Search
63 resources
-
Jing Xu, Da Ju, Margaret Li|Mar 14th, 2021|conferencePaperJing Xu, Da Ju, Margaret LiMar 14th, 2021
-
Weizhe Yuan, Graham Neubig, Pengfei Liu,...|Mar 14th, 2021|journalArticleWeizhe Yuan, Graham Neubig, Pengfei Liu,...Mar 14th, 2021
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...
-
Tianyi Zhang, Varsha Kishore, Felix Wu|Feb 24th, 2020|preprintTianyi Zhang, Varsha Kishore, Felix WuFeb 24th, 2020
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...
-
Esin Durmus, He He, Mona Diab|Mar 14th, 2020|conferencePaperEsin Durmus, He He, Mona DiabMar 14th, 2020
-
Shikib Mehri, Maxine Eskenazi|Mar 14th, 2020|conferencePaperShikib Mehri, Maxine EskenaziMar 14th, 2020
-
Thibault Sellam, Dipanjan Das, Ankur Par...|Mar 14th, 2020|conferencePaperThibault Sellam, Dipanjan Das, Ankur Par...Mar 14th, 2020
-
V Vijayaraghavan, Jack Brian Cooper, oth...|Mar 14th, 2020|journalArticleV Vijayaraghavan, Jack Brian Cooper, oth...Mar 14th, 2020
-
Samuel Holmes, Anne Moorhead, Raymond Bo...|Sep 10th, 2019|conferencePaperSamuel Holmes, Anne Moorhead, Raymond Bo...Sep 10th, 2019
-
Elizabeth Clark, Asli Celikyilmaz, Noah ...|Mar 14th, 2019|conferencePaperElizabeth Clark, Asli Celikyilmaz, Noah ...Mar 14th, 2019
-
Chris Van Der Lee, Albert Gatt, Emiel Va...|Mar 14th, 2019|conferencePaperChris Van Der Lee, Albert Gatt, Emiel Va...Mar 14th, 2019
-
Kavita Ganesan|Mar 5th, 2018|preprintKavita GanesanMar 5th, 2018
Evaluation of summarization tasks is extremely crucial to determining the quality of machine generated summaries. Over the last decade, ROUGE has become the standard automatic evaluation measure for evaluating summarization tasks. While ROUGE has been shown to be effective in capturing n-gram overlap between system and human composed summaries, there are several limitations with the existing ROUGE measures in terms of capturing synonymous concepts and coverage of topics. Thus, often times...
-
Ryan Lowe, Michael Noseworthy, Iulian Vl...|Mar 14th, 2017|conferencePaperRyan Lowe, Michael Noseworthy, Iulian Vl...Mar 14th, 2017
-
Ramakrishna Vedantam, C. Lawrence Zitnic...|Jun 2nd, 2015|preprintRamakrishna Vedantam, C. Lawrence Zitnic...Jun 2nd, 2015
Automatically describing an image with a sentence is a long-standing challenge in computer vision and natural language processing. Due to recent progress in object detection, attribute classification, action recognition, etc., there is renewed interest in this area. However, evaluating the quality of descriptions has proven to be challenging. We propose a novel paradigm for evaluating image descriptions that uses human consensus. This paradigm consists of three main parts: a new...
-
Sami Virpioja, Stig-Arne Grönroos|Mar 14th, 2015|conferencePaperSami Virpioja, Stig-Arne GrönroosMar 14th, 2015
-
David Hutchison, Takeo Kanade, Josef Kit...|Mar 14th, 2013|bookSectionDavid Hutchison, Takeo Kanade, Josef Kit...Mar 14th, 2013
-
Lise Getoor, Ashwin Machanavajjhala|Aug 14th, 2012|journalArticleLise Getoor, Ashwin MachanavajjhalaAug 14th, 2012
This tutorial brings together perspectives on ER from a variety of fields, including databases, machine learning, natural language processing and information retrieval, to provide, in one setting, a survey of a large body of work. We discuss both the practical aspects and theoretical underpinnings of ER. We describe existing solutions, current challenges, and open research problems.
-
Ehud Reiter, Anja Belz|Dec 14th, 2009|journalArticleEhud Reiter, Anja BelzDec 14th, 2009
There is growing interest in using automatically computed corpus-based evaluation metrics to evaluate Natural Language Generation (NLG) systems, because these are often considerably cheaper than the human-based evaluations which have traditionally been used in NLG. We review previous work on NLG evaluation and on validation of automatic metrics in NLP, and then present the results of two studies of how well some metrics which are popular in other areas of NLP (notably BLEU and ROUGE)...
-
Joseph P. Turian, Luke Shen, I. Dan Mela...|Jan 1st, 2006|conferencePaperJoseph P. Turian, Luke Shen, I. Dan Mela...Jan 1st, 2006
Evaluation of MT evaluation measures is limited by inconsistent human judgment data. Nonetheless, machine translation can be evaluated using the well-known measures precision, recall, and their average, the F-measure. The unigram-based F-measure has significantly higher correlation with human judgments than recently proposed alternatives. More importantly, this standard measure has an intuitive graphical interpretation, which can facilitate insight into how MT systems might be improved. The...
-
David Hutchison, Takeo Kanade, Josef Kit...|Mar 14th, 2004|bookSectionDavid Hutchison, Takeo Kanade, Josef Kit...Mar 14th, 2004
-
Chin-Yew Lin, Franz Josef Och|Mar 14th, 2004|conferencePaperChin-Yew Lin, Franz Josef OchMar 14th, 2004