العثور على التعريفي للبيانات هو مفتاح العديد من المهام، بما في ذلك توليد المضادة.إننا نبني نظام، بالنظر إلى بيان، يسترد معرفا من مصادر متنوعة على الويب.في صميم هذا النظام هو نموذج لاستدلال اللغة الطبيعية (NLI) يحدد ما إذا كانت الجملة المرشحة زاوية سارية المفعول أم لا.ومع ذلك، فإن معظم نماذج NLI حتى الآن، تفتقر إلى قدرات التفكير المناسبة اللازمة لإيجاد التعدد الزيادة التي تنطوي على استنتاج معقد.وبالتالي، نقدم نموذج NLI المحسن للمعرفة يهدف إلى التعامل مع الاستدلال المستندة إلى السببية والمثال من خلال دمج رسوم البيانية المعرفة.تتفوق نموذج NLI الخاص بنا على خطوط الأساس لمهام NLI، خاصة بالنسبة للحالات التي تتطلب الاستدلال المستهدف.بالإضافة إلى ذلك، يحسن نموذج NLI هذا نظام استرجاع معرفي، وخاصة إيجاد مزايا معقدة بشكل أفضل.
Finding counterevidence to statements is key to many tasks, including counterargument generation. We build a system that, given a statement, retrieves counterevidence from diverse sources on the Web. At the core of this system is a natural language inference (NLI) model that determines whether a candidate sentence is valid counterevidence or not. Most NLI models to date, however, lack proper reasoning abilities necessary to find counterevidence that involves complex inference. Thus, we present a knowledge-enhanced NLI model that aims to handle causality- and example-based inference by incorporating knowledge graphs. Our NLI model outperforms baselines for NLI tasks, especially for instances that require the targeted inference. In addition, this NLI model further improves the counterevidence retrieval system, notably finding complex counterevidence better.
References used
https://aclanthology.org/
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
Automated fact-checking on a large-scale is a challenging task that has not been studied systematically until recently. Large noisy document collections like the web or news articles make the task more difficult. We describe a three-stage automated f
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
Table-based fact verification task aims to verify whether the given statement is supported by the given semi-structured table. Symbolic reasoning with logical operations plays a crucial role in this task. Existing methods leverage programs that conta
Curriculum learning, a machine training strategy that feeds training instances to the model from easy to hard, has been proven to facilitate the dialogue generation task. Meanwhile, knowledge distillation, a knowledge transformation methodology among