Papers › CRFR: Improving Conversational Recommender Systems via Flexible Fragments Reasoning on...

CRFR: Improving Conversational Recommender Systems via Flexible Fragments Reasoning on Knowledge Graphs

1 Nov 2021EMNLP 2021 11archive 2025-07-28

Jinfeng Zhou, Bo wang, Ruifang He, Yuexian Hou

Although paths of user interests shift in knowledge graphs (KGs) can benefit conversational recommender systems (CRS), explicit reasoning on KGs has not been well considered in CRS, due to the complex of high-order and incomplete paths. We propose CRFR, which effectively does explicit multi-hop reasoning on KGs with a conversational context-based reinforcement learning model. Considering the incompleteness of KGs, instead of learning single complete reasoning path, CRFR flexibly learns multiple reasoning fragments which are likely contained in the complete paths of interests shift. A fragments-aware unified model is then designed to fuse the fragments information from item-oriented and concept-oriented KGs to enhance the CRS response with entities and words from the fragments. Extensive experiments demonstrate CRFR’s SOTA performance on recommendation, conversation and conversation interpretability.

PaperPDF

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

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

Tasks

Knowledge GraphsRecommendation SystemsText Generation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Recommendation Systems ReDial CRFR Recall@1 0.04 #4 of 8 Archive leaderboard report
Recommendation Systems ReDial CRFR Recall@10 0.202 #4 of 8 Archive leaderboard report
Recommendation Systems ReDial CRFR Recall@50 0.399 #4 of 8 Archive leaderboard report
Text Generation ReDial CRFR Distinct-2 0.345 #2 of 5 Archive leaderboard report
Text Generation ReDial CRFR Distinct-3 0.516 #2 of 5 Archive leaderboard report
Text Generation ReDial CRFR Distinct-4 0.639 #2 of 5 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.

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