Zero-Shot Cross-Lingual Opinion Target Extraction

Proceedings of NAACL-HLT 2019, pages 2486–2495 Minneapolis, Minnesota, June 2 - June 7, 2019. c⃝2019 Association for Computational Linguistics 2486 Zero-Shot Cross-Lingual Opinion Target Extraction Soufian Jebbara and Philipp Cimiano Semalytix GmbH, Bielefeld, Germany Semantic Computing Group, CITEC - Bielefeld University, Bielefeld, Germany soufian.jebbara@semalytix.com cimiano@cit-ec.uni-bielefeld.de Abstract Aspect-based sentiment analysis involves the recognition of so called opinion target expres- sions (OTEs). To automatically extract OTEs, supervised learning algorithms are usually em- ployed which are trained on manually anno- tated corpora. The creation of these corpora is labor-intensive and sufficiently large datasets are therefore usually only available for a very narrow selection of languages and domains. In this work, we address the lack of avail- able annotated data for specific languages by proposing a zero-shot cross-lingual approach for the extraction of opinion target expres- sions. We leverage multilingual word embed- dings that share a common vector space across various languages and incorporate these into a convolutional neural network architecture for OTE extraction. Our experiments with 5 lan- guages give promising results: We can suc- cessfully train a model on annotated data of a source language and perform accurate predic- tion on a target language without ever using any annotated samples in that target language. Depending on the source and target language pairs, we reach performances in a zero-shot regime of up to 77% of a model trained on target language data. Furthermore, we can in- crease this performance up to 87% of a base- line model trained on target language data by performing cross-lingual learning from multi- ple source languages. 1 Introduction In recent years, there has been an increasing in- terest in developing sentiment analysis models that predict sentiment at a more fine-grained level than at the level of a complete document. paradigm coined as Aspect-based Sentiment Anal-A ysis (ABSA) addresses this need by defining the sentiment expressed in a text relative to an opinion target (also called aspect). Consider the following example from a restaurant review: “ Moules were excellent , lobster ravioli was VERY salty ! ” In this example, there are two sentiment state- ments, one positive and one negative. The posi- tive one is indicated by the word “excellent” and is expressed towards the opinion target “Moules”. The second, negative sentiment, is indicated by the word “salty” and is expressed towards the “lobster ravioli”. A key task within this fine-grained sentiment analysis consists of identifying so called opinion target expressions (OTE). To automatically extract OTEs, supervised learning algorithms are usually employed which are trained on manually anno- tated corpora. In this paper, we are concerned with how to transfer classifiers trained on one domain to another domain. In particular, we focus on the transfer of models across languages to alleviate the need for multilingual training data. We pro- pose a model that is capable of accurate zero-shot cross-lingual OTE extraction, thus reducing the re- liance on annotated data for every language. Simi- lar to Upadhyay et al. (2018), our model leverages multilingual word embeddings (Smith et al., …

Content truncated to 500 words