Faculty Recruiting Support CICS

Neural Models for Information Retrieval without Labeled Data

27 Aug
Add to Calendar
Tuesday, 08/27/2019 4:00pm to 6:00pm
CS 151
Ph.D. Seminar
Speaker: Hamed Zamani
Abstract:

Recent developments of machine learning models, and in particular deep neural networks, have yielded significant improvements on several computer vision, natural language processing, and speech recognition tasks. Progress with information retrieval (IR) tasks has been slower, however, due to the lack of large-scale training data as well as neural network models specifically designed for effective information retrieval. In this dissertation, we address these two issues by introducing task-specific neural network architectures for a set of IR tasks and proposing novel unsupervised or weakly supervised solutions for training the models. The proposed learning solutions do not require labeled training data. Instead, in our weak supervision approach, neural models are trained on a large set of noisy and biased training data obtained from external resources, existing models, or heuristics.

 

We first introduce relevance-based embedding models that learn distributed representations for words and queries. We show that the learned representations can be effectively employed for a set of IR tasks, including query expansion, pseudo-relevance feedback, and query classification.

 

We further propose a standalone learning to rank model based on deep neural networks. Our model learns a sparse representation for queries and documents. This enables us to perform efficient retrieval by constructing an inverted index in the learned semantic space. Our model outperforms state-of-the-art retrieval models, while performing as efficient as term matching retrieval models.

 

We additionally propose a neural network framework for predicting the performance of a retrieval model for a given query. Inspired by existing query performance prediction models, our framework integrates several information sources, such as retrieval score distribution and term distribution in the top retrieved documents. This leads to state-of-the-art results for the performance prediction task on various standard collections.

 

We finally bridge the gap between retrieval and recommendation models, as the two key components in most information systems. Search and recommendation often share the same goal: helping people get the information they need at the right time. Therefore, joint modeling and optimization of search engines and recommender systems could potentially benefit both systems. In more detail, we propose to learn a retrieval model from the user interactions with the recommender system, with no need to query-document relevance information for training.

 

Our solutions and findings in this dissertation smooth the path towards learning efficient and effective models for various information retrieval and related tasks, especially when large-scale training data is not available.

Advisor: W. Bruce Croft