Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userDeepBlueAI at TextGraphs 2021 Shared Task: Treating Multi-Hop Inference Explanation Regeneration as A Ranking Problem
Deepblueai في TEXTGRAPHS 2021 المهمة المشتركة: علاج تجديد تفسير القفزات متعددة القفز كشام
217
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
تصف هذه الورقة النظام الفائز للمهمة المشتركة للمكاسب 2021: تجديد شرح القفز متعدد القفز. بالنظر إلى سؤال وإجابته الصحيحة المقابلة، تهدف هذه المهمة إلى تحديد الحقائق التي يمكن أن توضح سبب صحة الإجابة لهذا السؤال والرد (ضمان الجودة) من قاعدة معارف كبيرة. لمعالجة هذه المشكلة وتسريع التدريب أيضا، تتضمن استراتيجيتنا خطوتين. أولا، قم بضبط النماذج اللغوية المدربة مسبقا (PLMS) مع فقدان ثلاثي لاستدعاء الحقائق ذات الصلة Top-K لكل سؤال وجواب. بعد ذلك، اعتماد نفس الهندسة المعمارية لتدريب نموذج إعادة الترتيب لترتيب المرشحين الأعلى K. لتعزيز الأداء، نحن متوسط النتائج من النماذج المستندة إلى PLMS مختلفة (E.G.، ROBERTA) وإعدادات المعلمات المختلفة لجعل التنبؤات النهائية. يوضح التقييم الرسمي أنه، يمكن أن يتفوق نظامنا على ثاني أفضل نظام بمقدار 4.93 نقطة، مما يثبت فعالية نظامنا. كان رمزنا مفتوح المصدر، والعنوان هو https://github.com/deepblueaii/textgraphs-15
This paper describes the winning system for TextGraphs 2021 shared task: Multi-hop inference explanation regeneration. Given a question and its corresponding correct answer, this task aims to select the facts that can explain why the answer is correct for that question and answering (QA) from a large knowledge base. To address this problem and accelerate training as well, our strategy includes two steps. First, fine-tuning pre-trained language models (PLMs) with triplet loss to recall top-K relevant facts for each question and answer pair. Then, adopting the same architecture to train the re-ranking model to rank the top-K candidates. To further improve the performance, we average the results from models based on different PLMs (e.g., RoBERTa) and different parameter settings to make the final predictions. The official evaluation shows that, our system can outperform the second best system by 4.93 points, which proves the effectiveness of our system. Our code has been open source, address is https://github.com/DeepBlueAI/TextGraphs-15
References used
https://aclanthology.org/
rate research
Read More
This paper discusses different approaches to the Toxic Spans Detection task. The problem posed by the task was to determine which words contribute mostly to recognising a document as toxic. As opposed to binary classification of entire texts, word-le
vel assessment could be of great use during comment moderation, also allowing for a more in-depth comprehension of the model's predictions. As the main goal was to ensure transparency and understanding, this paper focuses on the current state-of-the-art approaches based on the explainable AI concepts and compares them to a supervised learning solution with word-level labels. The work consists of two xAI approaches that automatically provide the explanation for models trained for binary classification of toxic documents: an LSTM model with attention as a model-specific approach and the Shapley values for interpreting BERT predictions as a model-agnostic method. The competing approach considers this problem as supervised token classification, where models like BERT and its modifications were tested. The paper aims to explore, compare and assess the quality of predictions for different methods on the task. The advantages of each approach and further research direction are also discussed.
This paper present a description for the ROCLING 2021 shared task in dimensional sentiment analysis for educational texts. We submitted two runs in the final test. Both runs use the standard regression model. The Run1 uses Chinese version of BERT as
the base, and in Run2 we use the early version of MacBERT that Chinese version of RoBERTa-like BERT model, RoBERTa-wwm-ext. Using powerful pre-training model of BERT for text embedding to help train the model.
Lexical complexity plays an important role in reading comprehension. lexical complexity prediction (LCP) can not only be used as a part of Lexical Simplification systems, but also as a stand-alone application to help people better reading. This paper
presents the winning system we submitted to the LCP Shared Task of SemEval 2021 that capable of dealing with both two subtasks. We first perform fine-tuning on numbers of pre-trained language models (PLMs) with various hyperparameters and different training strategies such as pseudo-labelling and data augmentation. Then an effective stacking mechanism is applied on top of the fine-tuned PLMs to obtain the final prediction. Experimental results on the Complex dataset show the validity of our method and we rank first and second for subtask 2 and 1.
We develop a system for the FEVEROUS fact extraction and verification task that ranks an initial set of potential evidence and then pursues missing evidence in subsequent hops by trying to generate it, with a next hop prediction module'' whose output
is matched against page elements in a predicted article. Seeking evidence with the next hop prediction module continues to improve FEVEROUS score for up to seven hops. Label classification is trained on possibly incomplete extracted evidence chains, utilizing hints that facilitate numerical comparison. The system achieves .281 FEVEROUS score and .658 label accuracy on the development set, and finishes in second place with .259 FEVEROUS score and .576 label accuracy on the test set.
Among the tasks motivated by the proliferation of misinformation, propaganda detection is particularly challenging due to the deficit of fine-grained manual annotations required to train machine learning models. Here we show how data from other relat
ed tasks, including credibility assessment, can be leveraged in multi-task learning (MTL) framework to accelerate the training process. To that end, we design a BERT-based model with multiple output layers, train it in several MTL scenarios and perform evaluation against the SemEval gold standard.
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
