The aim of this paper is to mitigate the shortcomings of automatic evaluation of open-domain dialog systems through multi-reference evaluation. Existing metrics have been shown to correlate poorly with human judgement, particularly in open-domain dialog. One alternative is to collect human annotations for evaluation, which can be expensive and time consuming. To demonstrate the effectiveness of multi-reference evaluation, we augment the test set of DailyDialog with multiple references. A series of experiments show that the use of multiple references results in improved correlation between several automatic metrics and human judgement for both the quality and the diversity of system output.
more »
« less
A comprehensive assessment of dialog evaluation metrics
Automatic evaluation metrics are a crucial
component of dialog systems research. Standard language evaluation metrics are known
to be ineffective for evaluating dialog. As
such, recent research has proposed a number
of novel, dialog-specific metrics that correlate
better with human judgements. Due to the fast
pace of research, many of these metrics have
been assessed on different datasets and there
has as yet been no time for a systematic comparison between them. To this end, this paper provides a comprehensive assessment of
recently proposed dialog evaluation metrics on
a number of datasets. In this paper, 23 different automatic evaluation metrics are evaluated
on 10 different datasets. Furthermore, the metrics are assessed in different settings, to better qualify their respective strengths and weaknesses. Metrics are assessed (1) on both the
turn level and the dialog level, (2) for different dialog lengths, (3) for different dialog qualities (e.g., coherence, engaging), (4) for different types of response generation models (i.e.,
generative, retrieval, simple models and stateof-the-art models), (5) taking into account the
similarity of different metrics and (6) exploring combinations of different metrics. This
comprehensive assessment offers several takeaways pertaining to dialog evaluation metrics
in general. It also suggests how to best assess
evaluation metrics and indicates promising directions for future work.
more »
« less
- Award ID(s):
- 1924855
- PAR ID:
- 10346876
- Date Published:
- Journal Name:
- ArXivorg
- ISSN:
- 2331-8422
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
The ultimate goal of dialog research is to develop systems that can be effectively used in interactive settings by real users. To this end, we introduced the Interactive Evaluation of Dialog Track at the 9th Dialog System Technology Challenge. This track consisted of two sub-tasks. The first sub-task involved building knowledge-grounded response generation models. The second sub-task aimed to extend dialog models beyond static datasets by assessing them in an interactive setting with real users. Our track challenges participants to develop strong response generation models and explore strategies that extend them to back-and-forth interactions with real users. The progression from static corpora to interactive evaluation introduces unique challenges and facilitates a more thorough assessment of open-domain dialog systems. This paper provides an overview of the track, including the methodology and results. Furthermore, it provides insights into how to best evaluate open-domain dialog models.more » « less
-
Obeid, Iyad ; Selesnick, Ivan ; Picone, Joseph (Ed.)There has been a lack of standardization of the evaluation of sequential decoding systems in the bioengineering community. Assessment of the accuracy of a candidate system’s segmentations and measurement of a false alarm rate are examples of two performance metrics that are very critical to the operational acceptance of a technology. However, measurement of such quantities in a consistent manner require many scoring software implementation details to be resolved. Results can be highly sensitive to these implementation details. In this paper, we revisit and evaluate a set of metrics introduced in our open source scoring software for sequential decoding of multichannel signals. This software was used to rank sixteen automatic seizure detection systems recently developed for the 2020 Neureka® Epilepsy Challenge. The systems produced by the participants provided us with a broad range of design variations that allowed assessment of the consistency of the proposed metrics. We present a comprehensive assessment of four of these new metrics and validate our findings with our previous studies. We also validate a proposed new metric, time-aligned event scoring, that focuses on the segmentation behavior of an algorithm. We demonstrate how we can gain insight into the performance of a system using these metrics.more » « less
-
more » « less
Abstract Evaluation metrics such as precision, recall and normalized discounted cumulative gain have been widely applied in
ad hoc retrieval experiments. They have facilitated the assessment of system performance in various topics over the past decade. However, the effectiveness of such metrics in capturing users’ in-situ search experience, especially in complex search tasks that trigger interactive search sessions, is limited. To address this challenge, it is necessary to adaptively adjust the evaluation strategies of search systems to better respond to users’ changing information needs and evaluation criteria. In this work, we adopt a taxonomy of search task states that a user goes through in different scenarios and moments of search sessions, and perform a meta-evaluation of existing metrics to better understand their effectiveness in measuring user satisfaction. We then built models for predicting task states behind queries based on in-session signals. Furthermore, we constructed and meta-evaluated new state-aware evaluation metrics. Our analysis and experimental evaluation are performed on two datasets collected from a field study and a laboratory study, respectively. Results demonstrate that the effectiveness of individual evaluation metrics varies across task states. Meanwhile, task states can be detected from in-session signals. Our new state-aware evaluation metrics could better reflect in-situ user satisfaction than an extensive list of the widely used measures we analyzed in this work in certain states. Findings of our research can inspire the design and meta-evaluation of user-centered adaptive evaluation metrics, and also shed light on the development of state-aware interactive search systems. -
Image synthesis is a process of converting the input text, sketch, or other sources, i.e., another image or mask, into an image. It is an important problem in the computer vision field, where it has attracted the research community to attempt to solve this challenge at a high level to generate photorealistic images. Different techniques and strategies have been employed to achieve this purpose. Thus, the aim of this paper is to provide a comprehensive review of various image synthesis models covering several aspects. First, the image synthesis concept is introduced. We then review different image synthesis methods divided into three categories: image generation from text, sketch, and other inputs, respectively. Each sub-category is introduced under the proper category based upon the general framework to provide a broad vision of all existing image synthesis methods. Next, brief details of the benchmarked datasets used in image synthesis are discussed along with specifying the image synthesis models that leverage them. Regarding the evaluation, we summarize the metrics used to evaluate the image synthesis models. Moreover, a detailed analysis based on the evaluation metrics of the results of the introduced image synthesis is provided. Finally, we discuss some existing challenges and suggest possible future research directions.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- The DOI is not currently available.
