Papers with consistent tokenization

2 papers
jp-evalb: Robust Alignment-based PARSEVAL Measures (2024.naacl-demo)

Copied to clipboard

Challenge: evalb is used for constituency parsing evaluation, but imposes constraints and requires consistent tokenization and sentence boundary outcomes.
Approach: They propose an evaluation system designed to compute PARSEVAL measures, offering a viable alternative to evalb commonly used for constituency parsing evaluation.
Outcome: The proposed evaluation system is based on an alignment method that aligns sentences and words when discrepancies arise.
Tokenization Consistency Matters for Generative Models on Extractive NLP Tasks (2023.findings-emnlp)

Copied to clipboard

Challenge: Pretrained sequence-to-sequence (seq2sequ) models have been widely used to solve extractive tasks, where parts of the input are extracted to form the desired output.
Approach: They propose a simple fix to tokenization inconsistency that damages extractive nature of generative models by causing performance drop and hallucination.
Outcome: The proposed model performs better in both in-domain and out-of-domain datasets with a notable average of +1.7 F1 gain when a BART model is trained on SQuAD and evaluated on 8 QA datasets.

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