Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userSequence-to-Sequence Lexical Normalization with Multilingual Transformers
تطبيع تسلسل إلى تسلسل مع محولات متعددة اللغات
354
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
تحتوي المهام القياسية الحالية لمعالجة اللغة الطبيعية على نص مختلف عن النص المستخدم في اليومي غير الرسمي إلى الاتصال الرقمي اليومي. أدى هذا التناقض إلى تدهور الأداء الشديد لنماذج NLP الحديثة عندما يتم ضبطها بشكل جيد على بيانات العالم الحقيقي. طريقة واحدة لحل هذه المشكلة هي من خلال التطبيع المعجمي، وهي عملية تحويل النص غير القياسي، وعادة ما تكون من وسائل التواصل الاجتماعي، إلى نموذج أكثر موحدة. في هذا العمل، نقترح نموذج تسلسل تسلسل على مستوى الجملة بناء على MBART، مما يؤدي إلى إطارات المشكلة بمثابة مشكلة ترجمة آلية. نظرا لأن النص الصاخب يمثل مشكلة منتشرة عبر اللغات، وليس الإنجليزية فقط، فإننا نستفيد من التدريب المسبق متعدد اللغات ل MBART لضبطه إلى بياناتنا. في حين أن الأساليب الحالية تعمل بشكل رئيسي على مستوى الكلمة أو الكلمات الفرعية، فإننا نجادل بأن هذا النهج واضح واضح من وجهة نظر تقنية ويبني على شبكات المحولات الموجودة مسبقا. تظهر نتائجنا أنه في حين أن مستوى الكلمة، جوهري، فإن تقييم الأداء هو وراء الطرق الأخرى، فإن نموذجنا يحسن الأداء على مهام خارجية ومصمبة من خلال التطبيع مقارنة بالنماذج التي تعمل على نص وسائل التواصل الاجتماعي الخام وغير المجهزة.
Current benchmark tasks for natural language processing contain text that is qualitatively different from the text used in informal day to day digital communication. This discrepancy has led to severe performance degradation of state-of-the-art NLP models when fine-tuned on real-world data. One way to resolve this issue is through lexical normalization, which is the process of transforming non-standard text, usually from social media, into a more standardized form. In this work, we propose a sentence-level sequence-to-sequence model based on mBART, which frames the problem as a machine translation problem. As the noisy text is a pervasive problem across languages, not just English, we leverage the multi-lingual pre-training of mBART to fine-tune it to our data. While current approaches mainly operate at the word or subword level, we argue that this approach is straightforward from a technical standpoint and builds upon existing pre-trained transformer networks. Our results show that while word-level, intrinsic, performance evaluation is behind other methods, our model improves performance on extrinsic, downstream tasks through normalization compared to models operating on raw, unprocessed, social media text.
References used
https://aclanthology.org/
rate research
Read More
Predicting linearized Abstract Meaning Representation (AMR) graphs using pre-trained sequence-to-sequence Transformer models has recently led to large improvements on AMR parsing benchmarks. These parsers are simple and avoid explicit modeling of str
ucture but lack desirable properties such as graph well-formedness guarantees or built-in graph-sentence alignments. In this work we explore the integration of general pre-trained sequence-to-sequence language models and a structure-aware transition-based approach. We depart from a pointer-based transition system and propose a simplified transition set, designed to better exploit pre-trained language models for structured fine-tuning. We also explore modeling the parser state within the pre-trained encoder-decoder architecture and different vocabulary strategies for the same purpose. We provide a detailed comparison with recent progress in AMR parsing and show that the proposed parser retains the desirable properties of previous transition-based approaches, while being simpler and reaching the new parsing state of the art for AMR 2.0, without the need for graph re-categorization.
Complex natural language applications such as speech translation or pivot translation traditionally rely on cascaded models. However,cascaded models are known to be prone to error propagation and model discrepancy problems. Furthermore, there is no p
ossibility of using end-to-end training data in conventional cascaded systems, meaning that the training data most suited for the task cannot be used.Previous studies suggested several approaches for integrated end-to-end training to overcome those problems, however they mostly rely on(synthetic or natural) three-way data. We propose a cascaded model based on the non-autoregressive Transformer that enables end-to-end training without the need for an explicit intermediate representation. This new architecture (i) avoids unnecessary early decisions that can cause errors which are then propagated throughout the cascaded models and (ii) utilizes the end-to-end training data directly. We conduct an evaluation on two pivot-based machine translation tasks, namely French→German and German→Czech. Our experimental results show that the proposed architecture yields an improvement of more than 2 BLEU for French→German over the cascaded baseline.
The task of converting a nonstandard text to a standard and readable text is known as lexical normalization. Almost all the Natural Language Processing (NLP) applications require the text data in normalized form to build quality task-specific models.
Hence, lexical normalization has been proven to improve the performance of numerous natural language processing tasks on social media. This study aims to solve the problem of Lexical Normalization by formulating the Lexical Normalization task as a Sequence Labeling problem. This paper proposes a sequence labeling approach to solve the problem of Lexical Normalization in combination with the word-alignment technique. The goal is to use a single model to normalize text in various languages namely Croatian, Danish, Dutch, English, Indonesian-English, German, Italian, Serbian, Slovenian, Spanish, Turkish, and Turkish-German. This is a shared task in 2021 The 7th Workshop on Noisy User-generated Text (W-NUT)'' in which the participants are expected to create a system/model that performs lexical normalization, which is the translation of non-canonical texts into their canonical equivalents, comprising data from over 12 languages. The proposed single multilingual model achieves an overall ERR score of 43.75 on intrinsic evaluation and an overall Labeled Attachment Score (LAS) score of 63.12 on extrinsic evaluation. Further, the proposed method achieves the highest Error Reduction Rate (ERR) score of 61.33 among the participants in the shared task. This study highlights the effects of using additional training data to get better results as well as using a pre-trained Language model trained on multiple languages rather than only on one language.
Multi-label emotion classification is an important task in NLP and is essential to many applications. In this work, we propose a sequence-to-emotion (Seq2Emo) approach, which implicitly models emotion correlations in a bi-directional decoder. Experim
ents on SemEval'18 and GoEmotions datasets show that our approach outperforms state-of-the-art methods (without using external data). In particular, Seq2Emo outperforms the binary relevance (BR) and classifier chain (CC) approaches in a fair setting.
Non-autoregressive machine translation (NAT) approaches enable fast generation by utilizing parallelizable generative processes. The remaining bottleneck in these models is their decoder layers; unfortunately unlike in autoregressive models (Kasai et
al., 2020), removing decoder layers from NAT models significantly degrades accuracy. This work proposes a sequence-to-lattice model that replaces the decoder with a search lattice. Our approach first constructs a candidate lattice using efficient lookup operations, generates lattice scores from a deep encoder, and finally finds the best path using dynamic programming. Experiments on three machine translation datasets show that our method is faster than past non-autoregressive generation approaches, and more accurate than naively reducing the number of decoder layers.
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
