Papers by Matthew Richardson

6 papers
What Makes Instruction Learning Hard? An Investigation and a New Challenge in a Synthetic Environment (2022.emnlp-main)

Copied to clipboard

Challenge: Recent studies have focused on instruction learning, where a model learns to perform unseen tasks from task descriptions alone.
Approach: They propose to use a controlled synthetic environment to characterize large transformer models as instruction learners.
Outcome: The proposed model can interpret only 65.6% of test instructions and 11%-24% of instructions in out-of-distribution settings.
NL-EDIT: Correcting Semantic Parse Errors through Natural Language Interaction (2021.naacl-main)

Copied to clipboard

Challenge: Existing systems frame semantic parsing as a one-shot translation from a natural language question to the logical form.
Approach: They propose a model that uses natural language feedback to correct parsers . they show that NL-EDIT can boost the accuracy of existing parser by 20% .
Outcome: The proposed model can boost parsers' accuracy by 20% with just one turn of correction.
KaggleDBQA: Realistic Evaluation of Text-to-SQL Parsers (2021.acl-long)

Copied to clipboard

Challenge: Recent large-scale datasets such as Spider and WikiSQL facilitated novel modeling techniques for text-to-SQl parsing.
Approach: They propose a new cross-domain evaluation dataset of real Web databases . they examine the choice of evaluation tasks for text-to-SQL parsers .
Outcome: The proposed model improves accuracy by 13.2% over state-of-the-art parsers in real-life environments.
Structure-Grounded Pretraining for Text-to-SQL (2021.naacl-main)

Copied to clipboard

Challenge: STRUG is a weakly supervised structure-based pretraining framework for text-to-SQL . it can be used to learn to capture text-table alignment in a given database schema .
Approach: They propose a weakly supervised structure-grounded pretraining framework for text-to-SQL that can effectively learn to capture text-table alignment based on a parallel text-tab corpus.
Outcome: The proposed framework outperforms BERTLARGE and BERTLAGE on all text-to-SQL alignment settings.
Kreyòl-MT: Building MT for Latin American, Caribbean and Colonial African Creole Languages (2024.naacl-long)

Copied to clipboard

Challenge: Creole languages are used in much of Latin America, Africa and the Caribbean . a large multilingual bitext like ours has potential to build the best yet or first ever MT models for many languages .
Approach: They present the largest cumulative dataset to date for Creole language MT . they provide MT models supporting all 41 Creoles in 172 translation directions .
Outcome: The proposed model outperforms a genre-specific Creole MT model on its own benchmark for 23 of 34 translation directions.
RAT-SQL: Relation-Aware Schema Encoding and Linking for Text-to-SQL Parsers (2020.acl-main)

Copied to clipboard

Challenge: Existing semantic parsing models struggle to generalize to unseen database schemas.
Approach: They propose a framework to address schema encoding, schema linking, and feature representation within a text-to-SQL encoder.
Outcome: The proposed framework boosts the match accuracy to 57.2% on the spider dataset, surpassing its best counterparts by 8.7%.

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