An official website of the United States government
Sentiment classification typically relies on a large amount of labeled data. In practice, the availability of labels is highly imbalanced among different languages, e.g., more English texts are labeled than texts in any other languages, which creates a considerable inequality in the quality of related information services received by users speaking different languages. To tackle this problem, cross-lingual sentiment classification approaches aim to transfer knowledge learned from one language that has abundant labeled examples (i.e., the source language, usually English) to another language with fewer labels (i.e., the target language). The source and the target languages are usually bridged through off-the-shelf machine translation tools. Through such a channel, cross-language sentiment patterns can be successfully learned from English and transferred into the target languages. This approach, however, often fails to capture sentiment knowledge specific to the target language, and thus compromises the accuracy of the downstream classification task. In this paper, we employ emojis, which are widely available in many languages, as a new channel to learn both the cross-language and the language-specific sentiment patterns. We propose a novel representation learning method that uses emoji prediction as an instrument to learn respective sentiment-aware representations for each language. The learned representations are then integrated to facilitate cross-lingual sentiment classification. The proposed method demonstrates state-of-the-art performance on benchmark datasets, which is sustained even when sentiment labels are scarce.
more »
« less
NollySenti: Leveraging Transfer Learning and Machine Translation for Nigerian Movie Sentiment Classification
Africa has over 2000 indigenous languages but they are under-represented in NLP research due to lack of datasets. In recent years, there have been progress in developing labelled corpora for African languages. However, they are often available in a single domain and may not generalize to other domains. In this paper, we focus on the task of sentiment classification for cross-domain adaptation. We create a new dataset, NollySenti—based on the Nollywood movie reviews for five languages widely spoken in Nigeria (English, Hausa, Igbo, Nigerian-Pidgin, and Yorùbá). We provide an extensive empirical evaluation using classical machine learning methods and pre-trained language models. Leveraging transfer learning, we compare the performance of cross-domain adaptation from Twitter domain, and cross-lingual adaptation from English language. Our evaluation shows that transfer from English in the same target domain leads to more than 5% improvement in accuracy compared to transfer from Twitter in the same language. To further mitigate the domain difference, we leverage machine translation (MT) from English to other Nigerian languages, which leads to a further improvement of 7% over cross-lingual evaluation. While MT to low-resource languages are often of low quality, through human evaluation, we show that most of the translated sentences preserve the sentiment of the original English reviews.
more »
« less
- Award ID(s):
- 1704113
- PAR ID:
- 10470679
- Publisher / Repository:
- 61st Annual Meeting of the Association for Computational Linguistics (ACL’23)
- Date Published:
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Despite remarkable advancements in few-shot generalization in natural language processing, most models are developed and evaluated primarily in English. To establish a rigorous and equitable evaluation framework for few-shot cross-lingual transfer, we introduce a new benchmark, called BUFFET, which unifies 15 diverse tasks across 54 languages in a sequence-to-sequence format and provides a fixed set of few-shot examples and instructions. Using BUFFET, we perform thorough evaluations of ten state-of-the-art multilingual large language models with different transfer methods, namely in-context learning and fine-tuning. Our findings reveal significant room for improvement in few-shot in-context cross-lingual transfer. Strong multilingual pre-trained or instruction-tuned models such as BLOOM or ChatGPT often lag behind much smaller mT5-base models given the same number of few-shot samples, particularly in low-resource languages. Our analysis suggests avenues for future research in few-shot cross-lingual transfer.more » « less
-
Sentiment Analysis is a popular text classification task in natural language processing. It involves developing algorithms or machine learning models to determine the sentiment or opinion expressed in a piece of text. The results of this task can be used by business owners and product developers to understand their consumers’ perceptions of their products. Asides from customer feedback and product/service analysis, this task can be useful for social media monitoring (Martin et al., 2021). One of the popular applications of sentiment analysis is for classifying and detecting the positive and negative sentiments on movie reviews. Movie reviews enable movie producers to monitor the performances of their movies (Abhishek et al., 2020) and enhance the decision of movie viewers to know whether a movie is good enough and worth investing time to watch (Lakshmi Devi et al., 2020). However, the task has been under-explored for African languages compared to their western counterparts, ”high resource languages”, that are privileged to have received enormous attention due to the large amount of available textual data. African languages fall under the category of the low resource languages which are on the disadvantaged end because of the limited availability of data that gives them a poor representation (Nasim & Ghani, 2020). Recently, sentiment analysis has received attention on African languages in the Twitter domain for Nigerian (Muhammad et al., 2022) and Amharic (Yimam et al., 2020) languages. However, there is no available corpus in the movie domain. We decided to tackle the problem of unavailability of Yoru`ba´ data for movie sentiment analysis by creating the first Yoru`ba´ sentiment corpus for Nollywood movie reviews. Also, we develop sentiment classification models using state-of-the-art pre-trained language models like mBERT (Devlin et al., 2019) and AfriBERTa (Ogueji et al., 2021).more » « less
-
Communication tools such as email facilitate communication and collaboration between speakers of different languages, who use two primary strategies—English as a common language and machine translation (MT) tools—to help them overcome language barriers. However, each of these communication strategies creates its own challenges for cross-lingual communication. In this paper, we compare how people’s interpretations of an email sender’s social intention, and their evaluation of the email and the senders, differ when using a common language versus MT in email communication. We conducted an online experiment in which monolingual native English speakers read and rated request emails written by native English speakers, emails written by bilingual Chinese speakers in English, and emails written in Chinese then machine-translated into English. We found that participants interpreted the social intentions of the email sender less accurately for machine-translated emails than for emails written by non-native speakers in English. Participants also rated the senders and emails less positively overall for machine-translated emails compared to emails written by non-native speakers in English. Based on these findings, we suggest design possibilities that could better aid multilingual communication.more » « less
-
Language documentation encompasses translation, typically into the dominant high-resource language in the region where the target language is spoken. To make data accessible to a broader audience, additional translation into other high-resource languages might be needed. Working within a project documenting Kotiria, we explore the extent to which state-of-the-art machine translation (MT) systems can support this second translation – in our case from Portuguese to English. This translation task is challenging for multiple reasons: (1) the data is out-of-domain with respect to the MT system’s training data, (2) much of the data is conversational, (3) existing translations include non-standard and uncommon expressions, often reflecting properties of the documented language, and (4) the data includes borrowings from other regional languages. Despite these challenges, existing MT systems perform at a usable level, though there is still room for improvement. We then conduct a qualitative analysis and suggest ways to improve MT between high-resource languages in a language documentation setting.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- The DOI is not currently available.
