Generating a Common Question from Multiple Documents using Multi-source Encoder-Decoder Models
This addresses ambiguous user queries in search engines, but it is incremental as it builds on existing multi-source frameworks.
The paper tackled the problem of ambiguous search queries by proposing a task to generate a common question from multiple documents, using a multi-source encoder-decoder model called MSQG that outperformed baselines on the MS-MARCO-QA dataset.
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.