检索结果-内蒙古大学图书馆

Identifying and Adapting Transformer-Components Responsible for Gender Bias in an English language Model 6

学校读者我要写书评

暂无评论

Identifying and Adapting Transformer-Components Responsible ...

6th Workshop on Analyzing and Interpreting Neural Networks for NLP, BlackboxNLP 2023

作者： Chintam, Abhijith Beloch, Rahel Zuidema, Willem Hanna, Michael van der Wal, Oskar Master AI University of Amsterdam Netherlands Pegasystems Amsterdam Netherlands Institute for Logic Language & Computation University of Amsterdam Netherlands

ISBN: (纸本)9798891760523

language models (LMs) exhibit and amplify many types of undesirable biases learned from the training data, including gender bias. However, we lack tools for effectively and efficiently changing this behavior without hurting general language modeling performance. In this paper, we study three methods for identifying causal relations between LM components and particular output: causal mediation analysis, automated circuit discovery and our novel, efficient method called DiffMask+ based on differential masking. We apply the methods to GPT-2 small and the problem of gender bias, and use the discovered sets of components to perform parameter-efficient fine-tuning for bias mitigation. Our results show significant overlap in the identified components (despite huge differences in the computational requirements of the methods) as well as success in mitigating gender bias, with less damage to general language modeling compared to full model fine-tuning. However, our work also underscores the difficulty of defining and measuring bias, and the sensitivity of causal discovery procedures to dataset choice. We hope our work can contribute to more attention for dataset development, and lead to more effective mitigation strategies for other types of bias. ©2023 Association for computational Linguistics.

关键词： computational linguistics

Describing Images Fast and Slow: Quantifying and Predicting the Variation in Human Signals during Visuo-Linguistic Processes

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Takmaz, Ece Pezzelle, Sandro Fernández, Raquel Institute for Logic Language and Computation University of Amsterdam Netherlands

There is an intricate relation between the properties of an image and how humans behave while describing the image. This behavior shows ample variation, as manifested in human signals such as eye movements and when humans start to describe the image. Despite the value of such signals of visuo-linguistic variation, they are virtually disregarded in the training of current pretrained models, which motivates further investigation. Using a corpus of Dutch image descriptions with concurrently collected eye-tracking data, we explore the nature of the variation in visuo-linguistic signals, and find that they correlate with each other. Given this result, we hypothesize that variation stems partly from the properties of the images, and explore whether image representations encoded by pretrained vision encoders can capture such variation. Our results indicate that pretrained models do so to a weak-to-moderate degree, suggesting that the models lack biases about what makes a stimulus complex for humans and what leads to variations in human outputs. Copyright © 2024, The Authors. All rights reserved.

关键词： Eye movements

Not (yet) the whole story: Evaluating Visual Storytelling Requires More than Measuring Coherence, Grounding, and Repetition

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Surikuchi, Aditya K. Fernández, Raquel Pezzelle, Sandro Institute for Logic Language and Computation University of Amsterdam Netherlands

Visual storytelling consists in generating a natural language story given a temporally ordered sequence of images. This task is not only challenging for models, but also very difficult to evaluate with automatic metrics since there is no consensus about what makes a story ‘good’. In this paper, we introduce a novel method that measures story quality in terms of human likeness regarding three key aspects highlighted in previous work: visual grounding, coherence, and repetitiveness. We then use this method to evaluate the stories generated by several models, showing that the foundation model LLaVA obtains the best result, but only slightly so compared to TAPM, a 50-times smaller visual storytelling model. Upgrading the visual and language components of TAPM results in a model that yields competitive performance with a relatively low number of parameters. Finally, we carry out a human evaluation study, whose results suggest that a ‘good’ story may require more than a human-like level of visual grounding, coherence, and repetition. © 2024, CC BY.

