paper-with-me

Papers

BARTScore: Evaluating Generated Text as Text Generation

2021-06-22 · NeurIPS 2021 12 · Weizhe Yuan, Graham Neubig, PengFei Liu

A wide variety of NLP applications, such as machine translation, summarization, and dialog, involve text generation. One major challenge for these applications is how to evaluate whether such generated texts are actually fluent, accurate, or effective. In this work, we conceptualize the evaluation of generated text as a text generation problem, modeled using pre-trained sequence-to-sequence models. The general idea is that models trained to convert the generated text to/from a reference output or the source text will achieve higher scores when the generated text is better. We operationalize this idea using BART, an encoder-decoder based pre-trained model, and propose a metric BARTScore with a number of variants that can be flexibly applied in an unsupervised fashion to evaluation of text from different perspectives (e.g. informativeness, fluency, or factuality). BARTScore is conceptually simple and empirically effective. It can outperform existing top-scoring metrics in 16 of 22 test settings, covering evaluation of 16 datasets (e.g., machine translation, text summarization) and 7 different perspectives (e.g., informativeness, factuality). Code to calculate BARTScore is available at https://github.com/neulab/BARTScore, and we have released an interactive leaderboard for meta-evaluation at http://explainaboard.nlpedia.ai/leaderboard/task-meval/ on the ExplainaBoard platform, which allows us to interactively understand the strengths, weaknesses, and complementarity of each metric.

📄 PDF Abstract BibTeX arXiv:2106.11520

Code (3)

neulab/BARTScore 공식 구현
k-randl/self-explaining_llms pytorch
weipingfu/qgeval pytorch

Tasks

DecoderInformativenessMachine TranslationText GenerationText SummarizationTranslation

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Adam 설명 없음
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…

Similar Papers 제목 키워드 기반

DATScore: Evaluating Translation with Data Augmented Translations

2022-10-12 · Moussa Kamal Eddine, Guokan Shang, Michalis Vazirgiannis

The rapid development of large pretrained language models has revolutionized not only the field of Natural Language Generation (NLG) but also its evaluation. Inspired by the recent work of BARTScore: a metric leveraging …

Data AugmentationLanguage ModelingLanguage ModellingMachine Translation+2

Toward Human-Like Evaluation for Natural Language Generation with Error Analysis

2022-12-20 · Qingyu Lu, Liang Ding, Liping Xie, Kanjian Zhang 외

The state-of-the-art language model-based automatic metrics, e.g. BARTScore, benefiting from large-scale contextualized pre-training, have been successfully used in a wide range of natural language generation (NLG) tasks…

Language ModelingLanguage ModellingMachine TranslationText Generation+1

DiscoScore: Evaluating Text Generation with BERT and Discourse Coherence

2022-01-26 · Wei Zhao, Michael Strube, Steffen Eger

Recently, there has been a growing interest in designing text generation systems from a discourse coherence perspective, e.g., modeling the interdependence between sentences. Still, recent BERT-based evaluation metrics a…

Document Level Machine TranslationMachine TranslationText Generation

AMRFact: Enhancing Summarization Factuality Evaluation with AMR-Driven Negative Samples Generation

2023-11-16 · Haoyi Qiu, Kung-Hsiang Huang, Jingnong Qu, Nanyun Peng

Ensuring factual consistency is crucial for natural language generation tasks, particularly in abstractive summarization, where preserving the integrity of information is paramount. Prior works on evaluating factual cons…

Abstractive Text SummarizationNatural Language InferenceText Generation

LLMs as Narcissistic Evaluators: When Ego Inflates Evaluation Scores

2023-11-16 · Yiqi Liu, Nafise Sadat Moosavi, Chenghua Lin

Automatic evaluation of generated textual content presents an ongoing challenge within the field of NLP. Given the impressive capabilities of modern language models (LMs) across diverse NLP tasks, there is a growing tren…

Language ModelingLanguage Modelling