DeepAI AI Chat
Log In Sign Up

UserIdentifier: Implicit User Representations for Simple and Effective Personalized Sentiment Analysis

by   Fatemehsadat Mireshghallah, et al.
University of California, San Diego

Global models are trained to be as generalizable as possible, with user invariance considered desirable since the models are shared across multitudes of users. As such, these models are often unable to produce personalized responses for individual users, based on their data. Contrary to widely-used personalization techniques based on few-shot learning, we propose UserIdentifier, a novel scheme for training a single shared model for all users. Our approach produces personalized responses by adding fixed, non-trainable user identifiers to the input data. We empirically demonstrate that this proposed method outperforms the prefix-tuning based state-of-the-art approach by up to 13 that, unlike prior work, this method needs neither any additional model parameters nor any extra rounds of few-shot fine-tuning.


A Weak Supervision Approach for Few-Shot Aspect Based Sentiment

We explore how weak supervision on abundant unlabeled data can be levera...

Towards Personalized Intelligence at Scale

Personalized Intelligence (PI) is the problem of providing customized AI...

Efficient K-Shot Learning with Regularized Deep Networks

Feature representations from pre-trained deep neural networks have been ...

Earning Extra Performance from Restrictive Feedbacks

Many machine learning applications encounter a situation where model pro...

Impersonation: Modeling Persona in Smart Responses to Email

In this paper, we present design, implementation, and effectiveness of g...

Efficient Dynamic WFST Decoding for Personalized Language Models

We propose a two-layer cache mechanism to speed up dynamic WFST decoding...

Why So Toxic? Measuring and Triggering Toxic Behavior in Open-Domain Chatbots

Chatbots are used in many applications, e.g., automated agents, smart ho...