关键词： Visual languages

Don’t Buy it! Reassessing the Ad Understanding Abilities of Contrastive Multimodal Models

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Bavaresco, Anna Testoni, Alberto Fernández, Raquel Institute for Logic Language and Computation University of Amsterdam Netherlands

Image-based advertisements are complex multimodal stimuli that often contain unusual visual elements and figurative language. Previous research on automatic ad understanding has reported impressive zero-shot accuracy of contrastive vision-and-language models (VLMs) on an ad-explanation retrieval task. Here, we examine the original task setup and show that contrastive VLMs can solve it by exploiting grounding heuristics. To control for this confound, we introduce TRADE, a new evaluation test set with adversarial grounded explanations. While these explanations look implausible to humans, we show that they "fool" four different contrastive VLMs. Our findings highlight the need for an improved operationalisation of automatic ad understanding that truly evaluates VLMs’ multimodal reasoning abilities. We make our code and TRADE available at https://***/dmg-illc/trade. © 2024, CC BY.

关键词： Visual languages

Asking the Right Question at the Right Time: Human and Model Uncertainty Guidance to Ask Clarification Questions

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Testoni, Alberto Fernández, Raquel Institute for Logic Language and Computation University of Amsterdam Netherlands

Clarification questions are an essential dialogue tool to signal misunderstanding, ambiguities, and under-specification in language use. While humans are able to resolve uncertainty by asking questions since childhood, modern dialogue systems struggle to generate effective questions. To make progress in this direction, in this work we take a collaborative dialogue task as a testbed and study how model uncertainty relates to human uncertainty—an as yet under-explored problem. We show that model uncertainty does not mirror human clarification-seeking behavior, which suggests that using human clarification questions as supervision for deciding when to ask may not be the most effective way to resolve model uncertainty. To address this issue, we propose an approach to generating clarification questions based on model uncertainty estimation, compare it to several alternatives, and show that it leads to significant improvements in terms of task success. Our findings highlight the importance of equipping dialogue systems with the ability to assess their own uncertainty and exploit in interaction. © 2024, CC BY.

关键词： Uncertainty analysis

TAILED U-NET: MULTI-SCALE MUSIC REPRESENTATION LEARNING 23

学校读者我要写书评

暂无评论

TAILED U-NET: MULTI-SCALE MUSIC REPRESENTATION LEARNING

23rd International Society for Music Information Retrieval Conference, ISMIR 2022

作者： Vélez Vásquez, Marcel A. Burgoyne, John Ashley Music Cognition Group Institute for Logic Language and Computation University of Amsterdam Netherlands

ISBN: (纸本)9781732729926

Self-supervised learning has steadily been gaining traction in recent years. In music information retrieval (MIR), one promising recent application of self-supervised learning is the CLMR framework (contrastive learning of musical representations). CLMR has shown good performance, achieving results on par with state-of-the-art end-to-end classification models, but it is strictly an encoding framework. It suffers the characteristic limitation of any encoder that it cannot explicitly combine multi-timescale information, whereas a characteristic feature of human audio perception is that we tend to perceive all frequencies simultaneously. To this end, we propose a generalization of CLMR that learns to extract and explicitly combine representations across different frequency resolutions, which we coin the tailed U-Net (TUNe). TUNe architectures combine multi-timescale information during a decoding phase, similar to U-Net architectures used in computer vision and source separation, but have a tail added to reduce sample-level information to a smaller pre-defined number of representation dimensions. The size of the decoding phase is a hyperparameter, and in the case of a zero-layer decoding phase, TUNe reduces to CLMR. The best TUNe architectures, however, require less training time to match CLMR performance, have superior transfer learning performance, and are competitive with state-of-the-art models even at dramatically reduced dimensionalities. © M.A. Vélez Vásquez and J.A. Burgoyne.

