Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userShortcutted Commonsense: Data Spuriousness in Deep Learning of Commonsense Reasoning
Cortcutted Commonsense: Data Sprications في التعلم العميق من التفكير المنطقي
386
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
المنطقية هي القدرة البشرية المثالية التي كانت تحديا أساسيا للذكاء الاصطناعي منذ إنشائها. النتائج المثيرة للإعجاب في مهام معالجة اللغة الطبيعية، بما في ذلك في مجال المنطقي، قد تحققت باستمرار مع نماذج اللغة العصبية المحولات، حتى مطابقة أو تجاوز الأداء البشري في بعض المعايير. في الآونة الأخيرة، تم استدعاء بعض هذه التقدم سؤالا: لذلك ما يسمى بتحف البيانات في البيانات التدريبية واضحة مثل الارتباطات الزائفة والاختصارات الضحلة التي تستفيد في بعض النتائج هذه النتائج المتميزة. في هذه الورقة نسعى إلى مزيد من متابعة هذا التحليل في عالم مهام معالجة اللغة ذات الصلة بالعموم. نحن نقوم بدراسة عن مختلف المعايير البارزة التي تنطوي على التفكير في المنطقية، على طول عدد من تجارب الإجهاد الرئيسية، وبالتالي تسعى للحصول على نظرة ثاقبة حول ما إذا كانت النماذج تتعلم التعميمات القابلة للتحويل جوهرية للمشكلة الموجودة على المحك أو الاستفادة من الاختصارات العرضية في البيانات العناصر. تشير النتائج التي تم الحصول عليها إلى أن معظم مجموعات البيانات جربت إشكالية، مع اللجوء من النماذج إلى ميزات غير قوية ويبدو أن لا تتعلم وتعميم تجاه المهام الشاملة التي تهدف إلى نقلها أو تكتسبها مجموعات البيانات.
Commonsense is a quintessential human capacity that has been a core challenge to Artificial Intelligence since its inception. Impressive results in Natural Language Processing tasks, including in commonsense reasoning, have consistently been achieved with Transformer neural language models, even matching or surpassing human performance in some benchmarks. Recently, some of these advances have been called into question: so called data artifacts in the training data have been made evident as spurious correlations and shallow shortcuts that in some cases are leveraging these outstanding results. In this paper we seek to further pursue this analysis into the realm of commonsense related language processing tasks. We undertake a study on different prominent benchmarks that involve commonsense reasoning, along a number of key stress experiments, thus seeking to gain insight on whether the models are learning transferable generalizations intrinsic to the problem at stake or just taking advantage of incidental shortcuts in the data items. The results obtained indicate that most datasets experimented with are problematic, with models resorting to non-robust features and appearing not to be learning and generalizing towards the overall tasks intended to be conveyed or exemplified by the datasets.
References used
https://aclanthology.org/
rate research
Read More
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.
Pre-trained language models have led to substantial gains over a broad range of natural language processing (NLP) tasks, but have been shown to have limitations for natural language generation tasks with high-quality requirements on the output, such
as commonsense generation and ad keyword generation. In this work, we present a novel Knowledge Filtering and Contrastive learning Network (KFCNet) which references external knowledge and achieves better generation performance. Specifically, we propose a BERT-based filter model to remove low-quality candidates, and apply contrastive learning separately to each of the encoder and decoder, within a general encoder--decoder architecture. The encoder contrastive module helps to capture global target semantics during encoding, and the decoder contrastive module enhances the utility of retrieved prototypes while learning general features. Extensive experiments on the CommonGen benchmark show that our model outperforms the previous state of the art by a large margin: +6.6 points (42.5 vs. 35.9) for BLEU-4, +3.7 points (33.3 vs. 29.6) for SPICE, and +1.3 points (18.3 vs. 17.0) for CIDEr. We further verify the effectiveness of the proposed contrastive module on ad keyword generation, and show that our model has potential commercial value.
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.
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.
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.
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
