paper-with-me

Papers

BERTScore: Evaluating Text Generation with BERT

2019-04-21 · ICLR 2020 1 · Tianyi Zhang, Varsha Kishore, Felix Wu, Kilian Q. Weinberger, Yoav Artzi

We propose BERTScore, an automatic evaluation metric for text generation. Analogously to common metrics, BERTScore computes a similarity score for each token in the candidate sentence with each token in the reference sentence. However, instead of exact matches, we compute token similarity using contextual embeddings. We evaluate using the outputs of 363 machine translation and image captioning systems. BERTScore correlates better with human judgments and provides stronger model selection performance than existing metrics. Finally, we use an adversarial paraphrase detection task to show that BERTScore is more robust to challenging examples when compared to existing metrics.

📄 PDF Abstract BibTeX arXiv:1904.09675

Code (20)

Tiiiger/bert_score 공식 구현 pytorch
ShiYaya/Awesome_Evaluation_Metrics_for_Text_Generation
THUDM/KOBE pytorch
THUcqb/KOBE pytorch
allenai/mslr-shared-task pytorch
ananyacoder/mee_wmt2021
cyr19/reproducibility pytorch
danieldeutsch/bert_score_content_analysis pytorch
facebookresearch/vizseq
gotutiyan/gec-metrics
jonas-becker/text-generation
lovit/KoBERTScore pytorch
lovit/ko-BERTScore pytorch
neulab/code-bert-score pytorch
open-finance-lab/finlora pytorch
qibinc/KOBE pytorch
sebiancoder/bertscorevisualizer
stair-lab/villm-eval pytorch
yangletliu/finlora pytorch
yuhui-zh15/nlg_metrics pytorch

Tasks

Image CaptioningMachine TranslationModel SelectionSentenceText GenerationTranslation

Similar Papers 제목 키워드 기반

CodeBERTScore: Evaluating Code Generation with Pretrained Models of Code

2023-02-10 · Shuyan Zhou, Uri Alon, Sumit Agarwal, Graham Neubig

Since the rise of neural natural-language-to-code models (NL->Code) that can generate long expressions and statements rather than a single next-token, one of the major problems has been reliably evaluating their generate…

Code Generation

FinNuE: Exposing the Risks of Using BERTScore for Numerical Semantic Evaluation in Finance

2025-11-13 · Yu-Shiang Huang, Yun-Yu Lee, Tzu-Hsin Chou, Che Lin 외 arxiv

BERTScore has become a widely adopted metric for evaluating semantic similarity between natural language sentences. However, we identify a critical limitation: BERTScore exhibits low sensitivity to numerical variation, a…

Semantic Similarity

BERTScore is Unfair: On Social Bias in Language Model-Based Metrics for Text Generation

2022-10-14 · Tianxiang Sun, Junliang He, Xipeng Qiu, Xuanjing Huang

Automatic evaluation metrics are crucial to the development of generative systems. In recent years, pre-trained language model (PLM) based metrics, such as BERTScore, have been commonly adopted in various generation task…

FairnessLanguage ModelingLanguage ModellingText Generation

OARelatedWork: A Large-Scale Dataset of Related Work Sections with Full-texts from Open Access Sources

2024-05-03 · Martin Docekal, Martin Fajcik, Pavel Smrz

This paper introduces OARelatedWork, the first large-scale multi-document summarization dataset for related work generation containing whole related work sections and full-texts of cited papers. The dataset includes 94 4…

Document SummarizationExtractive SummarizationMulti-Document Summarization

Evaluating and Improving Factuality in Multimodal Abstractive Summarization

2022-11-04 · David Wan, Mohit Bansal

Current metrics for evaluating factuality for abstractive document summarization have achieved high correlations with human judgment, but they do not account for the vision modality and thus are not adequate for vision-a…

Abstractive Text SummarizationDocument Summarization