Isomorphic Transfer of Syntactic Structures in Cross-Lingual NLP
The transfer or share of knowledge between languages is a potential solution to resource scarcity in NLP. However, the effectiveness of cross-lingual transfer can be challenged by variation in syntactic structures. Frameworks such as Universal Dependencies (UD) are designed to be cross-lingually consistent, but even in carefully designed resources trees representing equivalent sentences may not always overlap. In this paper, we measure cross-lingual syntactic variation, or anisomorphism, in the UD treebank collection, considering both morphological and structural properties. We show that reducing the level of anisomorphism yields consistent gains in cross-lingual transfer tasks. We introduce a source language selection procedure that facilitates effective cross-lingual parser transfer, and propose a typologically driven method for syntactic tree processing which reduces anisomorphism. Our results show the effectiveness of this method for both machine translation and cross-lingual sentence similarity, demonstrating the importance of syntactic structure compatibility for boosting cross-lingual transfer in NLP.
Code (0)
등록된 구현이 없습니다.
Tasks
Cross-Lingual TransferMachine TranslationRepresentation LearningSentenceSentence SimilarityTransfer LearningTranslationSimilar Papers 제목 키워드 기반
Cross2StrA: Unpaired Cross-lingual Image Captioning with Cross-lingual Cross-modal Structure-pivoted Alignment
Unpaired cross-lingual image captioning has long suffered from irrelevancy and disfluency issues, due to the inconsistencies of the semantic scene and syntax attributes during transfer. In this work, we propose to addres…
Image CaptioningTranslationImproving Cross-Lingual Transfer for Event Argument Extraction with Language-Universal Sentence Structures
We study the problem of Cross-lingual Event Argument Extraction (CEAE). The task aims to predict argument roles of entity mentions for events in text, whose language is different from the language that a predictive model…
Cross-Lingual TransferEvent Argument ExtractionRepresentation LearningSemantic Similarity+2Assessing the Syntactic Capabilities of Transformer-based Multilingual Language Models
Multilingual Transformer-based language models, usually pretrained on more than 100 languages, have been shown to achieve outstanding results in a wide range of cross-lingual transfer tasks. However, it remains unknown w…
Cross-Lingual TransferLNMap: Departures from Isomorphic Assumption in Bilingual Lexicon Induction Through Non-Linear Mapping in Latent Space
Most of the successful and predominant methods for bilingual lexicon induction (BLI) are mapping-based, where a linear mapping function is learned with the assumption that the word embedding spaces of different languages…
Bilingual Lexicon InductionCross-Lingual Word EmbeddingsWord EmbeddingsCross-Linguistic Syntactic Difference in Multilingual BERT: How Good is It and How Does It Affect Transfer?
Multilingual BERT (mBERT) has demonstrated considerable cross-lingual syntactic ability, whereby it enables effective zero-shot cross-lingual transfer of syntactic knowledge. The transfer is more successful between some …
Cross-Lingual TransferDiversityZero-Shot Cross-Lingual Transfer