paper-with-me

홈 › Papers

Subjective Question Answering: Deciphering the inner workings of Transformers in the realm of subjectivity

2020-06-02 · Lukas Muttenthaler

Understanding subjectivity demands reasoning skills beyond the realm of common knowledge. It requires a machine learning model to process sentiment and to perform opinion mining. In this work, I've exploited a recently released dataset for span-selection Question Answering, namely SubjQA. SubjQA is the first QA dataset that contains questions that ask for subjective opinions corresponding to review paragraphs from six different domains. Hence, to answer these subjective questions, a learner must extract opinions and process sentiment for various domains, and additionally, align the knowledge extracted from a paragraph with the natural language utterances in the corresponding question, which together enhance the difficulty of a QA task. The primary goal of this thesis was to investigate the inner workings (i.e., latent representations) of a Transformer-based architecture to contribute to a better understanding of these not yet well understood "black-box" models. Transformer's hidden representations, concerning the true answer span, are clustered more closely in vector space than those representations corresponding to erroneous predictions. This observation holds across the top three Transformer layers for both objective and subjective questions and generally increases as a function of layer dimensions. Moreover, the probability to achieve a high cosine similarity among hidden representations in latent space concerning the true answer span tokens is significantly higher for correct compared to incorrect answer span predictions. These results have decisive implications for down-stream applications, where it is crucial to know about why a neural network made mistakes, and in which point, in space and time the mistake has happened (e.g., to automatically predict correctness of an answer span prediction without the necessity of labeled data).

📄 PDF Abstract BibTeX arXiv:2006.08342

Code (1)

LukasMut/Subjective_QA 공식 구현 pytorch

Tasks

Opinion MiningQuestion Answering

Methods 이 논문이 사용한 방법론

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Position-Wise Feed-Forward Layer 설명 없음
Residual Connection 설명 없음
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
Multi-Head Attention 설명 없음
Adam 설명 없음
ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…

Similar Papers 제목 키워드 기반

An Interactive Web-Interface for Visualizing the Inner Workings of the Question Answering LSTM

2018-11-01 · EMNLP 2018 11 · Ekaterina Loginova, G{\"u}nter Neumann

We present a visualisation tool which aims to illuminate the inner workings of an LSTM model for question answering. It plots heatmaps of neurons{'} firings and allows a user to check the dependency between neurons and m…

Feature EngineeringMachine TranslationQuestion Answering

Inside the Visual Mind: Neuroscience-Motivated Concept Circuits for Interpreting and Steering Vision Transformers

2026-06-04 · Tang Li, Yanlin Chen, Mengmeng Ma, Xi Peng arxiv

Despite high accuracy, Vision Transformer (ViT) predictions can be driven by spurious cues, raising the need to understand their inner workings before safe deployment. Sparse autoencoders (SAEs) provide a promising lens …

Structured World Representations in Maze-Solving Transformers

2023-12-05 · Michael Igorevich Ivanitskiy, Alex F. Spies, Tilman Räuker, Guillaume Corlouer 외

Transformer models underpin many recent advances in practical machine learning applications, yet understanding their internal behavior continues to elude researchers. Given the size and complexity of these models, formin…

valid

A Primer on the Inner Workings of Transformer-based Language Models

2024-04-30 · Javier Ferrando, Gabriele Sarti, Arianna Bisazza, Marta R. Costa-jussà

The rapid progress of research aimed at interpreting the inner workings of advanced language models has highlighted a need for contextualizing the insights gained from years of work in this area. This primer provides a c…

Decoder

Neural Activation Patterns (NAPs): Visual Explainability of Learned Concepts

2022-06-20 · Alex Bäuerle, Daniel Jönsson, Timo Ropinski

A key to deciphering the inner workings of neural networks is understanding what a model has learned. Promising methods for discovering learned features are based on analyzing activation values, whereby current technique…