Low-resource Personal Attribute Prediction from Conversation

TL;DR

This paper introduces PEARL, a novel framework that effectively predicts personal attributes from conversations in low-resource settings by leveraging unlabeled utterances and combining semantic and co-occurrence information, outperforming existing methods.

Contribution

PEARL is the first framework to utilize unlabeled conversation data for personal attribute prediction without external resources, improving accuracy over previous approaches.

Findings

PEARL outperforms baseline methods on two datasets for personal attribute prediction.

PEARL also achieves superior results on a weakly supervised text classification task.

The iterative refinement process enhances the integration of semantic and co-occurrence information.

Abstract

Personal knowledge bases (PKBs) are crucial for a broad range of applications such as personalized recommendation and Web-based chatbots. A critical challenge to build PKBs is extracting personal attribute knowledge from users' conversation data. Given some users of a conversational system, a personal attribute and these users' utterances, our goal is to predict the ranking of the given personal attribute values for each user. Previous studies often rely on a relative number of resources such as labeled utterances and external data, yet the attribute knowledge embedded in unlabeled utterances is underutilized and their performance of predicting some difficult personal attributes is still unsatisfactory. In addition, it is found that some text classification methods could be employed to resolve this task directly. However, they also perform not well over those difficult personal attributes. In this paper, we propose a novel framework PEARL to predict personal attributes from conversations by leveraging the abundant personal attribute knowledge from utterances under a low-resource setting in which no labeled utterances or external data are utilized. PEARL combines the biterm semantic information with the word co-occurrence information seamlessly via employing the updated prior attribute knowledge to refine the biterm topic model's Gibbs sampling process in an iterative manner. The extensive experimental results show that PEARL outperforms all the baseline methods not only on the task of personal attribute prediction from conversations over two data sets, but also on the more general weakly supervised text classification task over one data set.