paper-with-me

Papers

Do LSTMs Learn Compositionally?

2019-05-28 · Naomi Saphra, Adam Lopez

LSTM-based language models exhibit compositionality in their representations, but how this behavior emerges over the course of training has not been explored. Analyzing synthetic data experiments with contextual decomposition, we find that LSTMs learn long-range dependencies compositionally by building them from shorter constituents during training.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Recursive Neural Networks with Bottlenecks Diagnose (Non-)Compositionality

2023-01-31 · Verna Dankers, Ivan Titov

A recent line of work in NLP focuses on the (dis)ability of models to generalise compositionally for artificial languages. However, when considering natural language tasks, the data involved is not strictly, or locally, …

Sentiment AnalysisSentiment Classification

When can transformers compositionally generalize in-context?

2024-07-17 · Seijin Kobayashi, Simon Schug, Yassir Akram, Florian Redhardt 외

Many tasks can be composed from a few independent components. This gives rise to a combinatorial explosion of possible tasks, only some of which might be encountered during training. Under what circumstances can transfor…

Propositional Logic for Probing Generalization in Neural Networks

2025-06-10 · Anna Langedijk, Jaap Jumelet, Willem Zuidema

The extent to which neural networks are able to acquire and represent symbolic rules remains a key topic of research and debate. Much current work focuses on the impressive capabilities of large language models, as well …

Negation

Detecting Compositionally Out-of-Distribution Examples in Semantic Parsing

2021-11-01 · Findings (EMNLP) 2021 11 · Denis Lukovnikov, Sina Daubener, Asja Fischer

While neural networks are ubiquitous in state-of-the-art semantic parsers, it has been shown that most standard models suffer from dramatic performance losses when faced with compositionally out-of-distribution (OOD) dat…

Out of Distribution (OOD) DetectionSemantic Parsing

Compositional generalization through meta sequence-to-sequence learning

2019-06-12 · NeurIPS 2019 12 · Brenden M. Lake

People can learn a new concept and use it compositionally, understanding how to "blicket twice" after learning how to "blicket." In contrast, powerful sequence-to-sequence (seq2seq) neural networks fail such tests of com…