إن الاستدلال اللغوي الطبيعي (NLI) هي مهمة تحديد ما إذا كان جزء من النص ينطوي أو يتناقض أو لا علاقة له بقطعة أخرى من النص.في هذه الورقة، نحقق في كيفية ندف الاستنتاجات المنهجية (أي، العناصر التي يتفق بها الناس على تسمية NLI) بصرف النظر عن عناصر الخلاف (أي عناصر، التي تؤدي إلى تشريحية مختلفة)، والتي تم تجاهلها معظم العمل السابق.لتمييز الاستدلالات المنهجية عن عناصر الخلاف، نقترح معلقين اصطناعي (AAS) لمحاكاة عدم اليقين في عملية التوضيحية من خلال التقاط الأوضاع في التعليقات التوضيحية.تؤكد النتائج على الالتزام، وهي وجعة من خطابات حدوث طبيعية باللغة الإنجليزية، أن نهجنا يؤدي إحصائيا أفضل بكثير من جميع خطوط الأساس.نوضح كذلك أن AAS تعلم الأنماط اللغوية والتفكير المعتمد على السياق.
Natural language inference (NLI) is the task of determining whether a piece of text is entailed, contradicted by or unrelated to another piece of text. In this paper, we investigate how to tease systematic inferences (i.e., items for which people agree on the NLI label) apart from disagreement items (i.e., items which lead to different annotations), which most prior work has overlooked. To distinguish systematic inferences from disagreement items, we propose Artificial Annotators (AAs) to simulate the uncertainty in the annotation process by capturing the modes in annotations. Results on the CommitmentBank, a corpus of naturally occurring discourses in English, confirm that our approach performs statistically significantly better than all baselines. We further show that AAs learn linguistic patterns and context-dependent reasoning.
References used
https://aclanthology.org/
Recent methods based on pre-trained language models have shown strong supervised performance on commonsense reasoning. However, they rely on expensive data annotation and time-consuming training. Thus, we focus on unsupervised commonsense reasoning.
Many open-domain question answering problems can be cast as a textual entailment task, where a question and candidate answers are concatenated to form hypotheses. A QA system then determines if the supporting knowledge bases, regarded as potential pr
Deep learning (DL) based language models achieve high performance on various benchmarks for Natural Language Inference (NLI). And at this time, symbolic approaches to NLI are receiving less attention. Both approaches (symbolic and DL) have their adva
Due to large number of entities in biomedical knowledge bases, only a small fraction of entities have corresponding labelled training data. This necessitates entity linking models which are able to link mentions of unseen entities using learned repre
This paper describes the entry of the research group SINAI at SMM4H's ProfNER task on the identification of professions and occupations in social media related with health. Specifically we have participated in Task 7a: Tweet Binary Classification to