Papers › ITA: Image-Text Alignments for Multi-Modal Named Entity Recognition

ITA: Image-Text Alignments for Multi-Modal Named Entity Recognition

13 Dec 2021NAACL 2022 7arXiv:2112.06482archive 2025-07-28

Xinyu Wang, Min Gui, Yong Jiang, Zixia Jia, Nguyen Bach, Tao Wang, Zhongqiang Huang, Fei Huang, Kewei Tu

Recently, Multi-modal Named Entity Recognition (MNER) has attracted a lot of attention. Most of the work utilizes image information through region-level visual representations obtained from a pretrained object detector and relies on an attention mechanism to model the interactions between image and text representations. However, it is difficult to model such interactions as image and text representations are trained separately on the data of their respective modality and are not aligned in the same space. As text representations take the most important role in MNER, in this paper, we propose {\bf I}mage-{\bf t}ext {\bf A}lignments (ITA) to align image features into the textual space, so that the attention mechanism in transformer-based pretrained textual embeddings can be better utilized. ITA first aligns the image into regional object tags, image-level captions and optical characters as visual contexts, concatenates them with the input texts as a new cross-modal input, and then feeds it into a pretrained textual embedding model. This makes it easier for the attention module of a pretrained textual embedding model to model the interaction between the two modalities since they are both represented in the textual space. ITA further aligns the output distributions predicted from the cross-modal input and textual input views so that the MNER model can be more practical in dealing with text-only inputs and robust to noises from images. In our experiments, we show that ITA models can achieve state-of-the-art accuracy on multi-modal Named Entity Recognition datasets, even without image information.

PaperPDFConference PDFCode

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

Code

alibaba-nlp/kb-ner officialmentioned in papermentioned 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

Multi-modal Named Entity RecognitionNamed Entity RecognitionNamed Entity Recognition (NER)named-entity-recognition

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Multi-modal Named Entity Recognition SNAP (MNER) ITA-All F1 90.15 #3 of 6 Archive leaderboard report
Multi-modal Named Entity Recognition Twitter-17 ITA-All F1 89.75 #1 of 2 Archive leaderboard report
Multi-modal Named Entity Recognition Twitter-2017 ITA-All F1 89.75 #3 of 3 Archive leaderboard report
Multi-modal Named Entity Recognition WikiDiverse ITA-All F1 76.87 #4 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