Papers › Mention Memory: incorporating textual knowledge into Transformers through entity...

Mention Memory: incorporating textual knowledge into Transformers through entity mention attention

12 Oct 2021ICLR 2022 4arXiv:2110.06176archive 2025-07-28

Michiel de Jong, Yury Zemlyanskiy, Nicholas FitzGerald, Fei Sha, William Cohen

Natural language understanding tasks such as open-domain question answering often require retrieving and assimilating factual information from multiple sources. We propose to address this problem by integrating a semi-parametric representation of a large text corpus into a Transformer model as a source of factual knowledge. Specifically, our method represents knowledge with `mention memory', a table of dense vector representations of every entity mention in a corpus. The proposed model - TOME - is a Transformer that accesses the information through internal memory layers in which each entity mention in the input passage attends to the mention memory. This approach enables synthesis of and reasoning over many disparate sources of information within a single Transformer model. In experiments using a memory of 150 million Wikipedia mentions, TOME achieves strong performance on several open-domain knowledge-intensive tasks, including the claim verification benchmarks HoVer and FEVER and several entity-based QA benchmarks. We also show that the model learns to attend to informative mentions without any direct supervision. Finally we demonstrate that the model can generalize to new unseen entities by updating the memory without retraining.

PaperPDFConference PDFCode

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

Code

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

Claim VerificationNatural Language UnderstandingOpen-Domain Question AnsweringPassage RetrievalQuestion Answering

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Passage Retrieval EntityQuestions TOME-2 Recall@20 0.838 #1 of 7 Archive leaderboard report
Question Answering ComplexWebQuestions TOME-2 EM 47.7 #1 of 1 Archive leaderboard report
Question Answering TriviaQA TOME-2 EM 65.8 #38 of 56 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

Absolute Position EncodingsAdamAttentionBPEDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformer

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