Grammaticality
View article
Unified language model pre-training for natural language understanding and generation Open
This paper presents a new Unified pre-trained Language Model (UniLM) that can be fine-tuned for both natural language understanding and generation tasks. The model is pre-trained using three types of language modeling tasks: unidirectional…
View article
Is BERT Really Robust? A Strong Baseline for Natural Language Attack on Text Classification and Entailment Open
Machine learning algorithms are often vulnerable to adversarial examples that have imperceptible alterations from the original counterparts but can fool the state-of-the-art models. It is helpful to evaluate or even improve the robustness …
View article
Assessing the Ability of LSTMs to Learn Syntax-Sensitive Dependencies Open
The success of long short-term memory (LSTM) neural networks in language processing is typically attributed to their ability to capture long-distance statistical regularities. Linguistic regularities are often sensitive to syntactic struct…
View article
Learning to Ask: Neural Question Generation for Reading Comprehension Open
We study automatic question generation for sentences from text passages in reading comprehension. We introduce an attention-based sequence learning model for the task and investigate the effect of encoding sentence- vs. paragraph-level inf…
View article
Targeted Syntactic Evaluation of Language Models Open
We present a data set for evaluating the grammaticality of the predictions of a language model. We automatically construct a large number of minimally different pairs of English sentences, each consisting of a grammatical and an ungrammati…
View article
Crosslinguistic influence in the acquisition of a third language: The Linguistic Proximity Model Open
Aims and Objectives: The main goal of the present study is to investigate effects of crosslinguistic influence in third language acquisition by simultaneous bilinguals. We address the following research questions: Do both languages contrib…
View article
Grammaticality, Acceptability, and Probability: A Probabilistic View of Linguistic Knowledge Open
The question of whether humans represent grammatical knowledge as a binary condition on membership in a set of well‐formed sentences, or as a probabilistic property has been the subject of debate among linguists, psychologists, and cogniti…
View article
Effects of Type of Agreement Violation and Utterance Position on the Auditory Processing of Subject-Verb Agreement: An ERP Study Open
Previous ERP studies have often reported two ERP components-LAN and P600-in response to subject-verb (S-V) agreement violations (e.g., the boys (*) runs). However, the latency, amplitude and scalp distribution of these components have been…
View article
Counterfactual Data Augmentation for Mitigating Gender Stereotypes in Languages with Rich Morphology Open
Gender stereotypes are manifest in most of the world's languages and are consequently propagated or amplified by NLP systems. Although research has focused on mitigating gender stereotypes in English, the approaches that are commonly emplo…
View article
Exploring Neural Text Simplification Models Open
We present the first attempt at using sequence to sequence neural networks to model text simplification (TS). Unlike the previously proposed automated TS systems, our neural text simplification (NTS) systems are able to simultaneously perf…
View article
Is BERT Really Robust? Natural Language Attack on Text Classification and Entailment Open
Machine learning algorithms are often vulnerable to adversarial examples that have imperceptible alterations from the original counterparts but can fool the state-of-the-art models. It is helpful to evaluate or even improve the robustness …
View article
A Multilayer Convolutional Encoder-Decoder Neural Network for Grammatical Error Correction Open
We improve automatic correction of grammatical, orthographic, and collocation errors in text using a multilayer convolutional encoder-decoder neural network. The network is initialized with embeddings that make use of character N-gram info…
View article
The Effects of the Timing of Corrective Feedback on the Acquisition of a New Linguistic Structure Open
The article reports on a study investigating the comparative effects of immediate and delayed corrective feedback in learning the English past passive construction, a linguistic structure of which the learners had little prior knowledge. A…
View article
Ground Truth for Grammaticality Correction Metrics Open
Courtney Napoles, Keisuke Sakaguchi, Matt Post, Joel Tetreault. Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 2: Sh…
View article
BLEU is Not Suitable for the Evaluation of Text Simplification Open
BLEU is widely considered to be an informative metric for text-to-text generation, including Text Simplification (TS). TS includes both lexical and structural aspects. In this paper we show that BLEU is not suitable for the evaluation of s…
View article
The empirical base of linguistics Open
Throughout much of the history of linguistics, grammaticality judgments – intuitions about the well-formedness of sentences – have constituted most of the empirical base against which theoretical hypothesis have been tested. Although such …
View article
The empirical base of linguistics: Grammaticality judgments and linguistic methodology Open
Throughout much of the history of linguistics, grammaticality judgments – intuitions about the well-formedness of sentences – have constituted most of the empirical base against which theoretical hypothesis have been tested. Although such …
View article
Learning to Ask: Neural Question Generation for Reading Comprehension Open
We study automatic question generation for sentences from text passages in reading comprehension. We introduce an attention-based sequence learning model for the task and investigate the effect of encoding sentence- vs. paragraph-level inf…
View article
Is BERT Really Robust? A Strong Baseline for Natural Language Attack on Text Classification and Entailment Open
Machine learning algorithms are often vulnerable to adversarial examples that have imperceptible alterations from the original counterparts but can fool the state-of-the-art models. It is helpful to evaluate or even improve the robustness …
View article
WHAT THE GIANT TELLS US ABOUT AGREEING POST-VERBAL SUBJECTS IN XHOSA Open
Constructions with the subject following the verb are a widely studied topic in Bantu linguistics. One such construction, in which the subject is dislocated, is considered not as core subject inversion, but generally as an afterthought con…
View article
A Multilayer Convolutional Encoder-Decoder Neural Network for Grammatical Error Correction Open
We improve automatic correction of grammatical, orthographic, and collocation errors in text using a multilayer convolutional encoder-decoder neural network. The network is initialized with embeddings that make use of character N-gram info…
View article
Reproachatives and imperatives Open
This paper studies constructions dedicated to the expression of an after the fact reprimand to a second person in the languages of Europe. Taking a usage-based perspective, it argues against earlier analyses of these reproachatives as impe…
View article
Cross‐Linguistic Differences in Processing Double‐Embedded Relative Clauses: Working‐Memory Constraints or Language Statistics? Open
An English double‐embedded relative clause from which the middle verb is omitted can often be processed more easily than its grammatical counterpart, a phenomenon known as the grammaticality illusion. This effect has been found to be rever…
View article
Reassessing the Goals of Grammatical Error Correction: Fluency Instead of Grammaticality Open
The field of grammatical error correction (GEC) has grown substantially in recent years, with research directed at both evaluation metrics and improved system performance against those metrics. One unvisited assumption, however, is the rel…
View article
Temporally Regular Musical Primes Facilitate Subsequent Syntax Processing in Children with Specific Language Impairment Open
Children with developmental language disorders have been shown to be also impaired in rhythm and meter perception. Temporal processing and its link to language processing can be understood within the dynamic attending theory. An external s…
View article
The Complex Adaptive System Principles model for bilingualism: Language interactions within and across bilingual minds Open
Aims and objectives/purpose/research question: We propose a model that captures general patterns in bilingual language processing, based on empirical evidence elicited in a variety of experimental studies. We begin by considering what ling…
View article
The interaction between inhibitory control and corrective feedback timing Open
This article reports a study investigating the role of inhibitory control in the acquisition of Spanish noun-adjective gender agreement under different feedback timing conditions. Forty-three Spanish learners completed a communicative task…
View article
The multidimensionality of second language oral fluency: Interfacing cognitive fluency and utterance fluency Open
The current study examined the extent to which cognitive fluency (CF) contributes to utterance fluency (UF) at the level of constructs. A total of 128 Japanese-speaking learners of English completed four speaking tasks—argumentative task, …
View article
Developmental differences in beta and theta power during sentence processing Open
Although very young children process ongoing language quickly and effortlessly, research indicates that they continue to improve and mature in their language skills through adolescence. This prolonged development may be related to differin…
View article
Bilingual and monolingual adults learning an additional language: ERPs reveal differences in syntactic processing Open
It has been suggested that bilinguals learn additional languages ‘better’ than monolinguals. However, evidence is sparse, particularly for grammar. We examined behavioral and neural correlates of learning an additional (artificial) languag…