Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userA Statistical Extension of Byte-Pair Encoding
امتداد إحصائي لترميز بايت زوج
183
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
تجزئة الكلمات الفرعية هي حاليا أداة قياسية لتدريب أنظمة الترجمة الآلية العصبية (MT) ومهام NLP الأخرى. الهدف هو تقسيم الكلمات (في المصدر واللغات المستهدفة) إلى وحدات أصغر تشكل بعد ذلك المدخلات ومفردات نظام MT. الهدف من الحد من حجم المدخلات ومفردات الإخراج هو زيادة قدرات تعميم نموذج الترجمة، مما يتيح للنظام ترجمة وإنشاء كلمات نادرة وجديدة (غير مرئية) في وقت الاستدلال من خلال الجمع بين الوحدات الفرعية التي شوهدت سابقا. من الناحية المثالية، نتوقع أن تحتوي الوحدات التي تم إنشاؤها بعض المعنى اللغوي، بحيث يتم إنشاء الكلمات بطريقة ترفيهية. ومع ذلك، فإن أكثر طريقة تقسيم الكلمات الأكثر شعبية، ترميز بايت زوج (BPE)، والتي تنشأ من أدب ضغط البيانات، لا تشمل معايير صريحة لصالح الانقصام اللغوي أو للعثور على الحبيبية الفرعية الأمثل للكلمة الفرعية لبيانات التدريب المعطاة. في هذه الورقة، نقترح امتداد دوافع إحصائية خوارزمية BPE ومعيار التقارب الفعال الذي يتجنب دورة التجربة المكلفة اللازمة لتحديد أفضل حجم المفردات الفرعية. تظهر النتائج التجريبية مع اللغات الغنية المورفولوجية أن نموذجنا يحصل على درجات Bleu المثالية تقريبا وتنتج تجزئة كلمات أفضل مورفولوجية، مما يسمح بتوسيع نطاق تعميم BPE في ترجمة الجمل التي تحتوي على كلمات جديدة، كما هو موضح عبر التقييم البشري.
Sub-word segmentation is currently a standard tool for training neural machine translation (MT) systems and other NLP tasks. The goal is to split words (both in the source and target languages) into smaller units which then constitute the input and output vocabularies of the MT system. The aim of reducing the size of the input and output vocabularies is to increase the generalization capabilities of the translation model, enabling the system to translate and generate infrequent and new (unseen) words at inference time by combining previously seen sub-word units. Ideally, we would expect the created units to have some linguistic meaning, so that words are created in a compositional way. However, the most popular word-splitting method, Byte-Pair Encoding (BPE), which originates from the data compression literature, does not include explicit criteria to favor linguistic splittings nor to find the optimal sub-word granularity for the given training data. In this paper, we propose a statistically motivated extension of the BPE algorithm and an effective convergence criterion that avoids the costly experimentation cycle needed to select the best sub-word vocabulary size. Experimental results with morphologically rich languages show that our model achieves nearly-optimal BLEU scores and produces morphologically better word segmentations, which allows to outperform BPE's generalization in the translation of sentences containing new words, as shown via human evaluation.
References used
https://aclanthology.org/
rate research
Read More
Abstract The quality of a summarization evaluation metric is quantified by calculating the correlation between its scores and human annotations across a large number of summaries. Currently, it is unclear how precise these correlation estimates are,
nor whether differences between two metrics' correlations reflect a true difference or if it is due to mere chance. In this work, we address these two problems by proposing methods for calculating confidence intervals and running hypothesis tests for correlations using two resampling methods, bootstrapping and permutation. After evaluating which of the proposed methods is most appropriate for summarization through two simulation experiments, we analyze the results of applying these methods to several different automatic evaluation metrics across three sets of human annotations. We find that the confidence intervals are rather wide, demonstrating high uncertainty in the reliability of automatic metrics. Further, although many metrics fail to show statistical improvements over ROUGE, two recent works, QAEval and BERTScore, do so in some evaluation settings.1
The neural machine translation approach has gained popularity in machine translation because of its context analysing ability and its handling of long-term dependency issues. We have participated in the WMT21 shared task of similar language translati
on on a Tamil-Telugu pair with the team name: CNLP-NITS. In this task, we utilized monolingual data via pre-train word embeddings in transformer model based neural machine translation to tackle the limitation of parallel corpus. Our model has achieved a bilingual evaluation understudy (BLEU) score of 4.05, rank-based intuitive bilingual evaluation score (RIBES) score of 24.80 and translation edit rate (TER) score of 97.24 for both Tamil-to-Telugu and Telugu-to-Tamil translations respectively.
This paper presents a method for automatically identifying bilingual grammar patterns and extracting bilingual phrase instances from a given English-Chinese sentence pair. In our approach, the English-Chinese sentence pair is parsed to identify Engli
sh grammar patterns and Chinese counterparts. The method involves generating translations of each English grammar pattern and calculating translation probability of words from a word-aligned parallel corpora. The results allow us to extract the most probable English-Chinese phrase pairs in the sentence pair. We present a prototype system that applies the method to extract grammar patterns and phrases in parallel sentences. An evaluation on randomly selected examples from a dictionary shows that our approach has reasonably good performance. We use human judge to assess the bilingual phrases generated by our approach. The results have potential to assist language learning and machine translation research.
In this paper, we focus on identifying interactive argument pairs from two posts with opposite stances to a certain topic. Considering opinions are exchanged from different perspectives of the discussing topic, we study the discrete representations f
or arguments to capture varying aspects in argumentation languages (e.g., the debate focus and the participant behavior). Moreover, we utilize hierarchical structure to model post-wise information incorporating contextual knowledge. Experimental results on the large-scale dataset collected from CMV show that our proposed framework can significantly outperform the competitive baselines. Further analyses reveal why our model yields superior performance and prove the usefulness of our learned representations.
Although showing promising values to downstream applications, generating question and answer together is under-explored. In this paper, we introduce a novel task that targets question-answer pair generation from visual images. It requires not only ge
nerating diverse question-answer pairs but also keeping the consistency of them. We study different generation paradigms for this task and propose three models: the pipeline model, the joint model, and the sequential model. We integrate variational inference into these models to achieve diversity and consistency. We also propose region representation scaling and attention alignment to improve the consistency further. We finally devise an evaluator as a quantitative metric for consistency. We validate our approach on two benchmarks, VQA2.0 and Visual-7w, by automatically and manually evaluating diversity and consistency. Experimental results show the effectiveness of our models: they can generate diverse or consistent pairs. Moreover, this task can be used to improve visual question generation and visual question answering.
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
