1 |
How much do language models copy from their training data? Evaluating linguistic novelty in text generation using RAVEN ...
|
|
|
|
BASE
|
|
Show details
|
|
2 |
Picking BERT's Brain: Probing for Linguistic Dependencies in Contextualized Embeddings Using Representational Similarity Analysis ...
|
|
|
|
BASE
|
|
Show details
|
|
4 |
Representations of Syntax [MASK] Useful: Effects of Constituency and Dependency Structure in Recursive LSTMs ...
|
|
|
|
BASE
|
|
Show details
|
|
5 |
Does Syntax Need to Grow on Trees? Sources of Hierarchical Inductive Bias in Sequence-to-Sequence Networks
|
|
|
|
In: Transactions of the Association for Computational Linguistics, Vol 8, Pp 125-140 (2020) (2020)
|
|
BASE
|
|
Show details
|
|
6 |
RNNs Implicitly Implement Tensor Product Representations
|
|
|
|
In: International Conference on Learning Representations ; ICLR 2019 - International Conference on Learning Representations ; https://hal.archives-ouvertes.fr/hal-02274498 ; ICLR 2019 - International Conference on Learning Representations, May 2019, New Orleans, United States (2019)
|
|
BASE
|
|
Show details
|
|
7 |
What do you learn from context? Probing for sentence structure in contextualized word representations ...
|
|
|
|
BASE
|
|
Show details
|
|
8 |
Right for the Wrong Reasons: Diagnosing Syntactic Heuristics in Natural Language Inference ...
|
|
|
|
BASE
|
|
Show details
|
|
9 |
BERTs of a feather do not generalize together: Large variability in generalization across models with similar test set performance ...
|
|
|
|
BASE
|
|
Show details
|
|
10 |
Revisiting the poverty of the stimulus: hierarchical generalization without a hierarchical bias in recurrent neural networks ...
|
|
|
|
BASE
|
|
Show details
|
|
11 |
TAG Parsing with Neural Networks and Vector Representations of Supertags
|
|
|
|
In: Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, ; Conference on Empirical Methods in Natural Language Processing ; https://hal.archives-ouvertes.fr/hal-01771494 ; Conference on Empirical Methods in Natural Language Processing, Sep 2017, Copenhague, Denmark. pp.1712 - 1722 (2017)
|
|
Abstract:
International audience ; We present supertagging-based models for Tree Adjoining Grammar parsing that use neural network architectures and dense vector representation of supertags (elementary trees) to achieve state-of-the-art performance in unlabeled and labeled attachment scores. The shift-reduce parsing model eschews lexical information entirely , and uses only the 1-best supertags to parse a sentence, providing further support for the claim that supertagging is " almost parsing. " We demonstrate that the embedding vector representations the parser induces for supertags possess linguistically interpretable structure, supporting analogies between grammatical structures like those familiar from recent work in distri-butional semantics. This dense representation of supertags overcomes the drawbacks for statistical models of TAG as compared to CCG parsing, raising the possibility that TAG is a viable alternative for NLP tasks that require the assignment of richer structural descriptions to sentences.
|
|
Keyword:
[INFO.INFO-TT]Computer Science [cs]/Document and Text Processing
|
|
URL: https://hal.archives-ouvertes.fr/hal-01771494/file/D17-1180.pdf https://hal.archives-ouvertes.fr/hal-01771494/document https://hal.archives-ouvertes.fr/hal-01771494
|
|
BASE
|
|
Hide details
|
|
|
|