Few-shot Cross-lingual Aspect-Based Sentiment Analysis with Sequence-to-Sequence Models

• URL: http://arxiv.org/abs/2508.07866v1
• Date: Mon, 11 Aug 2025 11:31:37 GMT
• Title: Few-shot Cross-lingual Aspect-Based Sentiment Analysis with Sequence-to-Sequence Models
• Authors: Jakub Šmíd, Pavel Přibáň, Pavel Král,
• Abstract summary: We evaluate the effect of adding few-shot target language examples to the training set across four ABSA tasks, six target languages, and two sequence-to-sequence models.<n>We demonstrate that combining 1,000 target language examples with English data can even surpass monolingual baselines.
• Score: 0.8602553195689511
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Aspect-based sentiment analysis (ABSA) has received substantial attention in English, yet challenges remain for low-resource languages due to the scarcity of labelled data. Current cross-lingual ABSA approaches often rely on external translation tools and overlook the potential benefits of incorporating a small number of target language examples into training. In this paper, we evaluate the effect of adding few-shot target language examples to the training set across four ABSA tasks, six target languages, and two sequence-to-sequence models. We show that adding as few as ten target language examples significantly improves performance over zero-shot settings and achieves a similar effect to constrained decoding in reducing prediction errors. Furthermore, we demonstrate that combining 1,000 target language examples with English data can even surpass monolingual baselines. These findings offer practical insights for improving cross-lingual ABSA in low-resource and domain-specific settings, as obtaining ten high-quality annotated examples is both feasible and highly effective.

Related papers

• Improving Generative Cross-lingual Aspect-Based Sentiment Analysis with Constrained Decoding [0.8602553195689511]
  This paper introduces a novel approach using constrained decoding with sequence-to-sequence models.<n>It improves cross-lingual performance by 5% on average for the most complex task.<n>We evaluate our approach across seven languages and six ABSA tasks.
  arXiv  Detail & Related papers  (2025-08-14T06:07:53Z)
• LACA: Improving Cross-lingual Aspect-Based Sentiment Analysis with LLM Data Augmentation [0.8602553195689511]
  Cross-lingual aspect-based sentiment analysis involves detailed sentiment analysis in a target language.<n>Most existing methods depend heavily on often unreliable translation tools to bridge the language gap.<n>We propose a new approach that leverages a large language model to generate high-quality pseudo-labelled data in the target language.
  arXiv  Detail & Related papers  (2025-08-13T05:55:48Z)
• Cross-Lingual Pitfalls: Automatic Probing Cross-Lingual Weakness of Multilingual Large Language Models [55.14276067678253]
  This paper introduces a novel methodology for efficiently identifying inherent cross-lingual weaknesses in Large Language Models (LLMs)<n>We construct a new dataset of over 6,000 bilingual pairs across 16 languages using this methodology, demonstrating its effectiveness in revealing weaknesses even in state-of-the-art models.<n>Further experiments investigate the relationship between linguistic similarity and cross-lingual weaknesses, revealing that linguistically related languages share similar performance patterns.
  arXiv  Detail & Related papers  (2025-05-24T12:31:27Z)
• Enhancing Multilingual ASR for Unseen Languages via Language Embedding Modeling [50.62091603179394]
  Whisper, one of the most advanced ASR models, handles 99 languages effectively.<n>However, Whisper struggles with unseen languages, those not included in its pre-training.<n>We propose methods that exploit these relationships to enhance ASR performance on unseen languages.
  arXiv  Detail & Related papers  (2024-12-21T04:05:43Z)
• Evaluating Zero-Shot Multilingual Aspect-Based Sentiment Analysis with Large Language Models [0.9832963381777073]
  We evaluate large language models (LLMs) under zero-shot conditions to explore their potential to tackle ABSA task.<n>We investigate various prompting strategies, including vanilla zero-shot, chain-of-thought (CoT), self-improvement, self-debate, and self-consistency.<n>Results indicate that while LLMs show promise in handling multilingual ABSA, they generally fall short of fine-tuned, task-specific models.
  arXiv  Detail & Related papers  (2024-12-17T05:48:48Z)
• Towards Quantifying and Reducing Language Mismatch Effects in Cross-Lingual Speech Anti-Spoofing [21.214330523348046]
  Existing anti-spoofing datasets are mainly in English. High cost of acquiring multilingual datasets hinders training language-independent models. We propose an innovative approach - Accent-based data expansion via TTS (ACCENT)
  arXiv  Detail & Related papers  (2024-09-12T18:18:22Z)
• Unlikelihood Tuning on Negative Samples Amazingly Improves Zero-Shot Translation [79.96416609433724]
  Zero-shot translation (ZST) aims to translate between unseen language pairs in training data. The common practice to guide the zero-shot language mapping during inference is to deliberately insert the source and target language IDs. Recent studies have shown that language IDs sometimes fail to navigate the ZST task, making them suffer from the off-target problem.
  arXiv  Detail & Related papers  (2023-09-28T17:02:36Z)
• Few-Shot Cross-lingual Transfer for Coarse-grained De-identification of Code-Mixed Clinical Texts [56.72488923420374]
  Pre-trained language models (LMs) have shown great potential for cross-lingual transfer in low-resource settings. We show the few-shot cross-lingual transfer property of LMs for named recognition (NER) and apply it to solve a low-resource and real-world challenge of code-mixed (Spanish-Catalan) clinical notes de-identification in the stroke.
  arXiv  Detail & Related papers  (2022-04-10T21:46:52Z)
• Language Models are Few-shot Multilingual Learners [66.11011385895195]
  We evaluate the multilingual skills of the GPT and T5 models in conducting multi-class classification on non-English languages. We show that, given a few English examples as context, pre-trained language models can predict not only English test samples but also non-English ones.
  arXiv  Detail & Related papers  (2021-09-16T03:08:22Z)
• Few-Shot Cross-Lingual Stance Detection with Sentiment-Based Pre-Training [32.800766653254634]
  We present the most comprehensive study of cross-lingual stance detection to date. We use 15 diverse datasets in 12 languages from 6 language families. For our experiments, we build on pattern-exploiting training, proposing the addition of a novel label encoder.
  arXiv  Detail & Related papers  (2021-09-13T15:20:06Z)
• AM2iCo: Evaluating Word Meaning in Context across Low-ResourceLanguages with Adversarial Examples [51.048234591165155]
  We present AM2iCo, Adversarial and Multilingual Meaning in Context. It aims to faithfully assess the ability of state-of-the-art (SotA) representation models to understand the identity of word meaning in cross-lingual contexts. Results reveal that current SotA pretrained encoders substantially lag behind human performance.
  arXiv  Detail & Related papers  (2021-04-17T20:23:45Z)

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.