Split and Rephrase: Better Evaluation and Stronger Baselines (P18-2)

Copied to clipboard

Challenge: a dataset mapping a complex sentence to a sequence of sentences conveying the same meaning is challenging in NLP.
Approach: They propose a neural split and a copy-mechanism to break a complex sentence into several shorter sentences that convey the same meaning.
Outcome: The proposed model outperforms the baseline model by 8.68 BLEU and further improves on the task.

Similar Papers

Small but Mighty: New Benchmarks for Split and Rephrase (2020.emnlp-main)

Copied to clipboard

Challenge: Split and Rephrase is a text simplification task that requires a strong evaluation benchmark and metric . despite its relatively new nature, the benchmark dataset contains easily exploitable syntactic cues .
Approach: They propose to use crowdsourced datasets to evaluate split and rephrase models . they find that the widely used benchmark dataset universally contains exploitable syntactic cues .
Outcome: The proposed model performs better than the state-of-the-art model, the authors say . they show that the datasets contain significantly more diverse syntax .
BiSECT: Learning to Split and Rephrase Sentences with Bitexts (2021.emnlp-main)

Copied to clipboard

Challenge: Several past efforts have created Split and Rephrase training sets, which consist of long, complex input sentences paired with multiple shorter sentences that preserve the meaning of the input sentence.
Approach: They propose a new dataset and a model for this task by extracting 1-2 sentence alignments from bilingual parallel corpora and using machine translation to convert both sides of the corpus into the same language.
Outcome: The proposed model can perform a wider variety of split operations and improve upon previous state-of-the-art approaches in automatic and human evaluations.
WikiSplit++: Easy Data Refinement for Split and Rephrase (2024.lrec-main)

Copied to clipboard

Challenge: Existing text simplification methods rely on encoder-decoder models to achieve this task.
Approach: They propose a text-to-text generation approach that applies encoder-decoder models to a large-scale dataset to improve Split and Rephrase.
Outcome: The proposed approach improves Split and Rephrase readability and performance on large datasets, but still suffers from hallucinations and under-splitting.
Learning To Split and Rephrase From Wikipedia Edit History (D18-1)

Copied to clipboard

Challenge: Performing split and rephrase tasks is one of the main operations in text simplification, alongside paraphrasing and dropping less salient content.
Approach: They propose to use Wikipedia's edit history to extract a rich new dataset for the task.
Outcome: The proposed model scores 32 BLEU points above the previous best on the WebSplit benchmark.
Split and Rephrase with Large Language Models (2024.acl-long)

Copied to clipboard

Challenge: Split and Rephrase (SPRP) tasks require modelling complex grammatical aspects to provide optimal splits and appropriate rephrasing.
Approach: They evaluate large language models on the Split and Rephrase task . they show they can provide large improvements over the state of the art on main metrics .
Outcome: The proposed model outperforms the state-of-the-art model on the Split and Rephrase task on the main metric, but still lacks in splitting compliance.
Complexity-Weighted Loss and Diverse Reranking for Sentence Simplification (N19-1)

Copied to clipboard

Challenge: Recent research has applied sequence-to-sequence (Seq2Sequen) models to text simplification . generic models tend to copy directly from the original sentence, resulting in outputs that are long and complex.
Approach: They propose to incorporate word complexities into the loss function during training and generate a large set of diverse candidate simplifications at test time.
Outcome: The proposed model can perform competitively with state-of-the-art systems while generating simpler sentences.
We Need to Talk about Standard Splits (P19-1)

Copied to clipboard

Challenge: Existing methods to evaluate systems with a held-out test set are insufficient for system comparison.
Approach: They propose to use multiple random splits to compare performance of systems . they replicate results on standard split but fail to reproduce some rankings .
Outcome: The proposed method is based on multiple random splits to replicate results with a set of part-of-speech taggers.
We Need to Talk About train-dev-test Splits (2021.emnlp-main)

Copied to clipboard

Challenge: Standard train-dev-test splits used to benchmark multiple models are now used in NLP . comparing multiple versions of the same model on the test data leads to overfitting and "expiration" of test sets.
Approach: They propose to use a tune-set when developing neural network methods to do model picking.
Outcome: The proposed model picker is more robust against the evaluated hyperparameter ranges than the standard split split.
Benchmarking Long-tail Generalization with Likelihood Splits (2023.findings-eacl)

Copied to clipboard

Challenge: Existing methods to test out of distribution generalization have their own strengths and weaknesses.
Approach: They propose a method to create challenging benchmarks that require generalizing to the tail of the distribution by re-splitting existing datasets.
Outcome: The proposed approach can be customized to construct meaningful splits for a wide range of tasks.
Fluency Boost Learning and Inference for Neural Grammatical Error Correction (P18-1)

Copied to clipboard

Challenge: Seq2seq models for grammatical error correction (GEC) have two limitations: (1) a seq2q model may not be well generalized with only limited error-corrected data; (2) a model may fail to completely correct a sentence with multiple errors through normal seq1sequeq inference.
Approach: They propose a fluency boost learning and inference mechanism to improve the performance of seq2seq models for grammatical error correction (GEC) by generating fluency-boost sentence pairs during training.
Outcome: Experiments show that the proposed model improves on both CoNLL-2014 and JFLEG benchmark 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