… We investigate enhancing AMR-to-text decoding by integrating online back-parsing,
simultaneously predicting a projected AMR graph on the target sentence while it is being …

… We linearize an AMR graph into a sequence, so that both AMR parsing and AMR-to-text
generation can be performed using a seq2seq model. In addition, it allows pre-training on AMR …

… of heterogeneous subgraphs; 4) BetterG-Transformer [19], a transformer-based model
that generates sentences with additional structural reconstruction goals; 5)Back-Parsing [28] …

… by using a strong parser for back-parsing. It may be beneficial to use strong AMR-to-text
systems to generate from candidate AMRs, and to match the generations against the source …

… In this work, we focus on AMR-to-text generation where the goal is to generate a fluent
and grammatical sentence that is faithful to a given AMR graph (See Figure 1a). AMR is a …

Meaning Representation (AMR) parsing aims to predict an AMR graph from textual input.
Recently, there has been notable growth in AMR parsing performance. However, most existing …

… For example, as shown in Figure 1(a), AMR-to-text generation is to generate a sentence
that … further performs re-scoring based on AMR back-parsing for post processing. RA-TransCNN …

… By adding online back-parsing to the Decoder network, the structure information of the …
Amr-to-text generation with synchronous node replacement grammar. In ACL. Linfeng Song…

… [203] propose an alternate approach to fine-tuning GPT-2 for AMR-to-text generation where
… Online Back-Parsing for AMR-to-Text Generation. In Proceedings of the 2020 Conference on …

… More than half of the corpus of the AMR 3.0 dataset comes from internet forums and blogs,
which are similar to the Twitter dataset as they are both social media. As a result, the AMR …