Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userDelexicalized Cross-lingual Dependency Parsing for Xibe
مخليل التبعية عبر اللغات غير المتبادلة ل Xibe
357
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
يتخلص يدويا على بنك Treebank هو تستغرق وقتا طويلا وكثيفة العمالة. نحن نقوم بإجراء تجارب تحليل التبعية عبر اللغات المتبادلة، حيث نربع المحلل المحلل على لغة واحدة واختبار لغتهم المستهدفة. كحالة الاختبار الخاصة بنا، نستخدم Xibe، لغة تجميل أقل من الموارد. نفترض أن اختيار لغة مرتبطة ارتباطا وثيقا لأن لغة المصدر ستوفر نتائج أفضل من الأقارب البعيدين. ومع ذلك، ليس من الواضح كيفية تحديد تلك اللغات ذات الصلة عن كثب. نحن نحقق في ثلاث طرق مختلفة: اختيار الأقرب من اللغة النموذجية، باستخدام Langrank، واختيار اللغة الأكثر مماثلة تعتمد على الحيرة. نقوم بتدريب نماذج تحليل اللغات المحددة باستخدام udify واختبار على أنواع مختلفة من بيانات Xibe. تظهر النتائج أن اللغات المختارة بناء على التصنيفات وعشرات الحيرة تتفوق على تلك المتوقعة من قبل Langrank؛ اليابانية هي لغة المصدر المثلى. عند تحديد لغة المصدر، فإن القرب من اللغة المستهدفة هو أكثر أهمية من أحجام التدريب الكبيرة. يتأثر التحليل أيضا بخلافات النوع، لكنها لها تأثير ضئيل طالما أن البيانات التدريبية على الأقل معقدة مثل الهدف.
Manually annotating a treebank is time-consuming and labor-intensive. We conduct delexicalized cross-lingual dependency parsing experiments, where we train the parser on one language and test on our target language. As our test case, we use Xibe, a severely under-resourced Tungusic language. We assume that choosing a closely related language as the source language will provide better results than more distant relatives. However, it is not clear how to determine those closely related languages. We investigate three different methods: choosing the typologically closest language, using LangRank, and choosing the most similar language based on perplexity. We train parsing models on the selected languages using UDify and test on different genres of Xibe data. The results show that languages selected based on typology and perplexity scores outperform those predicted by LangRank; Japanese is the optimal source language. In determining the source language, proximity to the target language is more important than large training sizes. Parsing is also influenced by genre differences, but they have little influence as long as the training data is at least as complex as the target.
References used
https://aclanthology.org/
rate research
Read More
Recent work has shown that monolingual masked language models learn to represent data-driven notions of language variation which can be used for domain-targeted training data selection. Dataset genre labels are already frequently available, yet remai
n largely unexplored in cross-lingual setups. We harness this genre metadata as a weak supervision signal for targeted data selection in zero-shot dependency parsing. Specifically, we project treebank-level genre information to the finer-grained sentence level, with the goal to amplify information implicitly stored in unsupervised contextualized representations. We demonstrate that genre is recoverable from multilingual contextual embeddings and that it provides an effective signal for training data selection in cross-lingual, zero-shot scenarios. For 12 low-resource language treebanks, six of which are test-only, our genre-specific methods significantly outperform competitive baselines as well as recent embedding-based methods for data selection. Moreover, genre-based data selection provides new state-of-the-art results for three of these target languages.
Generative adversarial networks (GANs) have succeeded in inducing cross-lingual word embeddings - maps of matching words across languages - without supervision. Despite these successes, GANs' performance for the difficult case of distant languages is
still not satisfactory. These limitations have been explained by GANs' incorrect assumption that source and target embedding spaces are related by a single linear mapping and are approximately isomorphic. We assume instead that, especially across distant languages, the mapping is only piece-wise linear, and propose a multi-adversarial learning method. This novel method induces the seed cross-lingual dictionary through multiple mappings, each induced to fit the mapping for one subspace. Our experiments on unsupervised bilingual lexicon induction and cross-lingual document classification show that this method improves performance over previous single-mapping methods, especially for distant languages.
Multilingual and cross-lingual Semantic Role Labeling (SRL) have recently garnered increasing attention as multilingual text representation techniques have become more effective and widely available. While recent work has attained growing success, re
sults on gold multilingual benchmarks are still not easily comparable across languages, making it difficult to grasp where we stand. For example, in CoNLL-2009, the standard benchmark for multilingual SRL, language-to-language comparisons are affected by the fact that each language has its own dataset which differs from the others in size, domains, sets of labels and annotation guidelines. In this paper, we address this issue and propose UniteD-SRL, a new benchmark for multilingual and cross-lingual, span- and dependency-based SRL. UniteD-SRL provides expert-curated parallel annotations using a common predicate-argument structure inventory, allowing direct comparisons across languages and encouraging studies on cross-lingual transfer in SRL. We release UniteD-SRL v1.0 at https://github.com/SapienzaNLP/united-srl.
In cross-lingual Abstract Meaning Representation (AMR) parsing, researchers develop models that project sentences from various languages onto their AMRs to capture their essential semantic structures: given a sentence in any language, we aim to captu
re its core semantic content through concepts connected by manifold types of semantic relations. Methods typically leverage large silver training data to learn a single model that is able to project non-English sentences to AMRs. However, we find that a simple baseline tends to be overlooked: translating the sentences to English and projecting their AMR with a monolingual AMR parser (translate+parse,T+P). In this paper, we revisit this simple two-step base-line, and enhance it with a strong NMT system and a strong AMR parser. Our experiments show that T+P outperforms a recent state-of-the-art system across all tested languages: German, Italian, Spanish and Mandarin with +14.6, +12.6, +14.3 and +16.0 Smatch points
We propose the Recursive Non-autoregressive Graph-to-Graph Transformer architecture (RNGTr) for the iterative refinement of arbitrary graphs through the recursive application of a non-autoregressive Graph-to-Graph Transformer and apply it to syntacti
c dependency parsing. We demonstrate the power and effectiveness of RNGTr on several dependency corpora, using a refinement model pre-trained with BERT. We also introduce Syntactic Transformer (SynTr), a non-recursive parser similar to our refinement model. RNGTr can improve the accuracy of a variety of initial parsers on 13 languages from the Universal Dependencies Treebanks, English and Chinese Penn Treebanks, and the German CoNLL2009 corpus, even improving over the new state-of-the-art results achieved by SynTr, significantly improving the state-of-the-art for all corpora tested.
suggested questions
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
