Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userDetect and Perturb: Neutral Rewriting of Biased and Sensitive Text via Gradient-based Decoding
الكشف والاضطرب: إعادة كتابة محايدة للنص المتحيز والحساسة عبر فك التشفير المستندة إلى التدرج
262
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
اللغة المكتوبة تحمل تحيزات صريحة وتضيعة يمكن أن تصرفت عن إشارات ذات مغزى. على سبيل المثال، قد تصف خطابات المرجعية المرشحين الذكور والإناث بشكل مختلف، أو قد تكشف أسلوب الكتابة الخاصة بهم بشكل غير مباشر عن الخصائص الديموغرافية. في أحسن الأحوال، يصرف مثل هذه التحيزات عن المحتوى المجدي للنص؛ في أسوأ الأحوال يمكن أن تؤدي إلى نتائج غير عادلة. نحن نبحث في تحدي إعادة توليد جمل مدخلات لتحييد "السمات الحساسة" مع الحفاظ على المعنى الدلالي للنص الأصلي (E.G. هو المرشح المؤهل؟). نقترح إطار إعادة كتابة واستنادا في التدرج، والكشف عن وإقلاده لتحييد (DEPEN)، الذي يكتشف أولا مكونات حساسة ويخفيهن من أجل التجديد، ثم يزعج نموذج الجيل عند فك تشفير الوقت تحت قيد تحييد يدفع التوزيع (المتوقع) سمات نحو توزيع موحد. تظهر تجاربنا في سيناريوهات مختلفة أن DEPEN يمكن أن تجدد البدائل الطوفية محايدة في السمة الحساسة مع الحفاظ على دلالات السمات الأخرى.
Written language carries explicit and implicit biases that can distract from meaningful signals. For example, letters of reference may describe male and female candidates differently, or their writing style may indirectly reveal demographic characteristics. At best, such biases distract from the meaningful content of the text; at worst they can lead to unfair outcomes. We investigate the challenge of re-generating input sentences to neutralize' sensitive attributes while maintaining the semantic meaning of the original text (e.g. is the candidate qualified?). We propose a gradient-based rewriting framework, Detect and Perturb to Neutralize (DEPEN), that first detects sensitive components and masks them for regeneration, then perturbs the generation model at decoding time under a neutralizing constraint that pushes the (predicted) distribution of sensitive attributes towards a uniform distribution. Our experiments in two different scenarios show that DEPEN can regenerate fluent alternatives that are neutral in the sensitive attribute while maintaining the semantics of other attributes.
References used
https://aclanthology.org/
rate research
Read More
We propose the first general-purpose gradient-based adversarial attack against transformer models. Instead of searching for a single adversarial example, we search for a distribution of adversarial examples parameterized by a continuous-valued matrix
, hence enabling gradient-based optimization. We empirically demonstrate that our white-box attack attains state-of-the-art attack performance on a variety of natural language tasks, outperforming prior work in terms of adversarial success rate with matching imperceptibility as per automated and human evaluation. Furthermore, we show that a powerful black-box transfer attack, enabled by sampling from the adversarial distribution, matches or exceeds existing methods, while only requiring hard-label outputs.
Query rewrite (QR) is an emerging component in conversational AI systems, reducing user defect. User defect is caused by various reasons, such as errors in the spoken dialogue system, users' slips of the tongue or their abridged language. Many of the
user defects stem from personalized factors, such as user's speech pattern, dialect, or preferences. In this work, we propose a personalized search-based QR framework, which focuses on automatic reduction of user defect. We build a personalized index for each user, which encompasses diverse affinity layers to reflect personal preferences for each user in the conversational AI. Our personalized QR system contains retrieval and ranking layers. Supported by user feedback based learning, training our models does not require hand-annotated data. Experiments on personalized test set showed that our personalized QR system is able to correct systematic and user errors by utilizing phonetic and semantic inputs.
The dominant paradigm for semantic parsing in recent years is to formulate parsing as a sequence-to-sequence task, generating predictions with auto-regressive sequence decoders. In this work, we explore an alternative paradigm. We formulate semantic
parsing as a dependency parsing task, applying graph-based decoding techniques developed for syntactic parsing. We compare various decoding techniques given the same pre-trained Transformer encoder on the TOP dataset, including settings where training data is limited or contains only partially-annotated examples. We find that our graph-based approach is competitive with sequence decoders on the standard setting, and offers significant improvements in data efficiency and settings where partially-annotated data is available.
We introduce a new dataset for Question Rewriting in Conversational Context (QReCC), which contains 14K conversations with 80K question-answer pairs. The task in QReCC is to find answers to conversational questions within a collection of 10M web page
s (split into 54M passages). Answers to questions in the same conversation may be distributed across several web pages. QReCC provides annotations that allow us to train and evaluate individual subtasks of question rewriting, passage retrieval and reading comprehension required for the end-to-end conversational question answering (QA) task. We report the effectiveness of a strong baseline approach that combines the state-of-the-art model for question rewriting, and competitive models for open-domain QA. Our results set the first baseline for the QReCC dataset with F1 of 19.10, compared to the human upper bound of 75.45, indicating the difficulty of the setup and a large room for improvement.
Scheduled sampling is widely used to mitigate the exposure bias problem for neural machine translation. Its core motivation is to simulate the inference scene during training by replacing ground-truth tokens with predicted tokens, thus bridging the g
ap between training and inference. However, vanilla scheduled sampling is merely based on training steps and equally treats all decoding steps. Namely, it simulates an inference scene with uniform error rates, which disobeys the real inference scene, where larger decoding steps usually have higher error rates due to error accumulations. To alleviate the above discrepancy, we propose scheduled sampling methods based on decoding steps, increasing the selection chance of predicted tokens with the growth of decoding steps. Consequently, we can more realistically simulate the inference scene during training, thus better bridging the gap between training and inference. Moreover, we investigate scheduled sampling based on both training steps and decoding steps for further improvements. Experimentally, our approaches significantly outperform the Transformer baseline and vanilla scheduled sampling on three large-scale WMT tasks. Additionally, our approaches also generalize well to the text summarization task on two popular benchmarks.
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
