This document provides an overview of using deep autoencoders to improve question answering systems. It discusses how deep autoencoders can encode text or images into codes that are indexed and stored. This allows for fast lookup of potential answer candidates. The document describes the components of question answering systems and information retrieval systems. It also provides details on how deep autoencoders work, including using a stacked restricted Boltzmann machine architecture for encoding and decoding layers.

1. Information Retrieval With Deep Autoencoders
Adam Gibson
Blix.io
Zipfian Academy
Big Data Science 5-17-14

2. Overview
● Overview of IR and Question Answering Systems
● Overview of Deep Learning
● Tying the 2 together

3. Information Retrieval (IR) Overview

4. Components of an IR QA System

Data Ingestion and Indexing

Types of Answers

Relevance Measure

Search Queries

Types of Information Retrieval

Answer Disambiguation

5. Data Ingestion and Indexing

Solr/Elastic Search/Lucene

Focus on text: typically a custom process
for inputting data

Indexing can be done on a per token
(per word) basis

Typical preprocessing:

Named-entity recognition

Relation extraction

Augment the index with certain kinds
of information

6. Relevance Measure
Cosine similarity measures how “close” a document is to a query.
The query is vectorized via bag-of-words and compared to each
document, also vectorized. This is done in light of TF-IDF.

7. Different Kinds of QA

Definition (Several relevant paragraphs
concatenated in to one)

Direct Answer (Watson)

Interactive (Siri, voice assistants)

8. Question Answering Systems

Are a step beyond search engines…

Have several data sources from which a question
can be answered

A classifier for the question type is used on the query

Several data sources can answer different kinds of
questions

This is used to compile a list of question-answering

candidates, or “documents most likely to succeed”.

9. Question Answering Systems (cont.)

Take the input text and classify it, to determine
the type of question

Use different answer sources (search engines,
triple stores/graph databases and computational
engines such as Wolfram Alpha)

Compile a list of answer candidates from each
source

Rank each answer candidate by relevance

10. Deep Learning with DBNs
Use Cases:
● Any NLP (collobert and Weston 2011)
● Sound with phonetics (asamir,gdahl,hinton)
● Computer Vision (Lee, Grosse, Ng)
● Watson (DeepQA)
● Image search via object recogition (Google)
● Recommendation Engines (Netflix)

11. Restricted Boltzmann Machines
● Units – Binary,Gaussian,Rectified Linear,Softmax,Multinomial
● Hidden/Visible Units – Visible learns data – Hidden is partition
function
● Contrastive Divergence is used for learning the weights
● Positive phase: Learn inputs (Visible) Negative: Balance out
wrt partition function (Hidden)
Real Valued Inputs:
Binary Inputs:

12. Results – Feature Learning

13. More Results – Feature Learning

14. General Architecture
● Stacked Restricted Boltzmann Machines – Compose to learn higher level
● correlations in the data
● Creates feature extractors
Use any sort of output layer with different objective functions to do different
tasks:
● Logisitic/Softmax Regression – Negative Log likelihood classification
● Mean Squared Error – Regression
● Cross Entropy - Reconstructions

15. Deep Learning and QA Systems

Part of the problem with answer-candidate searches
is speed: They’re slow.

Each question to be answered is computationally intensive.

Deep learning allows for fast lookup of various kinds
of answer candidates by encoding them.

Deep autoencoders allow for the encoding and decoding
of images as well as text.

16. Deep Autoencoders

Deep autoencoders are two deep-belief networks:

The first is a series of RBMs that encode the input into
a very tiny set of numbers, also called the codes.

The codes are what’s indexed and stored in search.

The second DBN is the decoder, which reconstructs
the results from the codes.

17. Architecture Visualization

18. The Encoding Layer: A How-To

Take the input, and make the parameters of the
first hidden layer slightly bigger than that input.
That allows for more information representation
on the first layer.

Progressively decrease the hidden-layer sizes at
each layer until you get to the final, coding, layer,
which is a small number (10-30 figures).

Make the final hidden-layer output be linear
(i.e. real numbers). Linear is pass-through.

19. Decoding Layer

Transpose the matrices of the encoder and reverse the
order of its layers.

Each parameter, after training the encoder, is used
to create the decoding net.

The decoder’s hidden layers are the exact opposite of
the encoder.

The output layer of the decoder is then trained to reconstruct
the input.

20. Connecting the Dots

Deep autoencoders can assist in creating answer

candidates for information-retrieval systems.

This works for image or text search.



This technique is called semantic hashing.

21. PCA Results

22. Some Results