IRJun 3, 2017

Neural Architecture for Question Answering Using a Knowledge Graph and Web Corpus

arXiv:1706.00973v315 citations
Originality Incremental advance
AI Analysis

This addresses the problem of robust entity retrieval for web search users by integrating structured and unstructured data sources, representing an incremental advancement over existing QA systems.

The paper tackles the brittleness and coverage issues in question answering systems by combining knowledge graph and corpus evidence to rank entities directly, achieving 5-16% absolute improvement in mean average precision on over 8,000 queries and nearly doubling F1 scores for short queries.

In Web search, entity-seeking queries often trigger a special Question Answering (QA) system. It may use a parser to interpret the question to a structured query, execute that on a knowledge graph (KG), and return direct entity responses. QA systems based on precise parsing tend to be brittle: minor syntax variations may dramatically change the response. Moreover, KG coverage is patchy. At the other extreme, a large corpus may provide broader coverage, but in an unstructured, unreliable form. We present AQQUCN, a QA system that gracefully combines KG and corpus evidence. AQQUCN accepts a broad spectrum of query syntax, between well-formed questions to short `telegraphic' keyword sequences. In the face of inherent query ambiguities, AQQUCN aggregates signals from KGs and large corpora to directly rank KG entities, rather than commit to one semantic interpretation of the query. AQQUCN models the ideal interpretation as an unobservable or latent variable. Interpretations and candidate entity responses are scored as pairs, by combining signals from multiple convolutional networks that operate collectively on the query, KG and corpus. On four public query workloads, amounting to over 8,000 queries with diverse query syntax, we see 5--16% absolute improvement in mean average precision (MAP), compared to the entity ranking performance of recent systems. Our system is also competitive at entity set retrieval, almost doubling F1 scores for challenging short queries.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes