Catalogue Search | MBRL
Are you sure you want to remove the book from the shelf?
{{itemTitle}}
32,333
result(s) for
"American English"
Sort by:
AI generates covertly racist decisions about people based on their dialect
Hundreds of millions of people now interact with language models, with uses ranging from help with writing
1
,
2
to informing hiring decisions
3
. However, these language models are known to perpetuate systematic racial prejudices, making their judgements biased in problematic ways about groups such as African Americans
4
–
7
. Although previous research has focused on overt racism in language models, social scientists have argued that racism with a more subtle character has developed over time, particularly in the United States after the civil rights movement
8
,
9
. It is unknown whether this covert racism manifests in language models. Here, we demonstrate that language models embody covert racism in the form of dialect prejudice, exhibiting raciolinguistic stereotypes about speakers of African American English (AAE) that are more negative than any human stereotypes about African Americans ever experimentally recorded. By contrast, the language models’ overt stereotypes about African Americans are more positive. Dialect prejudice has the potential for harmful consequences: language models are more likely to suggest that speakers of AAE be assigned less-prestigious jobs, be convicted of crimes and be sentenced to death. Finally, we show that current practices of alleviating racial bias in language models, such as human preference alignment, exacerbate the discrepancy between covert and overt stereotypes, by superficially obscuring the racism that language models maintain on a deeper level. Our findings have far-reaching implications for the fair and safe use of language technology.
Despite efforts to remove overt racial prejudice, language models using artificial intelligence still show covert racism against speakers of African American English that is triggered by features of the dialect.
Journal Article
The 20th century children's poetry treasury
A collection of more than 200 poems by such modern poets as Nikki Grimes, John Ciardi, Karla Kuskin, Ted Hughes, e.e. cummings, Eve Merriam, Deborah Chandra, Arnold Adoff, and more than 100 others.
Book
Hate speech detection and racial bias mitigation in social media based on BERT model
Disparate biases associated with datasets and trained classifiers in hateful and abusive content identification tasks have raised many concerns recently. Although the problem of biased datasets on abusive language detection has been addressed more frequently, biases arising from trained classifiers have not yet been a matter of concern. In this paper, we first introduce a transfer learning approach for hate speech detection based on an existing pre-trained language model called BERT (Bidirectional Encoder Representations from Transformers) and evaluate the proposed model on two publicly available datasets that have been annotated for racism, sexism, hate or offensive content on Twitter. Next, we introduce a bias alleviation mechanism to mitigate the effect of bias in training set during the fine-tuning of our pre-trained BERT-based model for hate speech detection. Toward that end, we use an existing regularization method to reweight input samples, thereby decreasing the effects of high correlated training set' s n-grams with class labels, and then fine-tune our pre-trained BERT-based model with the new re-weighted samples. To evaluate our bias alleviation mechanism, we employed a cross-domain approach in which we use the trained classifiers on the aforementioned datasets to predict the labels of two new datasets from Twitter, AAE-aligned and White-aligned groups, which indicate tweets written in African-American English (AAE) and Standard American English (SAE), respectively. The results show the existence of systematic racial bias in trained classifiers, as they tend to assign tweets written in AAE from AAE-aligned group to negative classes such as racism, sexism, hate, and offensive more often than tweets written in SAE from White-aligned group. However, the racial bias in our classifiers reduces significantly after our bias alleviation mechanism is incorporated. This work could institute the first step towards debiasing hate speech and abusive language detection systems.
