paper-with-me

Papers

Subword-Level Language Identification for Intra-Word Code-Switching

2019-04-03 · NAACL 2019 6 · Manuel Mager, Özlem Çetinoğlu, Katharina Kann

Language identification for code-switching (CS), the phenomenon of alternating between two or more languages in conversations, has traditionally been approached under the assumption of a single language per token. However, if at least one language is morphologically rich, a large number of words can be composed of morphemes from more than one language (intra-word CS). In this paper, we extend the language identification task to the subword-level, such that it includes splitting mixed words while tagging each part with a language ID. We further propose a model for this task, which is based on a segmental recurrent neural network. In experiments on a new Spanish--Wixarika dataset and on an adapted German--Turkish dataset, our proposed model performs slightly better than or roughly on par with our best baseline, respectively. Considering only mixed words, however, it strongly outperforms all baselines.

📄 PDF Abstract BibTeX arXiv:1904.01989

Code (0)

등록된 구현이 없습니다.

Tasks

Language Identification

Similar Papers 제목 키워드 기반

Transliteration for Low-Resource Code-Switching Texts: Building an Automatic Cyrillic-to-Latin Converter for Tatar

2021-06-01 · NAACL (CALCS) 2021 6 · Chihiro Taguchi, Yusuke Sakai, Taro Watanabe

We introduce a Cyrillic-to-Latin transliterator for the Tatar language based on subword-level language identification. The transliteration is a challenging task due to the following two reasons. First, because modern Tat…

Language IdentificationTransliteration

Word-level Language Identification Using Subword Embeddings for Code-mixed Bangla-English Social Media Data

2022-06-01 · DCLRL (LREC) 2022 6 · Aparna Dutta

This paper reports work on building a word-level language identification (LID) model for code-mixed Bangla-English social media data using subword embeddings, with an ultimate goal of using this LID module as the first s…

Language IdentificationPOS

Universal Dependencies Treebank for Tatar: Incorporating Intra-Word Code-Switching Information

2022-06-01 · EURALI (LREC) 2022 6 · Chihiro Taguchi, Sei Iwata, Taro Watanabe

This paper introduces a new Universal Dependencies treebank for the Tatar language named NMCTT. A significant feature of the corpus is that it includes code-switching (CS) information at a morpheme level, given the fact …

Language IdentificationPOSTAG

Stem-driven Language Models for Morphologically Rich Languages

2019-10-25 · Yash Shah, Ishan Tarunesh, Harsh Deshpande, Preethi Jyothi

Neural language models (LMs) have shown to benefit significantly from enhancing word vectors with subword-level information, especially for morphologically rich languages. This has been mainly tackled by providing subwor…

Multi-Task Learning

Learning Mutually Informed Representations for Characters and Subwords

2023-11-14 · Yilin Wang, Xinyi Hu, Matthew R. Gormley

Most pretrained language models rely on subword tokenization, which processes text as a sequence of subword tokens. However, different granularities of text, such as characters, subwords, and words, can contain different…

named-entity-recognitionNamed Entity RecognitionPOSPOS Tagging+2