نماذج اللغة التوليدية المدربة على كبيرة، يمكن لشركة Corga الإجابة على الأسئلة حول مرور عن طريق توليد استمرار المرجح للمقطع الذي يتبعه زوج سؤال / إجابة.ومع ذلك، تختلف معدلات الدقة اعتمادا على نوع السؤال المطروح.في هذه الورقة، نحتفظ بالمرور الثابت، واختبار مجموعة واسعة من أنواع الأسئلة، واستكشاف نقاط القوة والضعف في نموذج لغة GPT-3.نحن نقدم أسئلة المرور واختبارها كتحدي محدد لنماذج لغات أخرى.
Generative language models trained on large, diverse corpora can answer questions about a passage by generating the most likely continuation of the passage followed by a question/answer pair. However, accuracy rates vary depending on the type of question asked. In this paper we keep the passage fixed, and test with a wide variety of question types, exploring the strengths and weaknesses of the GPT-3 language model. We provide the passage and test questions as a challenge set for other language models.
References used
https://aclanthology.org/
Despite achieving encouraging results, neural Referring Expression Generation models are often thought to lack transparency. We probed neural Referential Form Selection (RFS) models to find out to what extent the linguistic features influencing the R
GPT-3 shows remarkable in-context learning ability of large-scale language models (LMs) trained on hundreds of billion scale data. Here we address some remaining issues less reported by the GPT-3 paper, such as a non-English LM, the performances of d
Multilingual Neural Machine Translation has achieved remarkable performance by training a single translation model for multiple languages. This paper describes our submission (Team ID: CFILT-IITB) for the MultiIndicMT: An Indic Language Multilingual
We analyse how a transformer-based language model learns the rules of chess from text data of recorded games. We show how it is possible to investigate how the model capacity and the available number of training data influence the learning success of
Temporal commonsense reasoning is a challenging task as it requires temporal knowledge usually not explicit in text. In this work, we propose an ensemble model for temporal commonsense reasoning. Our model relies on pre-trained contextual representat