Papers with intermediate pre-training

6 papers
Learning to Decompose: Hypothetical Question Decomposition Based on Comparable Texts (2022.emnlp-main)

Copied to clipboard

Challenge: Existing approaches to end-to-end questionanswering assume that pre-trained language can decompose complex tasks into more straightforward sub-tasks.
Approach: They propose to use distant supervision to train decomposition-based transformers for large-scale parallel news.
Outcome: The proposed model improves on semantic parsing and on hotpotQA and strategyQA datasets by 20% to 30%.
Silver Syntax Pre-training for Cross-Domain Relation Extraction (2023.findings-acl)

Copied to clipboard

Challenge: Relation Extraction (RE) is the task of extracting structured knowledge from unstructured text.
Approach: They exploit the affinity between syntactic structure and semantic RE to obtain low-cost pre-training data.
Outcome: The proposed model outperforms baseline models in five out of six cross-domain setups without additional annotated data.
Hyperlink-induced Pre-training for Passage Retrieval in Open-domain Question Answering (2022.acl-long)

Copied to clipboard

Challenge: Existing methods to train dense passage retrieval have a large data gap between upstream and downstream relevance.
Approach: They propose a method to pre-train the dense retriever with the text relevance induced by hyperlinks within Web documents.
Outcome: The proposed method outperforms existing methods under different scenarios and in the open-domain question answering domain.
Learning Relational Decomposition of Queries for Question Answering from Tables (2024.acl-long)

Copied to clipboard

Challenge: Existing approaches to Table Question-Answering focus on generating answers directly from inputs, but there are limitations when executing numerical operations.
Approach: They propose to imitate a restricted subset of SQL-like algebraic operations and use them to generate a query.
Outcome: The proposed methods bridge the gap between semantic parsing and direct answering methods and offer valuable insights into which types of operations should be predicted by a generative architecture and which should be executed by an external algorithm.
On the Influence of Masking Policies in Intermediate Pre-training (2021.emnlp-main)

Copied to clipboard

Challenge: Existing studies show that inserting an intermediate pre-training stage improves performance of masked language models.
Approach: They propose methods to automate the discovery of optimal masking policies via direct supervision or meta-learning.
Outcome: The proposed method outperforms the heuristic of masking named entities on TriviaQA and can be generalizable beyond that task.
Strengthening Structural Inductive Biases by Pre-training to Perform Syntactic Transformations (2024.emnlp-main)

Copied to clipboard

Challenge: Inductive biases play a critical role in NLP, especially in learning from limited data and generalizing systematically outside of the training distribution.
Approach: They propose to strengthen the structural inductive bias of a Transformer by intermediate pre-training to perform syntactic transformations of dependency trees given a description of the transformation.
Outcome: The proposed model can perform syntactic transformations and generalize semantic parsing with attention heads that keep track of which syntaktic transformation needs to be applied to which token.

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