Knowledge Guided Text Retrieval and Reading for Open Domain Question Answering

Code

• github.com/huggingface/transformers
  In paperpytorch★ 158,292
• github.com/facebookresearch/DPR
  pytorch★ 1,864
• github.com/shmsw25/GraphRetriever
  pytorch★ 39
• github.com/hongyuntw/DPR
  pytorch★ 4
• github.com/hongyuntw/DPR_BESS
  pytorch★ 1
• github.com/nidhikamal-emb/DPR_repo
  pytorch★ 1
• github.com/Heidelberg-NLP/discourse-aware-semantic-self-attention
  pytorch★ 0

Abstract

We introduce an approach for open-domain question answering (QA) that retrieves and reads a passage graph, where vertices are passages of text and edges represent relationships that are derived from an external knowledge base or co-occurrence in the same article. Our goals are to boost coverage by using knowledge-guided retrieval to find more relevant passages than text-matching methods, and to improve accuracy by allowing for better knowledge-guided fusion of information across related passages. Our graph retrieval method expands a set of seed keyword-retrieved passages by traversing the graph structure of the knowledge base. Our reader extends a BERT-based architecture and updates passage representations by propagating information from related passages and their relations, instead of reading each passage in isolation. Experiments on three open-domain QA datasets, WebQuestions, Natural Questions and TriviaQA, show improved performance over non-graph baselines by 2-11% absolute. Our approach also matches or exceeds the state-of-the-art in every case, without using an expensive end-to-end training regime.

Tasks

Reproductions