Generating a Common Question from Multiple Documents using Multi-source Encoder-Decoder Models

10/25/2019
by   Woon Sang Cho, et al.
0

Ambiguous user queries in search engines result in the retrieval of documents that often span multiple topics. One potential solution is for the search engine to generate multiple refined queries, each of which relates to a subset of the documents spanning the same topic. A preliminary step towards this goal is to generate a question that captures common concepts of multiple documents. We propose a new task of generating common question from multiple documents and present simple variant of an existing multi-source encoder-decoder framework, called the Multi-Source Question Generator (MSQG). We first train an RNN-based single encoder-decoder generator from (single document, question) pairs. At test time, given multiple documents, the 'Distribute' step of our MSQG model predicts target word distributions for each document using the trained model. The 'Aggregate' step aggregates these distributions to generate a common question. This simple yet effective strategy significantly outperforms several existing baseline models applied to the new task when evaluated using automated metrics and human judgments on the MS-MARCO-QA dataset.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
11/08/2019

Unsupervised Common Question Generation from Multiple Documents using Reinforced Contrastive Coordinator

Web search engines today return a ranked list of document links in respo...
research
01/30/2018

Generating Wikipedia by Summarizing Long Sequences

We show that generating English Wikipedia articles can be approached as ...
research
08/19/2018

Adapting the Neural Encoder-Decoder Framework from Single to Multi-Document Summarization

Generating an abstract from a set of relevant documents remains challeng...
research
05/16/2023

Large Language Models are Built-in Autoregressive Search Engines

Document retrieval is a key stage of standard Web search engines. Existi...
research
11/04/2020

MK-SQuIT: Synthesizing Questions using Iterative Template-filling

The aim of this work is to create a framework for synthetically generati...
research
07/25/2022

Effective and Interpretable Information Aggregation with Capacity Networks

How to aggregate information from multiple instances is a key question m...
research
01/01/2023

Inflected Forms Are Redundant in Question Generation Models

Neural models with an encoder-decoder framework provide a feasible solut...

Please sign up or login with your details

Forgot password? Click here to reset