Design Challenges in Low-resource Cross-lingual Entity Linking

Abstract

Cross-lingual Entity Linking (XEL) grounds mentions of entities that appear in a foreign (source) language text into an English (target) knowledge base (KB) such as Wikipedia. XEL consists of two steps: candidate generation, which retrieves a list of candidate entities for each mention, followed by candidate ranking. XEL methods have been successful on high-resource languages, but generally perform poorly on low-resource languages due to lack of supervision.In this paper, we show a thorough analysis on existing low-resource XEL methods, especially on their candidate generation methods and limitations. We observed several interesting findings: 1. They are heavily limited by the Wikipedia bilingual resource coverage. 2. They perform better on Wikipedia text than on real-world text such as news or twitter. In this paper, we claim that, under the lowresource language setting, outside-Wikipedia cross-lingual resources are essential. To prove this argument, we propose a simple but effective zero-shot framework, CogCompXEL, that complements current methods by utilizing query log mapping files from online search engines. CogCompXEL outperforms current state-of-the-art models on almost all 25 languages of the LORELEI dataset, achieving an absolute average increase of 25% in gold candidate recall.

Semantic Orientation of Crosslingual Sentiments: Employment of Lexicon and Dictionaries

“…Natural Language Engineering proved to be the key source in the process of sentiment analysis and text normalization for formal as well as informal opinion bearing text [11], [12]. Beside the existence of formal and standard opinionative contents, the contemporary user collaboration contains colloquial as well as non-standard multilingual content, which poses a number of challenges in mining feelings and moods [13].…”

“…and PNV = TN (TN + FN ) (13) where PPV and PNV denotes Precision for Positive and Precision for Negative respectively. The lower precision indicates that high numbers of negatives tweets are labeled as positive while a higher precision means less number of negative tweets are incorrectly labeled as positive.…”

Untitled

“…Researchers have also explored tense classification in low-resource languages and cross-lingual scenarios [15]. Adapting machine learning models to languages with limited digital resources presents unique challenges related to data scarcity and linguistic diversity.…”

Low-resource Languages: A Review of Past Work and Future Challenges

“…(Zhou et al, 2020) replace the LSTM model by an n-gram bilingual model to solve the sub-optimal string modeling. Finally, (Fu et al, 2020) relies on log queries, morphological normalization, transliteration and projection as a comprehensive improvement over even supervised methods.…”