Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userEliciting Bias in Question Answering Models through Ambiguity
إظهار التحيز في سؤال الرد النماذج من خلال الغموض
275
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
نماذج الإجابة على الأسئلة (QA) تستخدم أنظمة المسترد والقارئ للإجابة على الأسئلة.يمكن الاعتماد على البيانات التدريبية من قبل أنظمة ضمان الجودة أو تعكس عدم المساواة من خلال ردودهم.يتم تدريب العديد من نماذج QA، مثل تلك الخاصة ب DataSet Squad، على مجموعة فرعية من مقالات ويكيبيديا التي تشفص لتحيزاتها الخاصة وإعادة إنتاج عدم المساواة في العالم الحقيقي.فهم كيفية تأثير البيانات التدريبية على التحيز في أنظمة ضمان الجودة يمكن أن تبلغ الأساليب لتخفيف عدم المساواة.نقوم بتطوير مجموعتين من الأسئلة لأسئلة النطاق المغلقة والفتوة على التوالي، والتي تستخدم أسئلة غامضة لتحقيق نماذج QA للتحيز.نطعم ثلاثة أنظمة ضمان الجودة في التعلم العميق مع مجموعات الأسئلة الخاصة بنا وتقييم الردود على التحيز عبر المقاييس.باستخدام مقاييسنا، نجد أن نماذج QA المجال المفتوحة تضخيم التحيزات أكثر من نظيرهم المغلقة من النطاق واقتراح أن يتحيزات في سطح المسترد بسهولة أكبر بسبب حرية الاختيار أكبر.
Question answering (QA) models use retriever and reader systems to answer questions. Reliance on training data by QA systems can amplify or reflect inequity through their responses. Many QA models, such as those for the SQuAD dataset, are trained and tested on a subset of Wikipedia articles which encode their own biases and also reproduce real-world inequality. Understanding how training data affects bias in QA systems can inform methods to mitigate inequity. We develop two sets of questions for closed and open domain questions respectively, which use ambiguous questions to probe QA models for bias. We feed three deep-learning-based QA systems with our question sets and evaluate responses for bias via the metrics. Using our metrics, we find that open-domain QA models amplify biases more than their closed-domain counterparts and propose that biases in the retriever surface more readily due to greater freedom of choice.
References used
https://aclanthology.org/
rate research
Read More
Current textual question answering (QA) models achieve strong performance on in-domain test sets, but often do so by fitting surface-level patterns, so they fail to generalize to out-of-distribution settings. To make a more robust and understandable
QA system, we model question answering as an alignment problem. We decompose both the question and context into smaller units based on off-the-shelf semantic representations (here, semantic roles), and align the question to a subgraph of the context in order to find the answer. We formulate our model as a structured SVM, with alignment scores computed via BERT, and we can train end-to-end despite using beam search for approximate inference. Our use of explicit alignments allows us to explore a set of constraints with which we can prohibit certain types of bad model behavior arising in cross-domain settings. Furthermore, by investigating differences in scores across different potential answers, we can seek to understand what particular aspects of the input lead the model to choose the answer without relying on post-hoc explanation techniques. We train our model on SQuAD v1.1 and test it on several adversarial and out-of-domain datasets. The results show that our model is more robust than the standard BERT QA model, and constraints derived from alignment scores allow us to effectively trade off coverage and accuracy.
We tackle multi-choice question answering. Acquiring related commonsense knowledge to the question and options facilitates the recognition of the correct answer. However, the current reasoning models suffer from the noises in the retrieved knowledge.
In this paper, we propose a novel encoding method which is able to conduct interception and soft filtering. This contributes to the harvesting and absorption of representative information with less interference from noises. We experiment on CommonsenseQA. Experimental results illustrate that our method yields substantial and consistent improvements compared to the strong Bert, RoBERTa and Albert-based baselines.
Large pre-trained language models (PLMs) have led to great success on various commonsense question answering (QA) tasks in an end-to-end fashion. However, little attention has been paid to what commonsense knowledge is needed to deeply characterize t
hese QA tasks. In this work, we proposed to categorize the semantics needed for these tasks using the SocialIQA as an example. Building upon our labeled social knowledge categories dataset on top of SocialIQA, we further train neural QA models to incorporate such social knowledge categories and relation information from a knowledge base. Unlike previous work, we observe our models with semantic categorizations of social knowledge can achieve comparable performance with a relatively simple model and smaller size compared to other complex approaches.
Question answering (QA) models for reading comprehension have been demonstrated to exploit unintended dataset biases such as question--context lexical overlap. This hinders QA models from generalizing to under-represented samples such as questions wi
th low lexical overlap. Question generation (QG), a method for augmenting QA datasets, can be a solution for such performance degradation if QG can properly debias QA datasets. However, we discover that recent neural QG models are biased towards generating questions with high lexical overlap, which can amplify the dataset bias. Moreover, our analysis reveals that data augmentation with these QG models frequently impairs the performance on questions with low lexical overlap, while improving that on questions with high lexical overlap. To address this problem, we use a synonym replacement-based approach to augment questions with low lexical overlap. We demonstrate that the proposed data augmentation approach is simple yet effective to mitigate the degradation problem with only 70k synthetic examples.
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.
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
