CMNEROne at SemEval-2022 Task 11: Code-Mixed Named Entity Recognition by leveraging multilingual data

Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022), pages 1556 - 1561 July 14-15, 2022 ©2022 Association for Computational Linguistics CMNEROne at SemEval-2022 Task 11: Code-Mixed Named Entity Recognition by leveraging multilingual data Suman Dowlagar LTRC IIIT-Hyderabad suman.dowlagar @research.iiit.ac.in Radhika Mamidi LTRC IIIT-Hyderabad radhika.mamidi @iiit.ac.in Abstract Identifying named entities is, in general, a prac- tical and challenging task in the field of Natural Language Processing. Named Entity Recog- nition on the code-mixed text is further chal- lenging due to the linguistic complexity re- sulting from the nature of the mixing. This paper addresses the submission of team CM- NEROne to the SEMEVAL 2022 shared task 11 MultiCoNER. The Code-mixed NER task aimed to identify named entities on the code- mixed dataset. Our work consists of Named Entity Recognition (NER) on the code-mixed dataset by leveraging the multilingual data. We achieved a weighted average F1 score of 0.7044, i.e., 6% greater than the baseline. 1 Introduction Named entity recognition (NER) is a fundamen- tal task in NLP. It aims to identify and classify entities in a text into predefined types. It is an essential tool for information retrieval, question answering, (Banerjee et al., 2019) and text summa- rization tasks (Patil et al., 2016; Li et al., 2020). However, except for some resource-rich monolin- gual languages, NER annotated data for most other languages are still very limited (Kruengkrai et al., 2020). Moreover, it is usually time-consuming to annotate such data, particularly for low-resource languages such as multilingual and code-mixed (Liu et al., 2021). Therefore, transfer learning and leveraging the other datasets for multilingual and code-mixed NER has attracted growing interest re- cently, especially with the influx of deep learning methods. This paper presents the system description for named entity recognition on the code-mixed dataset. Code-mixing is defined as using two or more languages in a single sentence or utterance (Dowlagar and Mamidi, 2021). The use of code- mixed language is prevalent in most multilingual societies. Due to linguistic complexity arising Sentence hameM this magic moment Languge Hi En En En NER tags O B-CW I-CW I-CW Table 1: An example of the code-mixed NER annotated sentence. The Hindi words are converted from utf to wx format and are italicized from mixing two languages, the processing of code- mixed sentences is a challenging task (Bali et al., 2014). So, the models that are trained on mono- lingual and multilingual datasets typically fail to handle code-mixed inputs (Khanuja et al., 2020). Therefore, to encourage research on code-mixing, the speech and NLP communities are organizing several shared tasks. The shared tasks have con- centrated on language identification, POS-tagging, sentiment analysis, hate speech detection, and sev- eral datasets exist for these as well. Similarly, SE- MEVAL 2022’s Task 11 sub-task 13 was devoted to identifying named entities in code-mixed lan- guages (Malmasi et al., 2022b). This task aims to classify the given tokens in the code-mixed sen- tences as persons, corporation, location, and others. An example is shown in Table 1. The lack of …

Content truncated to 500 words