SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2104.09580 · NAACL · 2021

Improving Cross-Modal Alignment in Vision Language Navigation via Syntactic Information

Mohit Bansal, Hao Tan, Jialu Li

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Vision language navigation is the task that requires an agent to navigate through a 3D environment based on natural language instructions. One key challenge in this task is to ground instructions with the current visual information that the agent perceives. Most of the existing work employs soft attention over individual words to locate the instruction required for the next action. However, different words have different functions in a sentence (e.g., modifiers convey attributes, verbs convey actions). Syntax information like dependencies and phrase structures can aid the agent to locate important parts of the instruction. Hence, in this paper, we propose a navigation agent that utilizes syntax information derived from a dependency tree to enhance alignment between the instruction and the current visual scenes. Empirically, our agent outperforms the baseline model that does not use syntax information on the Room-to-Room dataset, especially in the unseen environment. Besides, our agent achieves the new state-of-the-art on Room-Across-Room dataset, which contains instructions in 3 languages (English, Hindi, and Telugu). We also show that our agent is better at aligning instructions with the current visual information via qualitative visualizations. 1

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2104.09580")
get_code_for_paper("2104.09580")
have("2104.09580")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2104.09580.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2104.09580.svg)](https://syntology.ai/paper/2104.09580)

Connect an agent — have() is free.