Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userProbing Commonsense Explanation in Dialogue Response Generation
التحقيق في تفسير المنطقي في جيل استجابة الحوار
349
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
يستخدم البشر منطق المنطقي (CSR) ضمنيا لإنتاج ردود طبيعية ومتماسكة في المحادثات. تهدف إلى إغلاق الفجوة بين نماذج جيل الاستجابة الحالية (RG) قدرات الاتصالات البشرية، نريد أن نفهم لماذا تستجيب نماذج RG أثناء قيامهم بتحقيق فهم نموذج RG للمنطق المنطقي الذي يثير الاستجابات المناسبة. نحن نقوم بإضفاء الطابع الرسمي على المشكلة عن طريق تأطير العمولة كمتغير كامن في مهمة RG واستخدام توضيحات للاستجابات كأشكال نصية من العمليات النصية. نجمع 6K تفسيرات مشروحة تبرر الردود من أربعة مجموعات من مجموعات بيانات الحوار ونسأل البشر للتحقق منها واقتراح اثنين من إعدادات التحقيق لتقييم قدرات CSR نماذج RG. تظهر النتائج التحقيق أن النماذج تفشل في التقاط العلاقات المنطقية بين تفسيرات والردود المنطقية والضبط بشكل جيد على البيانات داخل المجال والأحجام النموذجية المتزايدة لا تؤدي إلى فهم المسؤولية الاجتماعية للشركات ل RG. نأمل أن تقوم دراستنا بحفز المزيد من الأبحاث في جعل نماذج RG محاكاة عملية التفكير البشرية في السعي لتحقيق اتصال ناعم للإنسان العربي.
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 models respond as they do by probing RG model's understanding of commonsense reasoning that elicits proper responses. We formalize the problem by framing commonsense as a latent variable in the RG task and using explanations for responses as textual form of commonsense. We collect 6k annotated explanations justifying responses from four dialogue datasets and ask humans to verify them and propose two probing settings to evaluate RG models' CSR capabilities. Probing results show that models fail to capture the logical relations between commonsense explanations and responses and fine-tuning on in-domain data and increasing model sizes do not lead to understanding of CSR for RG. We hope our study motivates more research in making RG models emulate the human reasoning process in pursuit of smooth human-AI communication.
References used
https://aclanthology.org/
rate research
Read More
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.
Commonsense inference to understand and explain human language is a fundamental research problem in natural language processing. Explaining human conversations poses a great challenge as it requires contextual understanding, planning, inference, and
several aspects of reasoning including causal, temporal, and commonsense reasoning. In this work, we introduce CIDER -- a manually curated dataset that contains dyadic dialogue explanations in the form of implicit and explicit knowledge triplets inferred using contextual commonsense inference. Extracting such rich explanations from conversations can be conducive to improving several downstream applications. The annotated triplets are categorized by the type of commonsense knowledge present (e.g., causal, conditional, temporal). We set up three different tasks conditioned on the annotated dataset: Dialogue-level Natural Language Inference, Span Extraction, and Multi-choice Span Selection. Baseline results obtained with transformer-based models reveal that the tasks are difficult, paving the way for promising future research. The dataset and the baseline implementations are publicly available at https://github.com/declare-lab/CIDER.
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
rol the generation. Recent works have tried on learning sentence representations using Transformer-based framework, but do not model the context-response relationship embedded in the dialogue datasets. In this work, we aim to construct a robust sentence representation learning model, that is specifically designed for dialogue response generation, with Transformer-based encoder-decoder structure. An utterance-level contrastive learning is proposed, encoding predictive information in each context representation for its corresponding response. Extensive experiments are conducted to verify the robustness of the proposed representation learning mechanism. By using both reference-based and reference-free evaluation metrics, we provide detailed analysis on the generated sentences, demonstrating the effectiveness of our proposed model.
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
the view of Kullback-Leibler divergence (KLD) and show that the gap between the real world probability distribution and the single-referenced data's probability distribution prevents the model from learning the one-to-many relations efficiently. Then we explore approaches to multi-referenced training in two aspects. Data-wise, we generate diverse pseudo references from a powerful pretrained model to build multi-referenced data that provides a better approximation of the real-world distribution. Model-wise, we propose to equip variational models with an expressive prior, named linear Gaussian model (LGM). Experimental results of automated evaluation and human evaluation show that the methods yield significant improvements over baselines.
Variational autoencoders have been studied as a promising approach to model one-to-many mappings from context to response in chat response generation. However, they often fail to learn proper mappings. One of the reasons for this failure is the discr
epancy between a response and a latent variable sampled from an approximated distribution in training. Inappropriately sampled latent variables hinder models from constructing a modulated latent space. As a result, the models stop handling uncertainty in conversations. To resolve that, we propose speculative sampling of latent variables. Our method chooses the most probable one from redundantly sampled latent variables for tying up the variable with a given response. We confirm the efficacy of our method in response generation with massive dialogue data constructed from Twitter posts.
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