关键词： Decoding

Human-like Linguistic Biases in Neural Speech Models: Phonetic Categorization and Phonotactic Constraints in Wav2Vec2.0

学校读者我要写书评

暂无评论

arXiv 2024年

作者： de Heer Kloots, Marianne Zuidema, Willem Institute for Logic Language and Computation University of Amsterdam Netherlands

What do deep neural speech models know about phonology? Existing work has examined the encoding of individual linguistic units such as phonemes in these models. Here we investigate interactions between units. Inspired by classic experiments on human speech perception, we study how Wav2Vec2 resolves phonotactic constraints. We synthesize sounds on an acoustic continuum between /l/ and /r/ and embed them in controlled contexts where only /l/, only /r/, or neither occur in English. Like humans, Wav2Vec2 models show a bias towards the phonotactically admissable category in processing such ambiguous sounds. Using simple measures to analyze model internals on the level of individual stimuli, we find that this bias emerges in early layers of the model’s Transformer module. This effect is amplified by ASR finetuning but also present in fully self-supervised models. Our approach demonstrates how controlled stimulus designs can help localize specific linguistic knowledge in neural speech models. © 2024, CC BY.

关键词： Speech recognition

Modelling Multimodal Integration in Human Concept Processing with Vision-and-language Models

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Bavaresco, Anna de Heer Kloots, Marianne Pezzelle, Sandro Fernández, Raquel Institute for Logic Language and Computation University of Amsterdam Netherlands

Representations from deep neural networks (DNNs) have proven remarkably predictive of neural activity involved in both visual and linguistic processing. Despite these successes, most studies to date concern unimodal DNNs, encoding either visual or textual input but not both. Yet, there is growing evidence that human meaning representations integrate linguistic and sensory-motor information. Here we investigate whether the integration of multimodal information operated by current vision-and-language DNN models (VLMs) leads to representations that are more aligned with human brain activity than those obtained by language-only and vision-only DNNs. We focus on fMRI responses recorded while participants read concept words in the context of either a full sentence or an accompanying picture. Our results reveal that VLM representations correlate more strongly than language- and vision-only DNNs with activations in brain areas functionally related to language processing. A comparison between different types of visuo-linguistic architectures shows that recent generative VLMs tend to be less brain-aligned than previous architectures with lower performance on downstream applications. Moreover, through an additional analysis comparing brain vs. behavioural alignment across multiple VLMs, we show that – with one remarkable exception – representations that strongly align with behavioural judgments do not correlate highly with brain responses. This indicates that brain similarity does not go hand in hand with behavioural similarity, and vice versa. © 2024, CC BY.

关键词： Deep neural networks

Analyzing the Potential of Linguistic Features for Sign Spotting: A Look at Approximative Features 2

学校读者我要写书评

暂无评论

Analyzing the Potential of Linguistic Features for Sign Spot...

2nd International Workshop on Automatic Translation for Signed and Spoken languages, AT4SSL 2023

作者： Hollain, Natalie Larson, Martha Roelofsen, Floris Institute for Computing and Information Sciences Radboud University Netherlands Center for Language Studies Institute for Computing and Information Sciences Radboud University Netherlands Institute for Logic Language and Computation University of Amsterdam Netherlands

ISBN: (纸本)9789464857184

Sign language processing is the field of research that aims to recognize, retrieve, and spot signs in videos. Various approaches have been developed, varying in whether they use linguistic features and whether they use landmark detection tools or not. Incorporating linguistics holds promise for improving sign language processing in terms of performance, generalizability, and explainability. This paper focuses on the task of sign spotting and aims to expand on the approximative linguistic features that have been used in previous work, and to understand when linguistic features deliver an improvement over landmark features. We detect landmarks with Mediapipe and extract linguistically relevant features from them, including handshape, orientation, location, and movement. We compare a sign spotting model using linguistic features with a model operating on landmarks directly, finding that the approximate linguistic features tested in this paper capture some aspects of signs better than the landmark features, while they are worse for others. © 2023 2023 VFS Handling Qualities Technical Meeting. All rights reserved.

关键词： Feature extraction