Journal Article
The importance of feeling english
American literature is typically seen as something that inspired its own conception and that sprang into being as a cultural offshoot of America's desire for national identity. But what of the vast precedent established by English literature, which was a major American import between 1750 and 1850? In The Importance of Feeling English, Leonard Tennenhouse revisits the landscape of early American literature and radically revises its features. Using the concept of transatlantic circulation, he shows how some of the first American authors--from poets such as Timothy Dwight and Philip Freneau to novelists like William Hill Brown and Charles Brockden Brown--applied their newfound perspective to pre-existing British literary models. These American \"re-writings\" would in turn inspire native British authors such as Jane Austen and Horace Walpole to reconsider their own ideas of subject, household, and nation. The enduring nature of these literary exchanges dramatically recasts early American literature as a literature of diaspora, Tennenhouse argues--and what made the settlers' writings distinctly and indelibly American was precisely their insistence on reproducing Englishness, on making English identity portable and adaptable. Written in an incisive and illuminating style, The Importance of Feeling English reveals the complex roots of American literature, and shows how its transatlantic movement aided and abetted the modernization of Anglophone culture at large.
eBook
Specific Language Impairment in African American English and Southern White English: Measures of Tense and Agreement With Dialect-Informed Probes and Strategic Scoring
Purpose: In African American English and Southern White English, we examined whether children with specific language impairment (SLI) overtly mark tense and agreement structures at lower percentages than typically developing (TD) controls, while also examining the effects of dialect, structure, and scoring approach. Method: One hundred six kindergartners completed 4 dialect-informed probes targeting 8 tense and agreement structures. The 3 scoring approaches varied in the treatment of nonmainstream English forms and responses coded as Other (i.e., those not obligating the target structure). The unmodified approach counted as correct only mainstream overt forms out of all responses, the modified approach counted as correct all mainstream and nonmainstream overt forms and zero forms out of all responses, and the strategic approach counted as correct all mainstream and nonmainstream overt forms out of all responses except those coded as Other. Results: With the probes combined and separated, the unmodified and strategic scoring approaches showed lower percentages of overt marking by the SLI groups than by the TD groups; this was not always the case for the modified scoring approach. With strategic scoring and dialect-specific cut scores, classification accuracy (SLI vs. TD) was highest for the 8 individual structures considered together, the past tense probe, and the past tense probe irregular items. Dialect and structure effects and dialect differences in classification accuracy also existed. Conclusions: African American English- and Southern White English-speaking kindergartners with SLI overtly mark tense and agreement at lower percentages than same dialect-speaking TD controls. Strategic scoring of dialect-informed probes targeting tense and agreement should be pursued in research and clinical practice.
Journal Article
The Random House book of poetry for children
More than 550 poems by American, English, and anonymous authors.
Book
The impact of dialect differences on spoken language comprehension
Research has suggested that children who speak African American English (AAE) have difficulty using features produced in Mainstream American English (MAE) but not AAE, to comprehend sentences in MAE. However, past studies mainly examined dialect features, such as verbal -s, that are produced as final consonants with shorter durations when produced in conversation which impacts their phonetic saliency. Therefore, it is unclear if previous results are due to the phonetic saliency of the feature or how AAE speakers process MAE dialect features more generally. This study evaluated if there were group differences in how AAE- and MAE-speaking children used the auxiliary verbs was and were, a dialect feature with increased phonetic saliency but produced differently between the dialects, to interpret sentences in MAE. Participants aged 6, 5–10, and 0 years, who spoke MAE or AAE, completed the DELV-ST, a vocabulary measure (PVT), and a sentence comprehension task. In the sentence comprehension task, participants heard sentences in MAE that had either unambiguous or ambiguous subjects. Sentences with ambiguous subjects were used to evaluate group differences in sentence comprehension. AAE-speaking children were less likely than MAE-speaking children to use the auxiliary verbs was and were to interpret sentences in MAE. Furthermore, dialect density was predictive of Black participant’s sensitivity to the auxiliary verb. This finding is consistent with how the auxiliary verb is produced between the two dialects: was is used to mark both singular and plural subjects in AAE, while MAE uses was for singular and were for plural subjects. This study demonstrated that even when the dialect feature is more phonetically salient, differences between how verb morphology is produced in AAE and MAE impact how AAE-speaking children comprehend MAE sentences.
Journal Article