paper-with-me

Papers

ListOps: A Diagnostic Dataset for Latent Tree Learning

2018-04-17 · NAACL 2018 6 · Nikita Nangia, Samuel R. Bowman

Latent tree learning models learn to parse a sentence without syntactic supervision, and use that parse to build the sentence representation. Existing work on such models has shown that, while they perform well on tasks like sentence classification, they do not learn grammars that conform to any plausible semantic or syntactic formalism (Williams et al., 2018a). Studying the parsing ability of such models in natural language can be challenging due to the inherent complexities of natural language, like having several valid parses for a single sentence. In this paper we introduce ListOps, a toy dataset created to study the parsing ability of latent tree models. ListOps sequences are in the style of prefix arithmetic. The dataset is designed to have a single correct parsing strategy that a system needs to learn to succeed at the task. We show that the current leading latent tree models are unable to learn to parse and succeed at ListOps. These models achieve accuracies worse than purely sequential RNNs.

📄 PDF Abstract BibTeX arXiv:1804.06028

Code (3)

chijames/gst pytorch
neurips-anon-h1ndi29v/verbose-listops jax
yikangshen/Ordered-Memory pytorch

Tasks

DiagnosticListOpsSentenceSentence Classificationvalid

Similar Papers 제목 키워드 기반

Investigating Recurrent Transformers with Dynamic Halt

2024-02-01 · Jishnu Ray Chowdhury, Cornelia Caragea

In this paper, we comprehensively study the inductive biases of two major approaches to augmenting Transformers with a recurrent mechanism: (1) the approach of incorporating a depth-wise recurrence similar to Universal T…

DiagnosticLanguage ModelingLanguage ModellingListOps

Beam Tree Recursive Cells

2023-05-31 · Jishnu Ray Chowdhury, Cornelia Caragea

We propose Beam Tree Recursive Cell (BT-Cell) - a backpropagation-friendly framework to extend Recursive Neural Networks (RvNNs) with beam search for latent structure induction. We further extend this framework by propos…

ListOps

Efficient Beam Tree Recursion

2023-09-21 · NeurIPS 2023 11

Beam Tree Recursive Neural Network (BT-RvNN) was recently proposed as an extension of Gumbel Tree RvNN and it was shown to achieve state-of-the-art length generalization performance in ListOps while maintaining comparabl…

Recursion in Recursion: Two-Level Nested Recursion for Length Generalization with Scalability

2023-09-21 · NeurIPS 2023 11

Binary Balanced Tree Recursive Neural Networks (BBT-RvNNs) enforce sequence composition according to a preset balanced binary tree structure. Thus, their non-linear recursion depth (which is the tree depth) is just $\log…

Context Is Not Comprehension

2025-06-05 · Alex Pan, Mary-Anne Williams

The dominant way of judging Large Language Models (LLMs) has been to ask how well they can recall explicit facts from very long inputs. While today's best models achieve near perfect recall, this masks a harder skill: pe…

ListOps