بالنسبة لجهاز كمبيوتر يتفاعل بشكل طبيعي مع إنسان، يجب أن يكون يشبه الإنسان.في هذه الورقة، نقترح نموذج توليد الاستجابة العصبي مع التعلم متعدد المهام للجيل والتصنيف، مع التركيز على العاطفة.يتم تدريب نموذجنا على أساس بارت (لويس وآخرون.، 2020)، وهو نموذج ترميز ترميز محول مدرب مسبقا، لتوليد الردود والاعتراف بالمشاعر في وقت واحد.علاوة على ذلك، فنحن نثق خسائر المهام للتحكم في تحديث المعلمات.تظهر التقييمات التلقائية والتقييمات الدليلية للجماعة الجماعية أن النموذج المقترح يجعل الردود التي تم إنشاؤها أكثر وعيا بنفسك.
For a computer to naturally interact with a human, it needs to be human-like. In this paper, we propose a neural response generation model with multi-task learning of generation and classification, focusing on emotion. Our model based on BART (Lewis et al., 2020), a pre-trained transformer encoder-decoder model, is trained to generate responses and recognize emotions simultaneously. Furthermore, we weight the losses for the tasks to control the update of parameters. Automatic evaluations and crowdsourced manual evaluations show that the proposed model makes generated responses more emotionally aware.
References used
https://aclanthology.org/
Large-scale auto-regressive models have achieved great success in dialogue response generation, with the help of Transformer layers. However, these models do not learn a representative latent space of the sentence distribution, making it hard to cont
In open-domain dialogue response generation, a dialogue context can be continued with diverse responses, and the dialogue models should capture such one-to-many relations. In this work, we first analyze the training objective of dialogue models from
Humans use commonsense reasoning (CSR) implicitly to produce natural and coherent responses in conversations. Aiming to close the gap between current response generation (RG) models and human communication abilities, we want to understand why RG mode
Conditioned dialogue generation suffers from the scarcity of labeled responses. In this work, we exploit labeled non-dialogue text data related to the condition, which are much easier to collect. We propose a multi-task learning approach to leverage
In task-oriented dialogue systems, recent dialogue state tracking methods tend to perform one-pass generation of the dialogue state based on the previous dialogue state. The mistakes of these models made at the current turn are prone to be carried ov