Content-based recommendation systems play a crucial role in delivering personalized content to users in the digital world. In this work, we introduce EmbSum, a novel framework that enables offline pre-computations of users and candidate items while capturing the interactions within the user engagement history. By utilizing the pretrained encoder-decoder model and poly-attention layers, EmbSum derives User Poly-Embedding (UPE) and Content Poly-Embedding (CPE) to calculate relevance scores between users and candidate items. EmbSum actively learns the long user engagement histories by generating user-interest summary with supervision from large language model (LLM). The effectiveness of EmbSum is validated on two datasets from different domains, surpassing state-of-the-art (SoTA) methods with higher accuracy and fewer parameters. Additionally, the model’s ability to generate summaries of user interests serves as a valuable by-product, enhancing its usefulness for personalized content recommendations.

Understanding the semantic meaning of content on the web through the lens of a taxonomy has many practical advantages. However, when building large-scale content classification systems, practitioners are faced with unique challenges involving finding the best ways to leverage the scale and variety of data available on internet platforms. We present learnings from our efforts in building a content classification system for multiple document types at Facebook using Multi-modal Transformers. We empirically demonstrate the effectiveness of multi-lingual, multi-modal and cross-document type learning. We describe effective strategies for exploiting weakly supervised signals as a pre-training step and show that they lead to significant gains in downstream classification accuracy. We also discuss label collection schemes that help minimize the amount of noise in collected data.

Angli Liu, Stephen Soderland, Jonathan Bragg, Christopher H. Lin, Xiao Ling, Daniel S. Weld. Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 2016.

The relationship between vowel formants and the second subglottal resonance (Sg2) has previously been explored in English, German, Hungarian and Korean. Results from these studies indicate that vowel space is categorically divided by Sg2 and that Sg2 correlates well with standing height. One of the goals of this work is to verify if the above findings hold true in Mandarin as well. The correlation between Sg2 and sitting height (trunk length) is also studied. Further, since Mandarin is a tonal language (with more pitch variations compared to English), we study the relationship between Sg2 and fundamental frequency (F0). A new corpus of simultaneous recordings of speech and subglottal acoustics was collected from 20 native Mandarin speakers. Results on this corpus indicate that Sg2 divides vowel space in Mandarin as well, and that it is more correlated with sitting height than standing height. Paired t-tests are conducted on the Sg2 measurements from different vowel parts, which represent different F0 regions. Preliminary results show that there is no statistically-significant variation of Sg2 with F0 within a tone. Index Terms: second subglottal resonance, Mandarin, vowel space, sitting height, tonal language

Communication primitives such as coding and multiple antenna processing have provided significant benefits for traditional wireless systems. Existing designs, however, consume significant power and computational resources, and hence cannot be run on low complexity, power constrained backscatter devices. This paper makes two main contributions: (1) we introduce the first multi-antenna cancellation design that operates on backscatter devices while retaining a small form factor and power footprint, (2) we introduce a novel coding mechanism that enables long range communication as well as concurrent transmissions and can be decoded on backscatter devices. We build hardware prototypes of the above designs that can be powered solely using harvested energy from TV and solar sources. The results show that our designs provide benefits for both RFID and ambient backscatter systems: they enable RFID tags to communicate directly with each other at distances of tens of meters and through multiple walls. They also increase the communication rate and range achieved by ambient backscatter systems by 100X and 40X respectively. We believe that this paper represents a substantial leap in the capabilities of backscatter communication.