Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userTeam Papelo at FEVEROUS: Multi-hop Evidence Pursuit
فريق Papelo في FEVEROUS: الأدلة متعددة القفز
281
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
نقوم بتطوير نظام لمهمة استخراج الحقائق الحميرة والتحقق من تحديد مجموعة أولية من الأدلة المحتملة، ثم يتابع الأدلة المفقودة في القفزات اللاحقة من خلال محاولة توليدها، مع وجود وحدة توقعات القفز التالية "التي يتم مطابقة خرجها من عناصر الصفحاتمقال متوقع.تسعى للحصول على أدلة مع وحدة تنبؤ القفز التالية تستمر في تحسين النتيجة الحميرة لمدة تصل إلى سبع قفزات.يتم تدريب تصنيف العلامات على سلاسل الأدلة المستخرجة غير كاملة غير كاملة، واستخدام تلميحات التي تسهل المقارنة العددية.يحقق النظام .281 النتيجة الحميرة ودقة التسمية .658 على مجموعة التطوير، وينتهي في المرتبة الثانية باستخدام 0.259 درجة حمامة ودقة التسمية .576 على مجموعة الاختبار.
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.
References used
https://aclanthology.org/
rate research
Read More
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 correc
t 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
Computational fact-checking has gained a lot of traction in the machine learning and natural language processing communities. A plethora of solutions have been developed, but methods which leverage both structured and unstructured information to dete
ct misinformation are of particular relevance. In this paper, we tackle the FEVEROUS (Fact Extraction and VERification Over Unstructured and Structured information) challenge which consists of an open source baseline system together with a benchmark dataset containing 87,026 verified claims. We extend this baseline model by improving the evidence retrieval module yielding the best evidence F1 score among the competitors in the challenge leaderboard while obtaining an overall FEVEROUS score of 0.20 (5th best ranked system).
How can we generate concise explanations for multi-hop Reading Comprehension (RC)? The current strategies of identifying supporting sentences can be seen as an extractive question-focused summarization of the input text. However, these extractive exp
lanations are not necessarily concise i.e. not minimally sufficient for answering a question. Instead, we advocate for an abstractive approach, where we propose to generate a question-focused, abstractive summary of input paragraphs and then feed it to an RC system. Given a limited amount of human-annotated abstractive explanations, we train the abstractive explainer in a semi-supervised manner, where we start from the supervised model and then train it further through trial and error maximizing a conciseness-promoted reward function. Our experiments demonstrate that the proposed abstractive explainer can generate more compact explanations than an extractive explainer with limited supervision (only 2k instances) while maintaining sufficiency.
Knowledge graphs are essential for numerous downstream natural language processing applications, but are typically incomplete with many facts missing. This results in research efforts on multi-hop reasoning task, which can be formulated as a search p
rocess and current models typically perform short distance reasoning. However, the long-distance reasoning is also vital with the ability to connect the superficially unrelated entities. To the best of our knowledge, there lacks a general framework that approaches multi-hop reasoning in mixed long-short distance reasoning scenarios. We argue that there are two key issues for a general multi-hop reasoning model: i) where to go, and ii) when to stop. Therefore, we propose a general model which resolves the issues with three modules: 1) the local-global knowledge module to estimate the possible paths, 2) the differentiated action dropout module to explore a diverse set of paths, and 3) the adaptive stopping search module to avoid over searching. The comprehensive results on three datasets demonstrate the superiority of our model with significant improvements against baselines in both short and long distance reasoning scenarios.
Claim verification is challenging because it requires first to find textual evidence and then apply claim-evidence entailment to verify a claim. Previous works evaluate the entailment step based on the retrieved evidence, whereas we hypothesize that
the entailment prediction can provide useful signals for evidence retrieval, in the sense that if a sentence supports or refutes a claim, the sentence must be relevant. We propose a novel model that uses the entailment score to express the relevancy. Our experiments verify that leveraging entailment prediction improves ranking multiple pieces of evidence.
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
