Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userWine is not v i n. On the Compatibility of Tokenizations across Languages
النبيذ ليس v i n.على توافق التوصيلات عبر اللغات
309
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
حجم المفردات عبارة عن خيار تصميم مركزي في نماذج اللغة المحددة مسبقا كبيرة، فيما يتعلق بمتطلبات الأداء والذاكرة.عادة، يتم استخدام خوارزميات تكتيح الكلمات الفرعية مثل ترميز زوج البايت والصفحة.في هذا العمل، نحقق في توافق التوصيلات الخاصة بمساحات التضمين الثابتة والسياق متعددة اللغات واقتراح تدبير يعكس توافق التوصيلات عبر اللغات.هدفنا هو منع التوصيلات غير المتوافقة، على سبيل المثال، النبيذ "(مستوى الكلمات) باللغة الإنجليزية مقابل V. (مستوى الحرف) باللغة الفرنسية، مما يجعل من الصعب تعلم تمثيلات دلالية جيدة متعددة اللغات.نظهر أن تدبير التوافق لدينا يسمح بمصمم النظام بإنشاء مفدين عبر اللغات المتوافقة - Desideratum الذي تم إهماله حتى الآن في نماذج متعددة اللغات.
The size of the vocabulary is a central design choice in large pretrained language models, with respect to both performance and memory requirements. Typically, subword tokenization algorithms such as byte pair encoding and WordPiece are used. In this work, we investigate the compatibility of tokenizations for multilingual static and contextualized embedding spaces and propose a measure that reflects the compatibility of tokenizations across languages. Our goal is to prevent incompatible tokenizations, e.g., wine'' (word-level) in English vs. v i n'' (character-level) in French, which make it hard to learn good multilingual semantic representations. We show that our compatibility measure allows the system designer to create vocabularies across languages that are compatible -- a desideratum that so far has been neglected in multilingual models.
References used
https://aclanthology.org/
rate research
Read More
How would you explain Bill Gates to a German? He is associated with founding a company in the United States, so perhaps the German founder Carl Benz could stand in for Gates in those contexts. This type of translation is called adaptation in the tran
slation community. Until now, this task has not been done computationally. Automatic adaptation could be used in natural language processing for machine translation and indirectly for generating new question answering datasets and education. We propose two automatic methods and compare them to human results for this novel NLP task. First, a structured knowledge base adapts named entities using their shared properties. Second, vector-arithmetic and orthogonal embedding mappings methods identify better candidates, but at the expense of interpretable features. We evaluate our methods through a new dataset of human adaptations.
State-of-the-art multilingual systems rely on shared vocabularies that sufficiently cover all considered languages. To this end, a simple and frequently used approach makes use of subword vocabularies constructed jointly over several languages. We hy
pothesize that such vocabularies are suboptimal due to false positives (identical subwords with different meanings across languages) and false negatives (different subwords with similar meanings). To address these issues, we propose Subword Mapping and Anchoring across Languages (SMALA), a method to construct bilingual subword vocabularies. SMALA extracts subword alignments using an unsupervised state-of-the-art mapping technique and uses them to create cross-lingual anchors based on subword similarities. We demonstrate the benefits of SMALA for cross-lingual natural language inference (XNLI), where it improves zero-shot transfer to an unseen language without task-specific data, but only by sharing subword embeddings. Moreover, in neural machine translation, we show that joint subword vocabularies obtained with SMALA lead to higher BLEU scores on sentences that contain many false positives and false negatives.
Neural Machine Translation (NMT) models have been observed to produce poor translations when there are few/no parallel sentences to train the models. In the absence of parallel data, several approaches have turned to the use of images to learn transl
ations. Since images of words, e.g., horse may be unchanged across languages, translations can be identified via images associated with words in different languages that have a high degree of visual similarity. However, translating via images has been shown to improve upon text-only models only marginally. To better understand when images are useful for translation, we study image translatability of words, which we define as the translatability of words via images, by measuring intra- and inter-cluster similarities of image representations of words that are translations of each other. We find that images of words are not always invariant across languages, and that language pairs with shared culture, meaning having either a common language family, ethnicity or religion, have improved image translatability (i.e., have more similar images for similar words) compared to its converse, regardless of their geographic proximity. In addition, in line with previous works that show images help more in translating concrete words, we found that concrete words have improved image translatability compared to abstract ones.
Word embeddings are powerful representations that form the foundation of many natural language processing architectures, both in English and in other languages. To gain further insight into word embeddings, we explore their stability (e.g., overlap b
etween the nearest neighbors of a word in different embedding spaces) in diverse languages. We discuss linguistic properties that are related to stability, drawing out insights about correlations with affixing, language gender systems, and other features. This has implications for embedding use, particularly in research that uses them to study language trends.
Natural Language Processing (NLP) systems are at the heart of many critical automated decision-making systems making crucial recommendations about our future world. Gender bias in NLP has been well studied in English, but has been less studied in oth
er languages. In this paper, a team including speakers of 9 languages - Chinese, Spanish, English, Arabic, German, French, Farsi, Urdu, and Wolof - reports and analyzes measurements of gender bias in the Wikipedia corpora for these 9 languages. We develop extensions to profession-level and corpus-level gender bias metric calculations originally designed for English and apply them to 8 other languages, including languages that have grammatically gendered nouns including different feminine, masculine, and neuter profession words. We discuss future work that would benefit immensely from a computational linguistics perspective.
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
