Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userRobust Open-Vocabulary Translation from Visual Text Representations
الترجمة المتفوعة المتفرعة قوية من تمثيلات نصية مرئية
238
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
تحتوي نماذج الترجمة الآلية على مفردات منفصلة واستخدام تقنيات تجزئة الكلمات الفرعية لتحقيق المفردات المفتوحة.يعتمد هذا النهج على تسلسل Unicode متسق وصحيح، ويجعل النماذج عرضة للتدهور من الأنواع المشتركة من الضوضاء والاختلاف.بدافع من متانة معالجة اللغات البشرية، نقترح استخدام تمثيلات نصية بصرية، والذي يتم الاستغناء عن مجموعة محدودة من Adgeddings النصية لصالح المفردات المستمرة التي تم إنشاؤها عن طريق معالجة النص المنصوص عليه بصريا مع Windows Sliding Windows.نظهر أن النماذج باستخدام نهج تمثيلات النص المرئي أو مطابقة أداء النماذج النصية التقليدية على مجموعات البيانات الصغيرة والأكبر.الأهم من ذلك، الأهم من ذلك، توضح النماذج ذات المدينات البصرية متانة كبيرة لأنواع الضوضاء المتنوعة، وتحقيق على سبيل المثال، 25.9 بلو على شخصية مسموعة باللغة الألمانية - المهمة الإنجليزية حيث تتحلل نماذج الكلمات الفرعية إلى 1.9.
Machine translation models have discrete vocabularies and commonly use subword segmentation techniques to achieve an open vocabulary.' This approach relies on consistent and correct underlying unicode sequences, and makes models susceptible to degradation from common types of noise and variation. Motivated by the robustness of human language processing, we propose the use of visual text representations, which dispense with a finite set of text embeddings in favor of continuous vocabularies created by processing visually rendered text with sliding windows. We show that models using visual text representations approach or match performance of traditional text models on small and larger datasets. More importantly, models with visual embeddings demonstrate significant robustness to varied types of noise, achieving e.g., 25.9 BLEU on a character permuted German--English task where subword models degrade to 1.9.
References used
https://aclanthology.org/
rate research
Read More
The success of large-scale contextual language models has attracted great interest in probing what is encoded in their representations. In this work, we consider a new question: to what extent contextual representations of concrete nouns are aligned
with corresponding visual representations? We design a probing model that evaluates how effective are text-only representations in distinguishing between matching and non-matching visual representations. Our findings show that language representations alone provide a strong signal for retrieving image patches from the correct object categories. Moreover, they are effective in retrieving specific instances of image patches; textual context plays an important role in this process. Visually grounded language models slightly outperform text-only language models in instance retrieval, but greatly under-perform humans. We hope our analyses inspire future research in understanding and improving the visual capabilities of language models.
Multilingual neural machine translation (MNMT) learns to translate multiple language pairs with a single model, potentially improving both the accuracy and the memory-efficiency of deployed models. However, the heavy data imbalance between languages
hinders the model from performing uniformly across language pairs. In this paper, we propose a new learning objective for MNMT based on distributionally robust optimization, which minimizes the worst-case expected loss over the set of language pairs. We further show how to practically optimize this objective for large translation corpora using an iterated best response scheme, which is both effective and incurs negligible additional computational cost compared to standard empirical risk minimization. We perform extensive experiments on three sets of languages from two datasets and show that our method consistently outperforms strong baseline methods in terms of average and per-language performance under both many-to-one and one-to-many translation settings.
Traditional translation systems trained on written documents perform well for text-based translation but not as well for speech-based applications. We aim to adapt translation models to speech by introducing actual lexical errors from ASR and segment
ation errors from automatic punctuation into our translation training data. We introduce an inverted projection approach that projects automatically detected system segments onto human transcripts and then re-segments the gold translations to align with the projected human transcripts. We demonstrate that this overcomes the train-test mismatch present in other training approaches. The new projection approach achieves gains of over 1 BLEU point over a baseline that is exposed to the human transcripts and segmentations, and these gains hold for both IWSLT data and YouTube data.
Neural encoders of biomedical names are typically considered robust if representations can be effectively exploited for various downstream NLP tasks. To achieve this, encoders need to model domain-specific biomedical semantics while rivaling the univ
ersal applicability of pretrained self-supervised representations. Previous work on robust representations has focused on learning low-level distinctions between names of fine-grained biomedical concepts. These fine-grained concepts can also be clustered together to reflect higher-level, more general semantic distinctions, such as grouping the names nettle sting and tick-borne fever together under the description puncture wound of skin. It has not yet been empirically confirmed that training biomedical name encoders on fine-grained distinctions automatically leads to bottom-up encoding of such higher-level semantics. In this paper, we show that this bottom-up effect exists, but that it is still relatively limited. As a solution, we propose a scalable multi-task training regime for biomedical name encoders which can also learn robust representations using only higher-level semantic classes. These representations can generalise both bottom-up as well as top-down among various semantic hierarchies. Moreover, we show how they can be used out-of-the-box for improved unsupervised detection of hypernyms, while retaining robust performance on various semantic relatedness benchmarks.
Abstract Dual encoders perform retrieval by encoding documents and queries into dense low-dimensional vectors, scoring each document by its inner product with the query. We investigate the capacity of this architecture relative to sparse bag-of-words
models and attentional neural networks. Using both theoretical and empirical analysis, we establish connections between the encoding dimension, the margin between gold and lower-ranked documents, and the document length, suggesting limitations in the capacity of fixed-length encodings to support precise retrieval of long documents. Building on these insights, we propose a simple neural model that combines the efficiency of dual encoders with some of the expressiveness of more costly attentional architectures, and explore sparse-dense hybrids to capitalize on the precision of sparse retrieval. These models outperform strong alternatives in large-scale retrieval.
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
