Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userCommonsense-Focused Dialogues for Response Generation: An Empirical Study
حوارات تركز على المنطقية لتوليد الاستجابة: دراسة تجريبية
288
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
يتطلب التواصل السلس والفعال القدرة على أداء استنتاج المناشد الكامن أو الصريح. يركز معايير التفكير في المناولة (مثل Socialiqa و Commonsenseqa) بشكل رئيسي على المهمة التمييزية المتمثلة في اختيار الإجابة الصحيحة من مجموعة من المرشحين، ولا تنطوي على توليد لغة تفاعلية كما هو الحال في الحوار. علاوة على ذلك، فإن مجموعات بيانات الحوار الحالية لا تركز صراحة على عرض المنطقي كجايت. في هذه الورقة، نقدم دراسة تجريبية للعموم في توليد استجابة الحوار. نحن أولا استخراج السيارات الحوارات العمومية من مجموعات بيانات الحوار الموجودة من خلال الاستفادة من Congalnet، الرسم البياني المعرفة للعموم. علاوة على ذلك، بناء على السياقات الاجتماعية / المواقف في Socialiqa، نجمع مجموعة بيانات حوار جديدة مع حوارات 25 كيلو بايت تهدف إلى عرض العمولة الاجتماعية في بيئة تفاعلية. نقوم بتقييم نماذج توليد الاستجابة المدربة باستخدام مجموعات البيانات هذه والعثور على النماذج المدربة على كلا من المستخرجة وبياناتنا التي تم جمعها تنتج الردود التي تظهر باستمرار المزيد من المنطقي من الأساس. أخيرا، نقترح نهج للتقييم التلقائي للعموم التي تعتمد على ميزات مشتقة من نماذج النقدية واللغة المدربة مسبقا وحوار الحوار، وتظهر ارتباطا معقولا بالتقييم البشري لجودة الردود.
Smooth and effective communication requires the ability to perform latent or explicit commonsense inference. Prior commonsense reasoning benchmarks (such as SocialIQA and CommonsenseQA) mainly focus on the discriminative task of choosing the right answer from a set of candidates, and do not involve interactive language generation as in dialogue. Moreover, existing dialogue datasets do not explicitly focus on exhibiting commonsense as a facet. In this paper, we present an empirical study of commonsense in dialogue response generation. We first auto-extract commonsensical dialogues from existing dialogue datasets by leveraging ConceptNet, a commonsense knowledge graph. Furthermore, building on social contexts/situations in SocialIQA, we collect a new dialogue dataset with 25K dialogues aimed at exhibiting social commonsense in an interactive setting. We evaluate response generation models trained using these datasets and find that models trained on both extracted and our collected data produce responses that consistently exhibit more commonsense than baselines. Finally we propose an approach for automatic evaluation of commonsense that relies on features derived from ConceptNet and pre-trained language and dialog models, and show reasonable correlation with human evaluation of responses' commonsense quality.
References used
https://aclanthology.org/
rate research
Read More
Understanding speaker's feelings and producing appropriate responses with emotion connection is a key communicative skill for empathetic dialogue systems. In this paper, we propose a simple technique called Affective Decoding for empathetic response
generation. Our method can effectively incorporate emotion signals during each decoding step, and can additionally be augmented with an auxiliary dual emotion encoder, which learns separate embeddings for the speaker and listener given the emotion base of the dialogue. Extensive empirical studies show that our models are perceived to be more empathetic by human evaluations, in comparison to several strong mainstream methods for empathetic responding.
Although there are many studies on neural language generation (NLG), few trials are put into the real world, especially in the advertising domain. Generating ads with NLG models can help copywriters in their creation. However, few studies have adequa
tely evaluated the effect of generated ads with actual serving included because it requires a large amount of training data and a particular environment. In this paper, we demonstrate a practical use case of generating ad-text with an NLG model. Specially, we show how to improve the ads' impact, deploy models to a product, and evaluate the generated ads.
Recent development in NLP shows a strong trend towards refining pre-trained models with a domain-specific dataset. This is especially the case for response generation where emotion plays an important role. However, existing empathetic datasets remain
small, delaying research efforts in this area, for example, the development of emotion-aware chatbots. One main technical challenge has been the cost of manually annotating dialogues with the right emotion labels. In this paper, we describe a large-scale silver dataset consisting of 1M dialogues annotated with 32 fine-grained emotions, eight empathetic response intents, and the Neutral category. To achieve this goal, we have developed a novel data curation pipeline starting with a small seed of manually annotated data and eventually scaling it to a satisfactory size. We compare its quality against a state-of-the-art gold dataset using both offline experiments and visual validation methods. The resultant procedure can be used to create similar datasets in the same domain as well as in other domains.
Recent years have seen a flourishing of neural keyphrase generation (KPG) works, including the release of several large-scale datasets and a host of new models to tackle them. Model performance on KPG tasks has increased significantly with evolving d
eep learning research. However, there lacks a comprehensive comparison among different model designs, and a thorough investigation on related factors that may affect a KPG system's generalization performance. In this empirical study, we aim to fill this gap by providing extensive experimental results and analyzing the most crucial factors impacting the generalizability of KPG models. We hope this study can help clarify some of the uncertainties surrounding the KPG task and facilitate future research on this topic.
Empathy is a complex cognitive ability based on the reasoning of others' affective states. In order to better understand others and express stronger empathy in dialogues, we argue that two issues must be tackled at the same time: (i) identifying whic
h word is the cause for the other's emotion from his or her utterance and (ii) reflecting those specific words in the response generation. However, previous approaches for recognizing emotion cause words in text require sub-utterance level annotations, which can be demanding. Taking inspiration from social cognition, we leverage a generative estimator to infer emotion cause words from utterances with no word-level label. Also, we introduce a novel method based on pragmatics to make dialogue models focus on targeted words in the input during generation. Our method is applicable to any dialogue models with no additional training on the fly. We show our approach improves multiple best-performing dialogue agents on generating more focused empathetic responses in terms of both automatic and human evaluation.
suggested questions
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
