Browse the Complete MapTask Corpus

Explore all 128 dialogues from the giver's and follower's perspectives. Select a map and dialogue, then follow each reference through the transcript, maps, GMMT annotations, and saved SINS judgments.

128 dialogues · 16 map pairs · 13,077 annotations. GPT-5 annotations cover the full corpus and are selected by default. Human-verified annotations are available only for q1ec2, q1nc3 and q1nc7 (504 references). Every visible landmark has a clickable region, including landmarks not mentioned in the selected dialogue.

What do aligned, pending and misunderstood mean?

Interactive demo

One expression, two situated interpretations

Click an underlined phrase in the dialogue. The coloured map outlines and the two interpretation cards update for that exact reference. The opening parked-van case is a real exchange (q8nc6), not the papers' simplified dialogue.

1 Choose a dialogue2 Click a phrase in context3 Compare the two interpretations
Interpretation annotation
Map pair m9

Real participant maps

HCRC MapTask · actual maps

Click a landmark's icon or name to find its mentions. Click the map background to enlarge.

Giver interpretation Follower interpretation Selected landmark

Find mentions of a landmark
Selected reference
—

Participant interpretations

Giver interpretation —
≠
Follower interpretation —
Inspect annotation fields and source rationale

Rationale text is retained from the selected source, not independently verified by this website. Null means the field was not evaluated in the annotation cascade.

Separate task: does a SINS model judge these interpretations to match?

Interpretation matching · Yes / No

Qwen3-VL-8B-Instruct · dialogue start through current transaction
SINS dataset target—
Dialogue only—
Dialogue + both maps—

These are matching judgments, not landmark predictions. The SINS target comes from the released GPT-5 annotation layer and does not change when you inspect a human-verified annotation above. A dash means no saved prediction is available.

Follow the whole conversation

All 128 dialogues · 16 map pairs · 13,077 reference annotations
GPT-5 throughout; human-verified annotations for 3 dialogues (504 references).

Browse all dialogues & annotations

Source and attribution. Maps and dialogue text are from the HCRC MapTask Corpus, displayed under CC BY 4.0 as stated on the official download page. Maps were converted to PNG and resized; transcripts were reconstructed from timed units and reformatted. Interactive overlays are project additions. Participant interpretations come from GMMT and matching judgments from SINS.

Enlarged map

Click the map again, click outside, or press Esc to close.