be moving towards more generalizable systems. In this work, we observe a bias in the GrailQA
Related content
-
August 04, 2021New approach corrects for cases when average improvements are accompanied by specific regressions.
-
July 29, 2021Amazon’s Dan Roth on a hot new research topic — that he’s been studying for more than 25 years.
-
July 19, 2021Five teams to compete for $500,000 first prize; winners will be announced in August 2021.
-
July 15, 2021Hirschberg explains why mastering empathetic speech is critical for successful dialogue systems.
-
July 15, 2021The paper, which received honorable mention at EACL, presents guidelines for better analysis and construction of datasets.
-
July 12, 2021New method uses cross-attention and multitask training to improve the accuracy and training efficiency of video moment retrieval.