تجزئة موضوع الحوار أمر بالغ الأهمية في العديد من مشاكل نموذج الحوار.ومع ذلك، فإن النهج الشائعة غير المعينة الشائعة لاستغلال الميزات السطحية فقط في تقييم التماسك الموضعي بين الكلام.في هذا العمل، نتعامل مع هذا القيد من خلال الاستفادة من الإشارات الإشرافية من مهمة التسجيل في اتساق زوج الكلام.أولا، نقدم استراتيجية بسيطة ولكنها فعالة لتوليد كوربوس التدريب لتسجيلات التماسك زوج الكلام.بعد ذلك، ندرب نموذج متماسك نطق برت مقره برت مع Corpus التدريب الذي تم الحصول عليه.أخيرا، يتم استخدام هذا النموذج لقياس الملاءمة الموضعية بين الكلام، والتصرف كأساس لاستدلال التجزئة.تجارب على ثلاث مجموعات بيانات عامة باللغة الإنجليزية والصينية توضح أن اقتراحنا يتفوق على خطوط الأساس الحديثة.
Dialogue topic segmentation is critical in several dialogue modeling problems. However, popular unsupervised approaches only exploit surface features in assessing topical coherence among utterances. In this work, we address this limitation by leveraging supervisory signals from the utterance-pair coherence scoring task. First, we present a simple yet effective strategy to generate a training corpus for utterance-pair coherence scoring. Then, we train a BERT-based neural utterance-pair coherence model with the obtained training corpus. Finally, such model is used to measure the topical relevance between utterances, acting as the basis of the segmentation inference. Experiments on three public datasets in English and Chinese demonstrate that our proposal outperforms the state-of-the-art baselines.
References used
https://aclanthology.org/
Recent state-of-the-art approaches in open-domain dialogue include training end-to-end deep-learning models to learn various conversational features like emotional content of response, symbolic transitions of dialogue contexts in a knowledge graph an
With the increasing abundance of meeting transcripts, meeting summary has attracted more and more attention from researchers. The unsupervised pre-training method based on transformer structure combined with fine-tuning of downstream tasks has achiev
This work revisits the task of detecting decision-related utterances in multi-party dialogue. We explore performance of a traditional approach and a deep learning-based approach based on transformer language models, with the latter providing modest i
We present a novel technique for zero-shot paraphrase generation. The key contribution is an end-to-end multilingual paraphrasing model that is trained using translated parallel corpora to generate paraphrases into meaning spaces'' -- replacing the f
Despite the remarkable progress in the field of computational argumentation, dialogue systems concerned with argumentative tasks often rely on structured knowledge about arguments and their relations. Since the manual acquisition of these argument st