Subject Verb Agreement
Related Papers
Dependency Grammar Based English Subject-Verb Agreement Evaluation
. As a key factor in English grammar checking, subject-verb agreement evaluation plays an important part in assessing translated English texts. In this paper, we propose a hybrid method for …...
Modeling verbal inflection for English to German SMT
German verbal inflection is frequently wrong in standard statistical machine translation approaches. German verbs agree with subjects in person and num- ber, and they bear information about mood and tense. …...
Exploring the Syntactic Abilities of RNNs with Multi-task Learning
AbstractRecent work has explored the syntactic abilities of RNNs using the subject-verb agreement task, which diagnoses sensitivity to sentence structure. RNNs performed this task well in common cases, but faltered …...
Using Deep Neural Networks to Learn Syntactic Agreement
AbstractWe consider the extent to which different deep neural network (DNN) configurations can learn syntactic relations, by taking up Linzen et al.’s (2016) work on subject-verb agreement with LSTM RNNs. …...
A Simple and Robust Approach to Detecting Subject-Verb Agreement Errors
AbstractWhile rule-based detection of subject-verb agreement (SVA) errors is sensitive to syntactic parsing errors and irregularities and exceptions to the main rules, neural sequential labelers have a tendency to overfit …...
Influence Paths for Characterizing Subject-Verb Number Agreement in LSTM Language Models
AbstractLSTM-based recurrent neural networks are the state-of-the-art for many natural language processing (NLP) tasks. Despite their performance, it is unclear whether, or how, LSTMs learn structural features of natural languages …...
Probing for targeted syntactic knowledge through grammatical error detection
AbstractTargeted studies testing knowledge of subject-verb agreement (SVA) indicate that pre-trained language models encode syntactic information. We assert that if models robustly encode subject-verb agreement, they should be able to …...
Subject Verb Agreement Error Patterns in Meaningless Sentences: Humans vs. BERT
AbstractBoth humans and neural language models are able to perform subject verb number agreement (SVA). In principle, semantics shouldn’t interfere with this task, which only requires syntactic knowledge. In this …...
Assessing the Capacity of Transformer to Abstract Syntactic Representations: A Contrastive Analysis Based on Long-distance Agreement
AbstractMany studies have shown that transformers are able to predict subject-verb agreement, demonstrating their ability to uncover an abstract representation of the sentence in an unsupervised way. Recently, Li et …...
BLM-AgrF: A New French Benchmark to Investigate Generalization of Agreement in Neural Networks
AbstractSuccessful machine learning systems currently rely on massive amounts of data, which are very effective in hiding some of the shallowness of the learned models. To help train models with …...
The Functional Relevance of Probed Information: A Case Study
AbstractRecent studies have shown that transformer models like BERT rely on number information encoded in their representations of sentences’ subjects and head verbs when performing subject-verb agreement. However, probing experiments …...