Abstract
We propose a Cross-lingual Encoder-Decoder model that simultaneously translates and generates sentences with Semantic Role Labeling annotations in a resource-poor target language. Unlike annotation projection techniques, our model does not need parallel data during inference time. Our approach can be applied in monolingual, multilingual and cross-lingual settings and is able to produce dependency-based and span-based SRL annotations. We benchmark the labeling performance of our model in different monolingual and multilingual settings using well-known SRL datasets. We then train our model in a cross-lingual setting to generate new SRL labeled data. Finally, we measure the effectiveness of our method by using the generated data to augment the training basis for resource-poor languages and perform manual evaluation to show that it produces high-quality sentences and assigns accurate semantic role annotations. Our proposed architecture offers a flexible method for leveraging SRL data in multiple languages.
Highlights
Semantic Role Labeling (SRL) extracts semantic predicate-argument structure from sentences. This has proven to be useful in Neural Machine Translation (NMT) (Marcheggiani et al, 2018), Multidocument-summarization (Khan et al, 2015), AMR parsing (Wang et al, 2015) and Reading Comprehension (Mihaylov and Frank, 2019)
The underlying corpus for this dataset is composed of Machine Translation (MT) parallel corpora: Europarl (Koehn, 2005) for ENDE, and UN (Ziemski et al, 2016) for EN-FR
We presented the first cross-lingual SRL system that translates a sentence and concurrently labels it with PropBank roles
Summary
Semantic Role Labeling (SRL) extracts semantic predicate-argument structure from sentences. While former SRL systems rely on syntactic features (Punyakanok et al, 2008; Tackstrom et al, 2015), recent neural approaches learn to model both argument detection and role classification given a Figure 1: We propose an Encoder-Decoder model that translates a sentence into a target language and applies SRL labeling to the translated words. In this example we translate from English to German and label roles for the predicate have. Our universal Enc-Dec model lends itself to monolingual, multilingual and crosslingual SRL and yields competitive performance
Sign-in/Register to view highlights & summary 
Published Version (
Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call