-
COLING 20222022To evaluate the performance of a multi-domain goal-oriented Dialogue System (DS), it is important to understand what the users’ goals are for the conversations and whether those goals are successfully achieved. The success rate of goals directly correlates with user satisfaction and perceived usefulness of the DS. In this paper, we propose a novel automatic dialogue evaluation framework that jointly performs
-
EMNLP 2022 Seventh Conference on Machine Translation (WMT22)2022We present a very simple method for extending pretrained machine translation metrics to incorporate document-level context. We apply our method to four popular metrics: BERTScore, Prism, COMET, and the reference-free metric COMET-QE. We evaluate our document-level metrics on the MQM annotations from the WMT 2021 metrics shared task and find that the document-level metrics outperform their sentence-level
-
COLING 20222022Relational web-tables are significant sources of structural information that are widely used for relation extraction and population of facts into knowledge graphs. To transform the webtable data into knowledge, we need to identify the relations that exist between column pairs. Currently, there are only a handful of publicly available datasets with relations annotated against natural web-tables. Most datasets
-
KDD 2022 Workshop on Deep Learning Practice and Theory for High-Dimensional Sparse and Imbalanced Data (DLP)2022In this paper, we introduce a targeted data enrichment framework to mitigate the problem of biased training data distribution. In real world applications, it is often observed that the training data distribution differs from the online live traffic data due to multiple reasons such as topic changes, seasonalities, the nature of users. Our targeted data augmentation techniques generate samples that are most
-
EMNLP 2022 Seventh Conference on Machine Translation (WMT22)2022Customer feedback can be an important signal for improving commercial machine translation systems. One solution for fixing specific translation errors is to remove the related erroneous training instances followed by re-training of the machine translation system, which we refer to as instance-specific data filtering. Influence functions (IF) have been shown to be effective in finding such relevant training
Related content
-
March 23, 2023The center will support UIUC researchers in their development of novel approaches to conversational AI systems.
-
March 20, 2023With Alexa Arena, developers can create simulated missions in which humans interact with virtual robots, providing a natural way to build generalizable AI models.
-
March 13, 2023Learn how Amazon uses machine-learning techniques to modify different aspects of speech — tone, phrasing, intonation, expressiveness, and accent — to create unique Alexa responses.
-
February 15, 2023Second iteration features five new teams.
-
February 9, 2023The collaboration includes Amazon funding for faculty research projects, with an initial focus on machine learning and natural-language processing.
-
February 7, 2023Parmida Beigi, an Amazon senior research scientist, shares a lifetime worth of experience, and uses her skills to help others grow into machine learning career paths.