Yue Zhang, Xuefeng Bai, Yulong Chen
We lifted 5 functions out of this paper's own repositories and ran 4 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.
| Repository | Role | Ran |
|---|---|---|
| muyeby/AMRBART | canonical | 3 of 3 |
| goodbai-nlp/amrbart | — | 1 of 2 |
| Function | Status | Where it lives |
|---|---|---|
| joint_infilling_full | Ran | goodbai-nlp/amrbart/pre-train/common/utils.py code served (permissive licence) · get_code("3f7786bc696c91ec") |
| label_smoothed_nll_loss | Ran | muyeby/AMRBART/fine-tune/seq2seq_trainer.py code served (permissive licence) · get_code("fadc10fc2c451c92") |
| shift_tokens_right | Ran | muyeby/AMRBART/fine-tune/model_interface/modeling_bart.py code served (permissive licence) · get_code("cfb09657fff12fcf") |
| shift_tokens_right | Ran | muyeby/AMRBART/pre-train/run_multitask_unified_pretraining.py code served (permissive licence) · get_code("59b0b785b926c986") |
| sentence_infilling | Not yet run | goodbai-nlp/amrbart/pre-train/common/utils.py code served (permissive licence) · get_code("d0b58628f19131d6") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
meaning representation (AMR) highlights the core semantic information of text in a graph structure. Recently, pre-trained language models (PLMs) have advanced tasks of AMR parsing and AMR-to-text generation, respectively. However, PLMs are typically pretrained on textual data, thus are sub-optimal for modeling structural knowledge. To this end, we investigate graph self-supervised training to improve the structure awareness of PLMs over AMR graphs. In particular, we introduce two graph auto-encoding strategies for graphto-graph pre-training and four tasks to integrate text and graph information during pre-training. We further design a unified framework to bridge the gap between pre-training and fine-tuning tasks. Experiments on both AMR parsing and AMR-to-text generation show the superiority of our model. To our knowledge, we are the first to consider pre-training on semantic graphs.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2203.07836")
get_code_for_paper("2203.07836")
have("2203.07836")
Connect an agent — have() is free.