b'Tal Linzen'

Does Putting a Linguist in the Loop Improve NLU Data Collection?

Many crowdsourced NLP datasets contain systematic gaps and biases that a...
04/15/2021 ∙ by Alicia Parrish, et al. ∙ 0 ∙ share

read it
COGS: A Compositional Generalization Challenge Based on Semantic Interpretation

Natural language is characterized by compositionality: the meaning of a ...
10/12/2020 ∙ by Najoung Kim, et al. ∙ 0 ∙ share

read it
Universal linguistic inductive biases via meta-learning

How do learners acquire languages from the limited data available to the...
06/29/2020 ∙ by R. Thomas McCoy, et al. ∙ 0 ∙ share

read it
How Can We Accelerate Progress Towards Human-like Linguistic Generalization?

This position paper describes and critiques the Pretraining-Agnostic Ide...
05/03/2020 ∙ by Tal Linzen, et al. ∙ 0 ∙ share

read it
Cross-Linguistic Syntactic Evaluation of Word Prediction Models

A range of studies have concluded that neural word prediction models can...
05/01/2020 ∙ by Aaron Mueller, et al. ∙ 0 ∙ share

read it
Representations of Syntax [MASK] Useful: Effects of Constituency and Dependency Structure in Recursive LSTMs

Sequence-based neural networks show significant sensitivity to syntactic...
04/30/2020 ∙ by Michael A Lepori, et al. ∙ 0 ∙ share

read it
Syntactic Data Augmentation Increases Robustness to Inference Heuristics

Pretrained neural models such as BERT, when fine-tuned to perform natura...
04/24/2020 ∙ by Junghyun Min, et al. ∙ 0 ∙ share

read it
Syntactic Structure from Deep Learning

Modern deep neural networks achieve impressive performance in engineerin...
04/22/2020 ∙ by Tal Linzen, et al. ∙ 0 ∙ share

read it
Does syntax need to grow on trees? Sources of hierarchical inductive bias in sequence-to-sequence networks

Learners that are exposed to the same training data might generalize dif...
01/10/2020 ∙ by R. Thomas McCoy, et al. ∙ 0 ∙ share

read it
BERTs of a feather do not generalize together: Large variability in generalization across models with similar test set performance

If the same neural architecture is trained multiple times on the same da...
11/07/2019 ∙ by R. Thomas McCoy, et al. ∙ 0 ∙ share

read it
Discovering the Compositional Structure of Vector Representations with Role Learning Networks

Neural networks (NNs) are able to perform tasks that rely on composition...
10/21/2019 ∙ by Paul Soulos, et al. ∙ 0 ∙ share

read it
Using Priming to Uncover the Organization of Syntactic Representations in Neural Language Models

Neural language models (LMs) perform well on tasks that require sensitiv...
09/23/2019 ∙ by Grusha Prasad, et al. ∙ 0 ∙ share

read it
Quantity doesn't buy quality syntax with neural language models

Recurrent neural networks can learn to predict upcoming words remarkably...
08/31/2019 ∙ by Marten van Schijndel, et al. ∙ 0 ∙ share

read it
Probing What Different NLP Tasks Teach Machines about Function Word Comprehension

We introduce a set of nine challenge tasks that test for the understandi...
04/25/2019 ∙ by Najoung Kim, et al. ∙ 0 ∙ share

read it
Analyzing and Interpreting Neural Networks for NLP: A Report on the First BlackboxNLP Workshop

The EMNLP 2018 workshop BlackboxNLP was dedicated to resources and techn...
04/05/2019 ∙ by Afra Alishahi, et al. ∙ 0 ∙ share

read it
Studying the Inductive Biases of RNNs with Synthetic Variations of Natural Languages

How do typological properties such as word order and morphological case ...
03/15/2019 ∙ by Shauli Ravfogel, et al. ∙ 0 ∙ share

read it
Right for the Wrong Reasons: Diagnosing Syntactic Heuristics in Natural Language Inference

Machine learning systems can often achieve high performance on a test se...
02/04/2019 ∙ by R. Thomas McCoy, et al. ∙ 0 ∙ share

read it
Human few-shot learning of compositional instructions

People learn in fast and flexible ways that have not been emulated by ma...
01/14/2019 ∙ by Brenden M. Lake, et al. ∙ 0 ∙ share

read it
RNNs Implicitly Implement Tensor Product Representations

Recurrent neural networks (RNNs) can learn continuous vector representat...
12/20/2018 ∙ by R. Thomas McCoy, et al. ∙ 0 ∙ share

read it
Non-entailed subsequences as a challenge for natural language inference

Neural network models have shown great success at natural language infer...
11/29/2018 ∙ by R. Thomas McCoy, et al. ∙ 0 ∙ share

read it
Can Entropy Explain Successor Surprisal Effects in Reading?

Human reading behavior is sensitive to surprisal: more predictable words...
10/26/2018 ∙ by Marten van Schijndel, et al. ∙ 0 ∙ share

read it
What can linguistics and deep learning contribute to each other?

Joe Pater's target article calls for greater interaction between neural ...
09/11/2018 ∙ by Tal Linzen, et al. ∙ 0 ∙ share

read it
A Neural Model of Adaptation in Reading

It has been argued that humans rapidly adapt their lexical and syntactic...
08/29/2018 ∙ by Marten van Schijndel, et al. ∙ 0 ∙ share

read it
Targeted Syntactic Evaluation of Language Models

We present a dataset for evaluating the grammaticality of the prediction...
08/27/2018 ∙ by Rebecca Marvin, et al. ∙ 0 ∙ share

read it
Distinct patterns of syntactic agreement errors in recurrent networks and humans

Determining the correct form of a verb in context requires an understand...
07/18/2018 ∙ by Tal Linzen, et al. ∙ 0 ∙ share

read it
Colorless green recurrent networks dream hierarchically

Recurrent neural networks (RNNs) have achieved impressive results in a v...
03/29/2018 ∙ by Kristina Gulordava, et al. ∙ 0 ∙ share

read it
Revisiting the poverty of the stimulus: hierarchical generalization without a hierarchical bias in recurrent neural networks

Syntactic rules in human language usually refer to the hierarchical stru...
02/25/2018 ∙ by R. Thomas McCoy, et al. ∙ 0 ∙ share

read it
Phonological (un)certainty weights lexical activation

Spoken word recognition involves at least two basic computations. First ...
11/17/2017 ∙ by Laura Gwilliams, et al. ∙ 0 ∙ share

read it
Exploring the Syntactic Abilities of RNNs with Multi-task Learning

Recent work has explored the syntactic abilities of RNNs using the subje...
06/12/2017 ∙ by Emile Enguehard, et al. ∙ 0 ∙ share

read it
Assessing the Ability of LSTMs to Learn Syntax-Sensitive Dependencies

The success of long short-term memory (LSTM) neural networks in language...
11/04/2016 ∙ by Tal Linzen, et al. ∙ 0 ∙ share

read it
Issues in evaluating semantic spaces using word analogies

The offset method for solving word analogies has become a standard evalu...
06/24/2016 ∙ by Tal Linzen, et al. ∙ 0 ∙ share

read it

Tal Linzen

Featured Co-authors