Papers › Explainable Conversational Question Answering over Heterogeneous Sources via Iterative...

Explainable Conversational Question Answering over Heterogeneous Sources via Iterative Graph Neural Networks

2 May 2023arXiv:2305.01548archive 2025-07-28

Philipp Christmann, Rishiraj Saha Roy, Gerhard Weikum

In conversational question answering, users express their information needs through a series of utterances with incomplete context. Typical ConvQA methods rely on a single source (a knowledge base (KB), or a text corpus, or a set of tables), thus being unable to benefit from increased answer coverage and redundancy of multiple sources. Our method EXPLAIGNN overcomes these limitations by integrating information from a mixture of sources with user-comprehensible explanations for answers. It constructs a heterogeneous graph from entities and evidence snippets retrieved from a KB, a text corpus, web tables, and infoboxes. This large graph is then iteratively reduced via graph neural networks that incorporate question-level attention, until the best answers and their explanations are distilled. Experiments show that EXPLAIGNN improves performance over state-of-the-art baselines. A user study demonstrates that derived answers are understandable by end users.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

philippchr/explaignn mentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Conversational Question AnsweringQuestion Answering

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Question Answering TIQ Explaignn P@1 44.6 #2 of 9 Archive leaderboard report
Question Answering TimeQuestions EXPLAIGNN P@1 52.5 #9 of 21 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

BASE

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections