English
Related papers

Related papers: DiscoScore: Evaluating Text Generation with BERT a…

200 papers

Recently BERT has been adopted for document encoding in state-of-the-art text summarization models. However, sentence-based extractive models often result in redundant or uninformative phrases in the extracted summaries. Also, long-range…

Computation and Language · Computer Science 2020-04-28 Jiacheng Xu , Zhe Gan , Yu Cheng , Jingjing Liu

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,…

Computation and Language · Computer Science 2020-02-25 Tianyi Zhang , Varsha Kishore , Felix Wu , Kilian Q. Weinberger , Yoav Artzi

Evaluation metrics are a key ingredient for progress of text generation systems. In recent years, several BERT-based evaluation metrics have been proposed (including BERTScore, MoverScore, BLEURT, etc.) which correlate much better with…

Computation and Language · Computer Science 2021-11-02 Marvin Kaster , Wei Zhao , Steffen Eger

Recent advances in pre-trained language models have significantly improved neural response generation. However, existing methods usually view the dialogue context as a linear sequence of tokens and learn to generate the next word through…

Computation and Language · Computer Science 2021-12-14 Xiaodong Gu , Kang Min Yoo , Jung-Woo Ha

The evaluation of recent embedding-based evaluation metrics for text generation is primarily based on measuring their correlation with human evaluations on standard benchmarks. However, these benchmarks are mostly from similar domains to…

Computation and Language · Computer Science 2022-09-08 Doan Nam Long Vu , Nafise Sadat Moosavi , Steffen Eger

While subjective assessments have been the gold standard for evaluating speech generation, there is a growing need for objective metrics that are highly correlated with human subjective judgments due to their cost efficiency. This paper…

Modeling discourse -- the linguistic phenomena that go beyond individual sentences, is a fundamental yet challenging aspect of natural language processing (NLP). However, existing evaluation benchmarks primarily focus on the evaluation of…

Computation and Language · Computer Science 2023-07-25 Longyue Wang , Zefeng Du , Donghuai Liu , Deng Cai , Dian Yu , Haiyun Jiang , Yan Wang , Leyang Cui , Shuming Shi , Zhaopeng Tu

We present novel automatic metrics for machine translation evaluation that use discourse structure and convolution kernels to compare the discourse tree of an automatic translation with that of the human reference. We experiment with five…

Computation and Language · Computer Science 2019-12-02 Shafiq Joty , Francisco Guzman , Lluis Marquez , Preslav Nakov

Recent advances in automatic evaluation metrics for text have shown that deep contextualized word representations, such as those generated by BERT encoders, are helpful for designing metrics that correlate well with human judgements. At the…

Computation and Language · Computer Science 2020-10-14 Xi Chen , Nan Ding , Tomer Levinboim , Radu Soricut

Dialogue topic segmentation is critical in several dialogue modeling problems. However, popular unsupervised approaches only exploit surface features in assessing topical coherence among utterances. In this work, we address this limitation…

Computation and Language · Computer Science 2021-06-15 Linzi Xing , Giuseppe Carenini

A new metric \texttt{BaryScore} to evaluate text generation based on deep contextualized embeddings e.g., BERT, Roberta, ELMo) is introduced. This metric is motivated by a new framework relying on optimal transport tools, i.e., Wasserstein…

Computation and Language · Computer Science 2021-09-10 Pierre Colombo , Guillaume Staerman , Chloe Clavel , Pablo Piantanida

A robust evaluation metric has a profound impact on the development of text generation systems. A desirable metric compares system output against references based on their semantics rather than surface forms. In this paper we investigate…

Computation and Language · Computer Science 2019-09-27 Wei Zhao , Maxime Peyrard , Fei Liu , Yang Gao , Christian M. Meyer , Steffen Eger

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 the BART language…

Computation and Language · Computer Science 2022-10-14 Moussa Kamal Eddine , Guokan Shang , Michalis Vazirgiannis

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 generated output. In this…

Software Engineering · Computer Science 2023-11-01 Shuyan Zhou , Uri Alon , Sumit Agarwal , Graham Neubig

Disentanglement is a problem in which multiple conversations occur in the same channel simultaneously, and the listener should decide which utterance is part of the conversation he will respond to. We propose a new model, named Dialogue…

Computation and Language · Computer Science 2021-09-14 Tianda Li , Jia-Chen Gu , Xiaodan Zhu , Quan Liu , Zhen-Hua Ling , Zhiming Su , Si Wei

Discourse coherence plays an important role in the translation of one text. However, the previous reported models most focus on improving performance over individual sentence while ignoring cross-sentence links and dependencies, which…

Computation and Language · Computer Science 2018-11-15 Hao Xiong , Zhongjun He , Hua Wu , Haifeng Wang

Existing metrics for assessing question generation not only require costly human reference but also fail to take into account the input context of generation, rendering the lack of deep understanding of the relevance between the generated…

Computation and Language · Computer Science 2022-05-02 Xiaoqiang Wang , Bang Liu , Siliang Tang , Lingfei Wu

Word Error Rate (WER) is the primary metric used to assess automatic speech recognition (ASR) model quality. It has been shown that ASR models tend to have much higher WER on speakers with speech impairments than typical English speakers.…

Audio and Speech Processing · Electrical Eng. & Systems 2022-09-23 Jimmy Tobin , Qisheng Li , Subhashini Venugopalan , Katie Seaver , Richard Cave , Katrin Tomanek

Online discourse is often perceived as polarized and unproductive. While some conversational discourse parsing frameworks are available, they do not naturally lend themselves to the analysis of contentious and polarizing discussions.…

Computation and Language · Computer Science 2020-12-09 Stepan Zakharov , Omri Hadar , Tovit Hakak , Dina Grossman , Yifat Ben-David Kolikant , Oren Tsur

The evaluation of discourse-level translation in expert domains remains inadequate, despite its centrality to knowledge dissemination and cross-lingual scholarly communication. While these translations demand discourse-level coherence and…

‹ Prev 1 2 3 10 Next ›