Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userTranslating Headers of Tabular Data: A Pilot Study of Schema Translation
ترجمة رؤوس البيانات الجدولة: دراسة تجريبية للترجمة المخطط
133
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
ترجمة المخطط هي مهمة ترجمة رؤوس البيانات الجدولية تلقائيا من لغة إلى أخرى. تلعب ترجمة المخطط عالية الجودة دورا مهما في البحث عبر الجدول عبر اللغات والتفاهم والتحليل. على الرغم من أهميتها، فإن ترجمة المخطط ليست مدروسة بشكل جيد في المجتمع، ولا يمكن أن تعمل نماذج الترجمة الآلية العصبية في هذه المهمة بشكل جيد في هذه المهمة بسبب اختلافات جوهرتين بين النص العادي والبيانات الجدولة: الفرق المورفولوجي وفرق السياق. لتسهيل الدراسة البحثية، نبني أول مجموعة بيانات متوازية للترجمة المخطط، والتي تتكون من 3،158 طاولة مع 11،979 رئيس مكتوبة في 6 لغات مختلفة، بما في ذلك الإنجليزية والصينية والفرنسية والألمانية والإسبانية واليابانية. أيضا، نقترح نموذج الترجمة المخطط الأول يسمى EAST، وهو نموذج الترجمة العصبي للرأس المعزز مع سياق المخطط. على وجه التحديد، نقوم بالنماذج رأسا مستهدف وسياقه كشركة بيانية موجهة لتمثيل أنواع كيانها وعلاقاتها. ثم يلقي يرميز الرسم البياني مع محول علمي عليري ويستخدم محول آخر لفك تشفير رأس اللغة الهدف. توضح التجارب في مجموعة بياناتنا التي توضح بشكل كبير من نماذج الترجمة الآلية العصبية لحالة الأحوال العصبية. سيتم إصدار DataSet لدينا في https://github.com/microsoft/contextualsp.
Schema translation is the task of automatically translating headers of tabular data from one language to another. High-quality schema translation plays an important role in cross-lingual table searching, understanding and analysis. Despite its importance, schema translation is not well studied in the community, and state-of-the-art neural machine translation models cannot work well on this task because of two intrinsic differences between plain text and tabular data: morphological difference and context difference. To facilitate the research study, we construct the first parallel dataset for schema translation, which consists of 3,158 tables with 11,979 headers written in 6 different languages, including English, Chinese, French, German, Spanish, and Japanese. Also, we propose the first schema translation model called CAST, which is a header-to-header neural machine translation model augmented with schema context. Specifically, we model a target header and its context as a directed graph to represent their entity types and relations. Then CAST encodes the graph with a relational-aware transformer and uses another transformer to decode the header in the target language. Experiments on our dataset demonstrate that CAST significantly outperforms state-of-the-art neural machine translation models. Our dataset will be released at https://github.com/microsoft/ContextualSP.
References used
https://aclanthology.org/
rate research
Read More
Existing work on tabular representation-learning jointly models tables and associated text using self-supervised objective functions derived from pretrained language models such as BERT. While this joint pretraining improves tasks involving paired ta
bles and text (e.g., answering questions about tables), we show that it underperforms on tasks that operate over tables without any associated text (e.g., populating missing cells). We devise a simple pretraining objective (corrupt cell detection) that learns exclusively from tabular data and reaches the state-of-the-art on a suite of table-based prediction tasks. Unlike competing approaches, our model (TABBIE) provides embeddings of all table substructures (cells, rows, and columns), and it also requires far less compute to train. A qualitative analysis of our model's learned cell, column, and row representations shows that it understands complex table semantics and numerical trends.
Data augmentation, which refers to manipulating the inputs (e.g., adding random noise,masking specific parts) to enlarge the dataset,has been widely adopted in machine learning. Most data augmentation techniques operate on a single input, which limit
s the diversity of the training corpus. In this paper, we propose a simple yet effective data augmentation technique for neural machine translation, mixSeq, which operates on multiple inputs and their corresponding targets. Specifically, we randomly select two input sequences,concatenate them together as a longer input aswell as their corresponding target sequencesas an enlarged target, and train models on theaugmented dataset. Experiments on nine machine translation tasks demonstrate that such asimple method boosts the baselines by a non-trivial margin. Our method can be further combined with single input based data augmentation methods to obtain further improvements.
We propose a data augmentation method for neural machine translation. It works by interpreting language models and phrasal alignment causally. Specifically, it creates augmented parallel translation corpora by generating (path-specific) counterfactua
l aligned phrases. We generate these by sampling new source phrases from a masked language model, then sampling an aligned counterfactual target phrase by noting that a translation language model can be interpreted as a Gumbel-Max Structural Causal Model (Oberst and Sontag, 2019). Compared to previous work, our method takes both context and alignment into account to maintain the symmetry between source and target sequences. Experiments on IWSLT'15 English → Vietnamese, WMT'17 English → German, WMT'18 English → Turkish, and WMT'19 robust English → French show that the method can improve the performance of translation, backtranslation and translation robustness.
Sign language translation (SLT) is often decomposed into video-to-gloss recognition and gloss to-text translation, where a gloss is a sequence of transcribed spoken-language words in the order in which they are signed. We focus here on gloss-to-text
translation, which we treat as a low-resource neural machine translation (NMT) problem. However, unlike traditional low resource NMT, gloss-to-text translation differs because gloss-text pairs often have a higher lexical overlap and lower syntactic overlap than pairs of spoken languages. We exploit this lexical overlap and handle syntactic divergence by proposing two rule-based heuristics that generate pseudo-parallel gloss-text pairs from monolingual spoken language text. By pre-training on this synthetic data, we improve translation from American Sign Language (ASL) to English and German Sign Language (DGS) to German by up to 3.14 and 2.20 BLEU, respectively.
In this paper, we investigate the driving factors behind concatenation, a simple but effective data augmentation method for low-resource neural machine translation. Our experiments suggest that discourse context is unlikely the cause for concatenatio
n improving BLEU by about +1 across four language pairs. Instead, we demonstrate that the improvement comes from three other factors unrelated to discourse: context diversity, length diversity, and (to a lesser extent) position shifting.
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
