1 |
How does the pre-training objective affect what large language models learn about linguistic properties? ...
|
|
|
|
BASE
|
|
Show details
|
|
2 |
Automatic Identification and Classification of Bragging in Social Media ...
|
|
|
|
BASE
|
|
Show details
|
|
5 |
Translation Error Detection as Rationale Extraction ...
|
|
|
|
Abstract:
Recent Quality Estimation (QE) models based on multilingual pre-trained representations have achieved very competitive results when predicting the overall quality of translated sentences. Predicting translation errors, i.e. detecting specifically which words are incorrect, is a more challenging task, especially with limited amounts of training data. We hypothesize that, not unlike humans, successful QE models rely on translation errors to predict overall sentence quality. By exploring a set of feature attribution methods that assign relevance scores to the inputs to explain model predictions, we study the behaviour of state-of-the-art sentence-level QE models and show that explanations (i.e. rationales) extracted from these models can indeed be used to detect translation errors. We therefore (i) introduce a novel semi-supervised method for word-level QE and (ii) propose to use the QE task as a new benchmark for evaluating the plausibility of feature attribution, i.e. how interpretable model explanations are ...
|
|
Keyword:
Computation and Language cs.CL; FOS Computer and information sciences
|
|
URL: https://arxiv.org/abs/2108.12197 https://dx.doi.org/10.48550/arxiv.2108.12197
|
|
BASE
|
|
Hide details
|
|
7 |
Frustratingly Simple Pretraining Alternatives to Masked Language Modeling ...
|
|
|
|
BASE
|
|
Show details
|
|
9 |
Improving the Faithfulness of Attention-based Explanations with Task-specific Information for Text Classification ...
|
|
|
|
BASE
|
|
Show details
|
|
10 |
Enjoy the Salience: Towards Better Transformer-based Faithful Explanations with Word Salience ...
|
|
|
|
BASE
|
|
Show details
|
|
13 |
In Factuality: Efficient Integration of Relevant Facts for Visual Question Answering ...
|
|
|
|
BASE
|
|
Show details
|
|
14 |
Frustratingly Simple Pretraining Alternatives to Masked Language Modeling ...
|
|
|
|
BASE
|
|
Show details
|
|
16 |
Machine Extraction of Tax Laws from Legislative Texts
|
|
|
|
In: Proceedings of the Natural Legal Language Processing Workshop 2021 (2021)
|
|
BASE
|
|
Show details
|
|
17 |
Point-of-Interest Type Prediction using Text and Images ...
|
|
|
|
BASE
|
|
Show details
|
|
18 |
Point-of-Interest Type Prediction using Text and Images ...
|
|
|
|
BASE
|
|
Show details
|
|
19 |
An Empirical Study on Leveraging Position Embeddings for Target-oriented Opinion Words Extraction ...
|
|
|
|
BASE
|
|
Show details
|
|
|
|