We lifted 3 functions out of this paper's own repositories and ran 0 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 |
|---|---|---|
| facebookresearch/latent-treelstm | canonical | 0 of 3 |
| Function | Status | Where it lives |
|---|---|---|
| clamp_grad | Not yet run | facebookresearch/latent-treelstm/utils.py pointer only (licence: MIT) · get_code("a491b0ceb6f33269") |
| get_logger | Not yet run | facebookresearch/latent-treelstm/utils.py pointer only (licence: MIT) · get_code("65f16c8097639496") |
| get_lr_scheduler | Not yet run | facebookresearch/latent-treelstm/utils.py pointer only (licence: MIT) · get_code("6bfbb52eff0a6e4a") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
There has been considerable attention devoted to models that learn to jointly infer an expression's syntactic structure and its semantics. Yet, \citet{NangiaB18} has recently shown that the current best systems fail to learn the correct parsing strategy on mathematical expressions generated from a simple context-free grammar. In this work, we present a recursive model inspired by \newcite{ChoiYL18} that reaches near perfect accuracy on this task. Our model is composed of two separated modules for syntax and semantics. They are cooperatively trained with standard continuous and discrete optimization schemes. Our model does not require any linguistic structure for supervision and its recursive nature allows for out-of-domain generalization with little loss in performance. Additionally, our approach performs competitively on several natural language tasks, such as Natural Language Inference or Sentiment Analysis.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("1902.09393")
get_code_for_paper("1902.09393")
have("1902.09393")
Connect an agent — have() is free.