Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userFaBULOUS: Fact-checking Based on Understanding of Language Over Unstructured and Structured information
رائع: فحص الحقائق بناء على فهم اللغة على المعلومات غير المنظمة والمنظم
173
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
كجزء من المهمة المشتركة الحميرة، قمنا بتطوير بنية قوية ومضبوطة بدقة للتعامل مع الاسترجاع المشترك وتتبعها على البيانات النصية وكذلك البيانات الهيكلية مثل الجداول.اقترحنا خططين تدريبي لمعالجة العقبات المتأصلة لمجموعات البيانات متعددة الوسائط متعددة القفزات.أول واحد يسمح بإجراء استرجاع قوي لمجموعات الأدلة الكاملة، في حين أن المرء الثاني يتيح الاستيطاط الاستفادة الكاملة من مدخلات الأدلة الصاخبة.بالإضافة إلى ذلك، كشف عملنا عن رؤى مهمة وسيلة بحثية محتملة للتحسين في المستقبل على هذا النوع من مجموعة البيانات.في التقييم الأولي حول مجموعة اختبار المهام المشتركة الحميرة، يحقق نظامنا 0.271 درجة حمامة، مع استدعاء الأدلة 0.4258 ودقة استقامة 0.5607.
As part of the FEVEROUS shared task, we developed a robust and finely tuned architecture to handle the joint retrieval and entailment on text data as well as structured data like tables. We proposed two training schemes to tackle the hurdles inherent to multi-hop multi-modal datasets. The first one allows having a robust retrieval of full evidence sets, while the second one enables entailment to take full advantage of noisy evidence inputs. In addition, our work has revealed important insights and potential avenue of research for future improvement on this kind of dataset. In preliminary evaluation on the FEVEROUS shared task test set, our system achieves 0.271 FEVEROUS score, with 0.4258 evidence recall and 0.5607 entailment accuracy.
References used
https://aclanthology.org/
rate research
Read More
The task of verifying the truthfulness of claims in textual documents, or fact-checking, has received significant attention in recent years. Many existing evidence-based factchecking datasets contain synthetic claims and the models trained on these d
ata might not be able to verify real-world claims. Particularly few studies addressed evidence-based fact-checking of health-related claims that require medical expertise or evidence from the scientific literature. In this paper, we introduce HEALTHVER, a new dataset for evidence-based fact-checking of health-related claims that allows to study the validity of real-world claims by evaluating their truthfulness against scientific articles. Using a three-step data creation method, we first retrieved real-world claims from snippets returned by a search engine for questions about COVID-19. Then we automatically retrieved and re-ranked relevant scientific papers using a T5 relevance-based model. Finally, the relations between each evidence statement and the associated claim were manually annotated as SUPPORT, REFUTE and NEUTRAL. To validate the created dataset of 14,330 evidence-claim pairs, we developed baseline models based on pretrained language models. Our experiments showed that training deep learning models on real-world medical claims greatly improves performance compared to models trained on synthetic and open-domain claims. Our results and manual analysis suggest that HEALTHVER provides a realistic and challenging dataset for future efforts on evidence-based fact-checking of health-related claims. The dataset, source code, and a leaderboard are available at https://github.com/sarrouti/healthver.
Fact Extraction and VERification (FEVER) is a recently introduced task that consists of the following subtasks (i) document retrieval, (ii) sentence retrieval, and (iii) claim verification. In this work, we focus on the subtask of sentence retrieval.
Specifically, we propose an evidence-aware transformer-based model that outperforms all other models in terms of FEVER score by using a subset of training instances. In addition, we conduct a large experimental study to get a better understanding of the problem, while we summarize our findings by presenting future research challenges.
Recent question answering and machine reading benchmarks frequently reduce the task to one of pinpointing spans within a certain text passage that answers the given question. Typically, these systems are not required to actually understand the text o
n a deeper level that allows for more complex reasoning on the information contained. We introduce a new dataset called BiQuAD that requires deeper comprehension in order to answer questions in both extractive and deductive fashion. The dataset consist of 4,190 closed-domain texts and a total of 99,149 question-answer pairs. The texts are synthetically generated soccer match reports that verbalize the main events of each match. All texts are accompanied by a structured Datalog program that represents a (logical) model of its information. We show that state-of-the-art QA models do not perform well on the challenging long form contexts and reasoning requirements posed by the dataset. In particular, transformer based state-of-the-art models achieve F1-scores of only 39.0. We demonstrate how these synthetic datasets align structured knowledge with natural text and aid model introspection when approaching complex text understanding.
In this paper, we propose a novel fact checking and verification system to check claims against Wikipedia content. Our system retrieves relevant Wikipedia pages using Anserini, uses BERT-large-cased question answering model to select correct evidence
, and verifies claims using XLNET natural language inference model by comparing it with the evidence. Table cell evidence is obtained through looking for entity-matching cell values and TAPAS table question answering model. The pipeline utilizes zero-shot capabilities of existing models and all the models used in the pipeline requires no additional training. Our system got a FEVEROUS score of 0.06 and a label accuracy of 0.39 in FEVEROUS challenge.
Inspired by mutual information (MI) based feature selection in SVMs and logistic regression, in this paper, we propose MI-based layer-wise pruning: for each layer of a multi-layer neural network, neurons with higher values of MI with respect to prese
rved neurons in the upper layer are preserved. Starting from the top softmax layer, layer-wise pruning proceeds in a top-down fashion until reaching the bottom word embedding layer. The proposed pruning strategy offers merits over weight-based pruning techniques: (1) it avoids irregular memory access since representations and matrices can be squeezed into their smaller but dense counterparts, leading to greater speedup; (2) in a manner of top-down pruning, the proposed method operates from a more global perspective based on training signals in the top layer, and prunes each layer by propagating the effect of global signals through layers, leading to better performances at the same sparsity level. Extensive experiments show that at the same sparsity level, the proposed strategy offers both greater speedup and higher performances than weight-based pruning methods (e.g., magnitude pruning, movement pruning).
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
