CL-XABSA: Contrastive Learning for Cross-lingual Aspect-based Sentiment Analysis

04/02/2022
by   Nankai Lin, et al.
0

As an extensive research in the field of Natural language processing (NLP), aspect-based sentiment analysis (ABSA) is the task of predicting the sentiment expressed in a text relative to the corresponding aspect. Unfortunately, most languages lack of sufficient annotation resources, thus more and more recent researchers focus on cross-lingual aspect-based sentiment analysis (XABSA). However, most recent researches only concentrate on cross-lingual data alignment instead of model alignment. To this end, we propose a novel framework, CL-XABSA: Contrastive Learning for Cross-lingual Aspect-Based Sentiment Analysis. Specifically, we design two contrastive strategies, token level contrastive learning of token embeddings (TL-CTE) and sentiment level contrastive learning of token embeddings (SL-CTE), to regularize the semantic space of source and target language to be more uniform. Since our framework can receive datasets in multiple languages during training, our framework can be adapted not only for XABSA task, but also for multilingual aspect-based sentiment analysis (MABSA). To further improve the performance of our model, we perform knowledge distillation technology leveraging data from unlabeled target language. In the distillation XABSA task, we further explore the comparative effectiveness of different data (source dataset, translated dataset, and code-switched dataset). The results demonstrate that the proposed method has a certain improvement in the three tasks of XABSA, distillation XABSA and MABSA. For reproducibility, our code for this paper is available at https://github.com/GKLMIP/CL-XABSA.

READ FULL TEXT
research
03/22/2018

MultiBooked: A Corpus of Basque and Catalan Hotel Reviews Annotated for Aspect-level Sentiment Classification

While sentiment analysis has become an established field in the NLP comm...
research
09/06/2023

A deep Natural Language Inference predictor without language-specific training data

In this paper we present a technique of NLP to tackle the problem of inf...
research
06/24/2019

Embedding Projection for Targeted Cross-Lingual Sentiment: Model Comparisons and a Real-World Study

Sentiment analysis benefits from large, hand-annotated resources in orde...
research
01/26/2021

Analyzing Zero-shot Cross-lingual Transfer in Supervised NLP Tasks

In zero-shot cross-lingual transfer, a supervised NLP task trained on a ...
research
10/04/2019

Contrastive Language Adaptation for Cross-Lingual Stance Detection

We study cross-lingual stance detection, which aims to leverage labeled ...
research
05/22/2023

Towards Unsupervised Recognition of Semantic Differences in Related Documents

Automatically highlighting words that cause semantic differences between...
research
06/06/2022

Discriminative Models Can Still Outperform Generative Models in Aspect Based Sentiment Analysis

Aspect-based Sentiment Analysis (ABSA) helps to explain customers' opini...

Please sign up or login with your details

Forgot password? Click here to reset