Papers with neural module networks

3 papers
Social Norms-Grounded Machine Ethics in Complex Narrative Situation (2022.coling-1)

Copied to clipboard

Challenge: Recent studies focus on data-driven methods to judge the ethics of complex real-world narratives but face two major challenges: they cannot handle dilemma situations due to a lack of basic knowledge about social norms; and they focus on sparse situation-level judgment regardless of the social norm.
Approach: They propose to complement a complex situation with grounded social norms by a norm-supported ethical judgment model in line with neural module networks to alleviate dilemma situations and improve norm-level explainability.
Outcome: The proposed model improves state-of-the-art performance on two narrative judgment benchmarks.
Multi-Step Inference for Reasoning Over Paragraphs (2020.emnlp-main)

Copied to clipboard

Challenge: Existing models for complex reasoning use symbols or black-box transformers . a compositional model can chain together free-form predicates and logical connectives .
Approach: They propose a compositional model that finds relevant sentences and then chains them together using neural modules.
Outcome: The proposed model improves performance on a recently-introduced dataset.
Paired Examples as Indirect Supervision in Latent Decision Models (2021.emnlp-main)

Copied to clipboard

Challenge: a new method to learn compositional structured models is needed . end-task supervision provides only a weak indirect signal on values the latent decisions should take.
Approach: They propose a way to leverage paired examples that provide stronger cues for learning latent decisions . they use a DROP dataset to acquire paired questions that provide strong cue signals .
Outcome: The proposed approach improves compositional question answering on a DROP dataset.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations