Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userSpurious Correlations in Cross-Topic Argument Mining
الارتباطات الزائفة في تعدين الوسيطة عبر الموضوع
182
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
يعمل العمل الحديث في محاولات تعدين الحجة عبر الموضوعات لتعلم النماذج التي تعزز عبر الموضوعات بدلا من الاعتماد فقط على الارتباطات الزائفة داخل الموضوع.نحن ندرس فعالية هذا النهج من خلال تحليل إخراج النماذج ذات المهمة الفردية ومتعدد المهام للتطوير عبر الموضوعات التعدين، من خلال مزيج من تقريبية خطية من حدود قراراتهم، وتجميع الميزات اليدوية، أمثلة التحدي، والاعتبارات عبر المدخلاتكلمات.من المستغرب أن نوضح أن النماذج عبر الموضوعات لا تزال تعتمد في الغالب على ارتباطات زائفة وتعميم فقط داخل مواضيع مرتبطة ارتباطا وثيقا، على سبيل المثال، نموذج مدرب فقط على الكلمات الفئة المغلقة وبعض الكلمات المفتوحة الشائعة تفوقت على حالة منالفن المتبادل نموذج المواضيع المستهدفة البعيدة.
Recent work in cross-topic argument mining attempts to learn models that generalise across topics rather than merely relying on within-topic spurious correlations. We examine the effectiveness of this approach by analysing the output of single-task and multi-task models for cross-topic argument mining, through a combination of linear approximations of their decision boundaries, manual feature grouping, challenge examples, and ablations across the input vocabulary. Surprisingly, we show that cross-topic models still rely mostly on spurious correlations and only generalise within closely related topics, e.g., a model trained only on closed-class words and a few common open-class words outperforms a state-of-the-art cross-topic model on distant target topics.
References used
https://aclanthology.org/
rate research
Read More
Among the most critical limitations of deep learning NLP models are their lack of interpretability, and their reliance on spurious correlations. Prior work proposed various approaches to interpreting the black-box models to unveil the spurious correl
ations, but the research was primarily used in human-computer interaction scenarios. It still remains underexplored whether or how such model interpretations can be used to automatically unlearn'' confounding features. In this work, we propose influence tuning---a procedure that leverages model interpretations to update the model parameters towards a plausible interpretation (rather than an interpretation that relies on spurious patterns in the data) in addition to learning to predict the task labels. We show that in a controlled setup, influence tuning can help deconfounding the model from spurious patterns in data, significantly outperforming baseline methods that use adversarial training.
Following the increasing performance of neural machine translation systems, the paradigm of using automatically translated data for cross-lingual adaptation is now studied in several applicative domains. The capacity to accurately project annotations
remains however an issue for sequence tagging tasks where annotation must be projected with correct spans. Additionally, when the task implies noisy user-generated text, the quality of translation and annotation projection can be affected. In this paper we propose to tackle multilingual sequence tagging with a new span alignment method and apply it to opinion target extraction from customer reviews. We show that provided suitable heuristics, translated data with automatic span-level annotation projection can yield improvements both for cross-lingual adaptation compared to zero-shot transfer, and data augmentation compared to a multilingual baseline.
Rapidly changing social media content calls for robust and generalisable abuse detection models. However, the state-of-the-art supervised models display degraded performance when they are evaluated on abusive comments that differ from the training co
rpus. We investigate if the performance of supervised models for cross-corpora abuse detection can be improved by incorporating additional information from topic models, as the latter can infer the latent topic mixtures from unseen samples. In particular, we combine topical information with representations from a model tuned for classifying abusive comments. Our performance analysis reveals that topic models are able to capture abuse-related topics that can transfer across corpora, and result in improved generalisability.
High-quality arguments are an essential part of decision-making. Automatically predicting the quality of an argument is a complex task that recently got much attention in argument mining. However, the annotation effort for this task is exceptionally
high. Therefore, we test uncertainty-based active learning (AL) methods on two popular argument-strength data sets to estimate whether sample-efficient learning can be enabled. Our extensive empirical evaluation shows that uncertainty-based acquisition functions can not surpass the accuracy reached with the random acquisition on these data sets.
Cross-document event coreference resolution (CDCR) is the task of identifying which event mentions refer to the same events throughout a collection of documents. Annotating CDCR data is an arduous and expensive process, explaining why existing corpor
a are small and lack domain coverage. To overcome this bottleneck, we automatically extract event coreference data from hyperlinks in online news: When referring to a significant real-world event, writers often add a hyperlink to another article covering this event. We demonstrate that collecting hyperlinks which point to the same article(s) produces extensive and high-quality CDCR data and create a corpus of 2M documents and 2.7M silver-standard event mentions called HyperCoref. We evaluate a state-of-the-art system on three CDCR corpora and find that models trained on small subsets of HyperCoref are highly competitive, with performance similar to models trained on gold-standard data. With our work, we free CDCR research from depending on costly human-annotated training data and open up possibilities for research beyond English CDCR, as our data extraction approach can be easily adapted to other languages.
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
