Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userCIDER: Commonsense Inference for Dialogue Explanation and Reasoning
عصير التفاح: استنتاج المنطقي لتفسير الحوار والتفكير
465
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
إن استنتاج المنطقي لفهم وشرح اللغة البشرية هي مشكلة بحثية أساسية في معالجة اللغة الطبيعية. يطرح المشرف على المحادثات الإنسانية تحديا كبيرا لأنه يتطلب التفاهم السياقي والتخطيط والاستدلال والعديد من جوانب المنطق بما في ذلك التفكير السببية والزمان والعموم. في هذا العمل، نقدم عصير التفاح - مجموعة بيانات مفيدة يدويا تحتوي على تفسيرات حوار دولي في شكل ثلاثة توائم في ثلاثة أضعاف تستنتج المعرفة الصريحة باستخدام استنتاج المناشد السياقي. يمكن أن يؤدي استخراج التفسيرات الغنية من المحادثات إلى تحسين العديد من التطبيقات المصب. يتم تصنيف ثلاثة توائم مشروح حسب نوع المعرفة المنطقية الحالية (على سبيل المثال، السببية، الشرطية، الزمنية). لقد أنشأنا ثلاث مهام مختلفة مكيفة على مجموعة البيانات المشروحة: الاستدلال اللغوي الطبيعي على مستوى الحوار، واستخراج تمتد، واختيار سبان متعدد الخيارات. النتائج الأساسية التي تم الحصول عليها مع النماذج القائمة على المحولات تكشف أن المهام صعبة، مما يمهد الطريق للبحث في المستقبل الواعدة. تتوفر DataSet وتطبيقات الأساس علنا في https://github.com/declare-lab/cider.
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.
References used
https://aclanthology.org/
rate research
Read More
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
ls 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.
Pre-trained language models learn socially harmful biases from their training corpora, and may repeat these biases when used for generation. We study gender biases associated with the protagonist in model-generated stories. Such biases may be express
ed either explicitly (women can't park'') or implicitly (e.g. an unsolicited male character guides her into a parking space). We focus on implicit biases, and use a commonsense reasoning engine to uncover them. Specifically, we infer and analyze the protagonist's motivations, attributes, mental states, and implications on others. Our findings regarding implicit biases are in line with prior work that studied explicit biases, for example showing that female characters' portrayal is centered around appearance, while male figures' focus on intellect.
Recent methods based on pre-trained language models have shown strong supervised performance on commonsense reasoning. However, they rely on expensive data annotation and time-consuming training. Thus, we focus on unsupervised commonsense reasoning.
We show the effectiveness of using a common framework, Natural Language Inference (NLI), to solve diverse commonsense reasoning tasks. By leveraging transfer learning from large NLI datasets, and injecting crucial knowledge from commonsense sources such as ATOMIC 2020 and ConceptNet, our method achieved state-of-the-art unsupervised performance on two commonsense reasoning tasks: WinoWhy and CommonsenseQA. Further analysis demonstrated the benefits of multiple categories of knowledge, but problems about quantities and antonyms are still challenging.
Current commonsense reasoning research focuses on developing models that use commonsense knowledge to answer multiple-choice questions. However, systems designed to answer multiple-choice questions may not be useful in applications that do not provid
e a small list of candidate answers to choose from. As a step towards making commonsense reasoning research more realistic, we propose to study open-ended commonsense reasoning (OpenCSR) --- the task of answering a commonsense question without any pre-defined choices --- using as a resource only a corpus of commonsense facts written in natural language. OpenCSR is challenging due to a large decision space, and because many questions require implicit multi-hop reasoning. As an approach to OpenCSR, we propose DrFact, an efficient Differentiable model for multi-hop Reasoning over knowledge Facts. To evaluate OpenCSR methods, we adapt several popular commonsense reasoning benchmarks, and collect multiple new answers for each test question via crowd-sourcing. Experiments show that DrFact outperforms strong baseline methods by a large margin.
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
ions from transformer-based language models (i.e., BERT), and on a variety of training methods for enhancing model generalization: 1) multi-step fine-tuning using carefully selected auxiliary tasks and datasets, and 2) a specifically designed temporal masked language model task aimed to capture temporal commonsense knowledge. Our model greatly outperforms the standard fine-tuning approach and strong baselines on the MC-TACO dataset.
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
