Semantic text matching for long-form documents

JY Jiang, M Zhang, C Li, M Bendersky… - The world wide web …, 2019 - dl.acm.org
Semantic text matching is one of the most important research problems in many domains,
including, but not limited to, information retrieval, question answering, and recommendation …

Comparing retrieval-augmentation and parameter-efficient fine-tuning for privacy-preserving personalization of large language models

A Salemi, H Zamani - arxiv preprint arxiv:2409.09510, 2024 - arxiv.org
Privacy-preserving methods for personalizing large language models (LLMs) are relatively
under-explored. There are two schools of thought on this topic:(1) generating personalized …

EmailSum: Abstractive email thread summarization

S Zhang, A Celikyilmaz, J Gao, M Bansal - arxiv preprint arxiv:2107.14691, 2021 - arxiv.org
Recent years have brought about an interest in the challenging task of summarizing
conversation threads (meetings, online discussions, etc.). Such summaries help analysis of …

Longlamp: A benchmark for personalized long-form text generation

I Kumar, S Viswanathan, S Yerra, A Salemi… - arxiv preprint arxiv …, 2024 - arxiv.org
Long-text generation is seemingly ubiquitous in real-world applications of large language
models such as generating an email or writing a review. Despite the fundamental …

Automated evaluation of personalized text generation using large language models

Y Wang, J Jiang, M Zhang, C Li, Y Liang, Q Mei… - arxiv preprint arxiv …, 2023 - arxiv.org
Personalized text generation presents a specialized mechanism for delivering content that is
specific to a user's personal context. While the research progress in this area has been …

Membership inference on word embedding and beyond

S Mahloujifar, HA Inan, M Chase, E Ghosh… - arxiv preprint arxiv …, 2021 - arxiv.org
In the text processing context, most ML models are built on word embeddings. These
embeddings are themselves trained on some datasets, potentially containing sensitive data …

Context-aware intent identification in email conversations

W Wang, S Hosseini, AH Awadallah… - Proceedings of the …, 2019 - dl.acm.org
Email continues to be one of the most important means of online communication. People
spend a significant amount of time sending, reading, searching and responding to email in …

Privacy regularization: Joint privacy-utility optimization in language models

F Mireshghallah, HA Inan, M Hasegawa… - arxiv preprint arxiv …, 2021 - arxiv.org
Neural language models are known to have a high capacity for memorization of training
samples. This may have serious privacy implications when training models on user content …

Learning with weak supervision for email intent detection

K Shu, S Mukherjee, G Zheng, AH Awadallah… - Proceedings of the 43rd …, 2020 - dl.acm.org
Email remains one of the most frequently used means of online communication. People
spend significant amount of time every day on emails to exchange information, manage …

Searching the enterprise

U Kruschwitz, C Hull - Foundations and Trends® in …, 2017 - nowpublishers.com
Search has become ubiquitous but that does not mean that search has been solved.
Enterprise search, which is broadly speaking the use of information retrieval technology to …