| 4 |
Structural Supervision Improves Few-Shot Learning and Syntactic Generalization in Neural Language Models
|
|
|
|
In: Association for Computational Linguistics (2021)
|
|
Abstract:
Humans can learn structural properties about a word from minimal experience, and deploy their learned syntactic representations uniformly in different grammatical contexts. We assess the ability of modern neural language models to reproduce this behavior in English and evaluate the effect of structural supervision on learning outcomes. First, we assess few-shot learning capabilities by developing controlled experiments that probe models’ syntactic nominal number and verbal argument structure generalizations for tokens seen as few as two times during training. Second, we assess invariance properties of learned representation: the ability of a model to transfer syntactic generalizations from a base context (e.g., a simple declarative active-voice sentence) to a transformed context (e.g., an interrogative sentence). We test four models trained on the same dataset: an n-gram baseline, an LSTM, and two LSTM-variants trained with explicit structural supervision (Dyer et al., 2016; Charniak et al., 2016). We find that in most cases, the neural models are able to induce the proper syntactic generalizations after minimal exposure, often from just two examples during training, and that the two structurally supervised models generalize more accurately than the LSTM model. All neural models are able to leverage information learned in base contexts to drive expectations in transformed contexts, indicating that they have learned some invariance properties of syntax.
|
|
URL: https://hdl.handle.net/1721.1/138280
|
|
BASE
|
|
Hide details
|
|
|
| 5 |
Structural Supervision Improves Learning of Non-Local Grammatical Dependencies
|
|
|
|
In: Association for Computational Linguistics (2021)
|
|
BASE
|
|
Show details
|
|
|
| 6 |
Event-Driven News Stream Clustering using Entity-Aware Contextual Embeddings ...
|
|
|
|
BASE
|
|
Show details
|
|
|
| 8 |
On the Evolution of Syntactic Information Encoded by BERT's Contextualized Representations ...
|
|
|
|
BASE
|
|
Show details
|
|
|
| 9 |
How much pretraining data do language models need to learn syntax? ...
|
|
|
|
BASE
|
|
Show details
|
|
|
| 14 |
Universal Dependencies 2.2
|
|
|
|
In: https://hal.archives-ouvertes.fr/hal-01930733 ; 2018 (2018)
|
|
BASE
|
|
Show details
|
|
|
| 18 |
Multilingual Neural Machine Translation with Task-Specific Attention ...
|
|
|
|
BASE
|
|
Show details
|
|
|
| 19 |
Scheduled Multi-Task Learning: From Syntax to Translation ...
|
|
|
|
BASE
|
|
Show details
|
|
|
|
|
