Compositional Language Understanding with Text-based Relational Reasoning
Neural networks for natural language reasoning have largely focused on extractive, fact-based question-answering (QA) and common-sense inference. However, it is also crucial to understand the extent to which neural networks can perform relational reasoning and combinatorial generalization from natural language---abilities that are often obscured by annotation artifacts and the dominance of language modeling in standard QA benchmarks. In this work, we present a novel benchmark dataset for language understanding that isolates performance on relational reasoning. We also present a neural message-passing baseline and show that this model, which incorporates a relational inductive bias, is superior at combinatorial generalization compared to a traditional recurrent neural network approach.
Authors

Are you an author of this paper? Check the Twitter handle we have for you is correct.

Koustuv Sinha (edit)
Shagun Sodhani (edit)
William L. Hamilton (edit)
Joelle Pineau (add twitter)
Ask The Authors

Ask the authors of this paper a question or leave a comment.

Read it. Rate it.
#1. Which part of the paper did you read?

#2. The paper contains new data or analyses that is openly accessible?
#3. The conclusion is supported by the data and analyses?
#4. The conclusion is of scientific interest?
#5. The result is likely to lead to future research?

Github
Stargazers:
6
Forks:
1
Open Issues:
1
Network:
1
Subscribers:
1
Language:
Python
Youtube
Link:
None (add)
Views:
0
Likes:
0
Dislikes:
0
Favorites:
0
Comments:
0
Other
Sample Sizes (N=):
Inserted:
Words Total:
Words Unique:
Source:
Abstract:
None
11/07/18 06:02PM
4,146
1,593
Tweets
arxiv_cscl: Compositional Language Understanding with Text-based Relational Reasoning https://t.co/C76ydZltOx
arxiv_cscl: Compositional Language Understanding with Text-based Relational Reasoning https://t.co/C76ydZltOx
arxiv_cscl: Compositional Language Understanding with Text-based Relational Reasoning https://t.co/C76ydZltOx
puneethmishra: RT @arxiv_cscl: Compositional Language Understanding with Text-based Relational Reasoning https://t.co/C76ydZltOx
arxiv_cscl: Compositional Language Understanding with Text-based Relational Reasoning https://t.co/C76ydZltOx
arxiv_cscl: Compositional Language Understanding with Text-based Relational Reasoning https://t.co/C76ydZltOx
arxiv_cscl: Compositional Language Understanding with Text-based Relational Reasoning https://t.co/C76ydZltOx
arxiv_cscl: Compositional Language Understanding with Text-based Relational Reasoning https://t.co/C76ydZltOx
arxivml: "Compositional Language Understanding with Text-based Relational Reasoning", Koustuv Sinha, Shagun Sodhani, William… https://t.co/8X2Fnc05dA
nmfeeds: [O] https://t.co/xmRJiT6SoS Compositional Language Understanding with Text-based Relational Reasoning. Neural networks for...
nmfeeds: [CL] https://t.co/xmRJiT6SoS Compositional Language Understanding with Text-based Relational Reasoning. Neural networks fo...
nmfeeds: [AI] https://t.co/xmRJiT6SoS Compositional Language Understanding with Text-based Relational Reasoning. Neural networks fo...
BrundageBot: Compositional Language Understanding with Text-based Relational Reasoning. Koustuv Sinha, Shagun Sodhani, William L. Hamilton, and Joelle Pineau https://t.co/H7D0TWTnLD
arxiv_cscl: Compositional Language Understanding with Text-based Relational Reasoning https://t.co/C76ydZltOx
Images
Related