Average Is Not Enough: Caveats of Multilingual Evaluation

• URL: http://arxiv.org/abs/2301.01269v1
• Date: Tue, 3 Jan 2023 18:23:42 GMT
• Title: Average Is Not Enough: Caveats of Multilingual Evaluation
• Authors: Mat\'u\v{s} Pikuliak and Mari\'an \v{S}imko
• Abstract summary: We argue that a qualitative analysis informed by comparative linguistics is needed for multilingual results to detect this kind of bias. We show in our case study that results in published works can indeed be linguistically biased and we demonstrate that visualization based on onEL typological database can detect it.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: This position paper discusses the problem of multilingual evaluation. Using simple statistics, such as average language performance, might inject linguistic biases in favor of dominant language families into evaluation methodology. We argue that a qualitative analysis informed by comparative linguistics is needed for multilingual results to detect this kind of bias. We show in our case study that results in published works can indeed be linguistically biased and we demonstrate that visualization based on URIEL typological database can detect it.

Related papers

• Quantifying the Dialect Gap and its Correlates Across Languages [69.18461982439031]
  This work will lay the foundation for furthering the field of dialectal NLP by laying out evident disparities and identifying possible pathways for addressing them through mindful data collection.
  arXiv  Detail & Related papers  (2023-10-23T17:42:01Z)
• On Evaluating and Mitigating Gender Biases in Multilingual Settings [5.248564173595024]
  We investigate some of the challenges with evaluating and mitigating biases in multilingual settings. We first create a benchmark for evaluating gender biases in pre-trained masked language models. We extend various debiasing methods to work beyond English and evaluate their effectiveness for SOTA massively multilingual models.
  arXiv  Detail & Related papers  (2023-07-04T06:23:04Z)
• Multilingual Few-Shot Learning via Language Model Retrieval [18.465566186549072]
  Transformer-based language models have achieved remarkable success in few-shot in-context learning. We conduct a study of retrieving semantically similar few-shot samples and using them as the context. We evaluate the proposed method on five natural language understanding datasets related to intent detection, question classification, sentiment analysis, and topic classification.
  arXiv  Detail & Related papers  (2023-06-19T14:27:21Z)
• Comparing Biases and the Impact of Multilingual Training across Multiple Languages [70.84047257764405]
  We present a bias analysis across Italian, Chinese, English, Hebrew, and Spanish on the downstream sentiment analysis task. We adapt existing sentiment bias templates in English to Italian, Chinese, Hebrew, and Spanish for four attributes: race, religion, nationality, and gender. Our results reveal similarities in bias expression such as favoritism of groups that are dominant in each language's culture.
  arXiv  Detail & Related papers  (2023-05-18T18:15:07Z)
• An Analysis of Social Biases Present in BERT Variants Across Multiple Languages [0.0]
  We investigate the bias present in monolingual BERT models across a diverse set of languages. We propose a template-based method to measure any kind of bias, based on sentence pseudo-likelihood. We conclude that current methods of probing for bias are highly language-dependent.
  arXiv  Detail & Related papers  (2022-11-25T23:38:08Z)
• Easy Adaptation to Mitigate Gender Bias in Multilingual Text Classification [8.137681060429527]
  We treat the gender as domains and present a standard domain adaptation model to reduce the gender bias. We evaluate our approach on two text classification tasks, hate speech detection and rating prediction, and demonstrate the effectiveness of our approach.
  arXiv  Detail & Related papers  (2022-04-12T01:15:36Z)
• Exploring Language Patterns in a Medical Licensure Exam Item Bank [0.25782420501870296]
  This study is the first attempt using machine learning (ML) and NLP to explore language bias on a large item bank. Using a prediction algorithm trained on clusters of similar item stems, we demonstrate that our approach can be used to review large item banks for potential biased language.
  arXiv  Detail & Related papers  (2021-11-20T02:45:35Z)
• Curious Case of Language Generation Evaluation Metrics: A Cautionary Tale [52.663117551150954]
  A few popular metrics remain as the de facto metrics to evaluate tasks such as image captioning and machine translation. This is partly due to ease of use, and partly because researchers expect to see them and know how to interpret them. In this paper, we urge the community for more careful consideration of how they automatically evaluate their models.
  arXiv  Detail & Related papers  (2020-10-26T13:57:20Z)
• Gender Bias in Multilingual Embeddings and Cross-Lingual Transfer [101.58431011820755]
  We study gender bias in multilingual embeddings and how it affects transfer learning for NLP applications. We create a multilingual dataset for bias analysis and propose several ways for quantifying bias in multilingual representations.
  arXiv  Detail & Related papers  (2020-05-02T04:34:37Z)
• Bridging Linguistic Typology and Multilingual Machine Translation with Multi-View Language Representations [83.27475281544868]
  We use singular vector canonical correlation analysis to study what kind of information is induced from each source. We observe that our representations embed typology and strengthen correlations with language relationships. We then take advantage of our multi-view language vector space for multilingual machine translation, where we achieve competitive overall translation accuracy.
  arXiv  Detail & Related papers  (2020-04-30T16:25:39Z)
• On the Language Neutrality of Pre-trained Multilingual Representations [70.93503607755055]
  We investigate the language-neutrality of multilingual contextual embeddings directly and with respect to lexical semantics. Our results show that contextual embeddings are more language-neutral and, in general, more informative than aligned static word-type embeddings. We show how to reach state-of-the-art accuracy on language identification and match the performance of statistical methods for word alignment of parallel sentences.
  arXiv  Detail & Related papers  (2020-04-09T19:50:32Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.