paper-with-me

Papers

A Character-Word Compositional Neural Language Model for Finnish

2016-12-10 · Matti Lankinen, Hannes Heikinheimo, Pyry Takala, Tapani Raiko, Juha Karhunen

Inspired by recent research, we explore ways to model the highly morphological Finnish language at the level of characters while maintaining the performance of word-level models. We propose a new Character-to-Word-to-Character (C2W2C) compositional language model that uses characters as input and output while still internally processing word level embeddings. Our preliminary experiments, using the Finnish Europarl V7 corpus, indicate that C2W2C can respond well to the challenges of morphologically rich languages such as high out of vocabulary rates, the prediction of novel words, and growing vocabulary size. Notably, the model is able to correctly score inflectional forms that are not present in the training data and sample grammatically and semantically correct Finnish sentences character by character.

📄 PDF Abstract BibTeX arXiv:1612.03266

Code (1)

milankinen/c2w2c 공식 구현

Tasks

Language ModelingLanguage Modelling

Similar Papers 제목 키워드 기반

Tokenization Strategies for Low-Resource Agglutinative Languages in Word2Vec: Case Study on Turkish and Finnish

2025-08-27 · Jinfan Frank Hu arxiv

Tokenization plays a critical role in processing agglutinative languages, where a single word can encode multiple morphemes carrying syntactic and semantic information. This study evaluates the impact of various tokeniza…

Evaluating Morphological Compositional Generalization in Large Language Models

2024-10-16 · Mete Ismayilzada, Defne Circi, Jonne Sälevä, Hale Sirin 외

Large language models (LLMs) have demonstrated significant progress in various natural language generation and understanding tasks. However, their linguistic generalization capabilities remain questionable, raising doubt…

Text Generation

Understanding Pure Character-Based Neural Machine Translation: The Case of Translating Finnish into English

2020-11-06 · COLING 2020 8 · Gongbo Tang, Rico Sennrich, Joakim Nivre

Recent work has shown that deeper character-based neural machine translation (NMT) models can outperform subword-based models. However, it is still unclear what makes deeper character-based models successful. In this pap…

Machine TranslationNMTTranslation

Do Character-Level Neural Network Language Models Capture Knowledge of Multiword Expression Compositionality?

2018-08-01 · COLING 2018 8 · Ali Hakimi Parizi, Paul Cook

In this paper, we propose the first model for multiword expression (MWE) compositionality prediction based on character-level neural network language models. Experimental results on two kinds of MWEs (noun compounds and …

Machine TranslationPrediction

The Corpus of Finnish Sign Language

2020-05-01 · LREC 2020 5 · Juhana Salonen, Antti Kronqvist, Tommi Jantunen

This paper presents the Corpus of Finnish Sign Language (Corpus FinSL), a structured and annotated collection of Finnish Sign Language (FinSL) videos published in May 2019 in FIN-CLARIN{'}s Language Bank of Finland. The …