DeepAI AI Chat
Log In Sign Up

Latent Compositional Representations Improve Systematic Generalization in Grounded Question Answering

by   Ben Bogin, et al.
Tel Aviv University
Allen Institute for Artificial Intelligence

Answering questions that involve multi-step reasoning requires decomposing them and using the answers of intermediate steps to reach the final answer. However, state-of-the-art models in grounded question answering often do not explicitly perform decomposition, leading to difficulties in generalization to out-of-distribution examples. In this work, we propose a model that computes a representation and denotation for all question spans in a bottom-up, compositional manner using a CKY-style parser. Our model effectively induces latent trees, driven by end-to-end (the answer) supervision only. We show that this inductive bias towards tree structures dramatically improves systematic generalization to out-of-distribution examples compared to strong baselines on an arithmetic expressions benchmark as well as on CLOSURE, a dataset that focuses on systematic generalization of models for grounded question answering. On this challenging dataset, our model reaches an accuracy of 92.8 significantly higher than prior models that almost perfectly solve the task on a random, in-distribution split.


page 11

page 17

page 18


Grounded Graph Decoding Improves Compositional Generalization in Question Answering

Question answering models struggle to generalize to novel compositions o...

Paired Examples as Indirect Supervision in Latent Decision Models

Compositional, structured models are appealing because they explicitly d...

CLOSURE: Assessing Systematic Generalization of CLEVR Models

The CLEVR dataset of natural-looking questions about 3D-rendered scenes ...

Successive Prompting for Decomposing Complex Questions

Answering complex questions that require making latent decisions is a ch...

ScienceWorld: Is your Agent Smarter than a 5th Grader?

This paper presents a new benchmark, ScienceWorld, to test agents' scien...

On the Transferability of Minimal Prediction Preserving Inputs in Question Answering

Recent work (Feng et al., 2018) establishes the presence of short, unint...

Iterated learning for emergent systematicity in VQA

Although neural module networks have an architectural bias towards compo...

Code Repositories



view repo