Jennifer Foster
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Jennifer Foster has a total of 45 co-authors. Here are the top co-authors by number of shared publications:
- Joachim Wagner
Dublin City University
9 shared publications Josef van Genabith
4 shared publicationsDasha Bogdanova
3 shared publicationsJohann Roturier
3 shared publicationsPiyush Arora
3 shared publicationsRasoul Kaljahi
3 shared publications
Latest Publications
- Open Access
- 26 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 3975-3984
Graph-Based Video-Language Learning with Multi-Grained Audio-Visual Alignment
Video-language learning has attracted significant attention in the fields of multimedia, computer vision and natural language processing in recent years. One of the key challenges in this area is how to effectively integrate visual and linguistic information to enable machines to understand video content and query information. In this work, we leverage graph-based representations and multi-grained audio-visual alignment to address this challenge. First, our approach starts by transforming video and query inputs into visual-scene graphs and semantic role graphs using a visual-scene parser and semantic role labeler respectively. These graphs are then encoded using graph neural networks to obtain enriched representations and combined to obtain a video-query joint representation that enhances the semantic expressivity of the inputs. Second, to achieve accurate matching of relevant parts of audio and visual features, we propose a multi-grained alignment module that aligns the audio and visual features at multiple scales. This enables us to effectively fuse the audio and visual information in a way that is consistent with the semantic-level information captured by the graph-based representations. Experiments on five representative datasets collected for Video Retrieval and Video Question Answering tasks show that our approach outperforms the literature on several metrics. Our extensive ablation studies demonstrate the effectiveness of graph-based representation and multi-grained audio-visual alignment.
- 26 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 3975-3984
Open AccessGraph-Based Video-Language Learning with Multi-Grained Audio-Visual Alignment
Video-language learning has attracted significant attention in the fields of multimedia, computer vision and natural language processing in recent years. One of the key challenges in this area is how to effectively integrate visual and linguistic information to enable machines to understand video content and query information. In this work, we leverage graph-based representations and multi-grained audio-visual alignment to address this challenge. First, our approach starts by transforming video and query inputs into visual-scene graphs and semantic role graphs using a visual-scene parser and semantic role labeler respectively. These graphs are then encoded using graph neural networks to obtain enriched representations and combined to obtain a video-query joint representation that enhances the semantic expressivity of the inputs. Second, to achieve accurate matching of relevant parts of audio and visual features, we propose a multi-grained alignment module that aligns the audio and visual features at multiple scales. This enables us to effectively fuse the audio and visual information in a way that is consistent with the semantic-level information captured by the graph-based representations. Experiments on five representative datasets collected for Video Retrieval and Video Question Answering tasks show that our approach outperforms the literature on several metrics. Our extensive ablation studies demonstrate the effectiveness of graph-based representation and multi-grained audio-visual alignment.
- Open Access
- 13 April 2023
- Published by Elsevier in Journal of Pain and Symptom Management
- Vol. 65 (5) , e592
End-of-Life Outcomes in Children with Relapsed/Refractory Solid Tumors: A Single-Center Study (Sch425)
- 13 April 2023
- Published by Elsevier in Journal of Pain and Symptom Management
- Vol. 65 (5) , e592
Open AccessEnd-of-Life Outcomes in Children with Relapsed/Refractory Solid Tumors: A Single-Center Study (Sch425)
- Open Access
- 1 January 2023
- Published by Association for Computational Linguistics (ACL)
- p. 12751-12769
Investigating the Saliency of Sentiment Expressions in Aspect-Based Sentiment Analysis
Joachim Wagner, Jennifer Foster. Findings of the Association for Computational Linguistics: ACL 2023. 2023.
- 1 January 2023
- Published by Association for Computational Linguistics (ACL)
- p. 12751-12769
Open AccessInvestigating the Saliency of Sentiment Expressions in Aspect-Based Sentiment Analysis
Joachim Wagner, Jennifer Foster. Findings of the Association for Computational Linguistics: ACL 2023. 2023.
- Open Access
- 1 January 2023
- Published by Association for Computational Linguistics (ACL)
- p. 183-189
Is a Video worth n n Images? A Highly Efficient Approach to Transformer-based Video Question Answering
Chenyang Lyu, Tianbo Ji, Yvette Graham, Jennifer Foster. Proceedings of The Fourth Workshop on Simple and Efficient Natural Language Processing (SustaiNLP). 2023.
- 1 January 2023
- Published by Association for Computational Linguistics (ACL)
- p. 183-189
Open AccessIs a Video worth n n Images? A Highly Efficient Approach to Transformer-based Video Question Answering
Chenyang Lyu, Tianbo Ji, Yvette Graham, Jennifer Foster. Proceedings of The Fourth Workshop on Simple and Efficient Natural Language Processing (SustaiNLP). 2023.
- Open Access
Extending the Scope of Out-of-Domain: Examining QA models in multiple subdomains
Past works that investigate out-of-domain performance of QA systems have mainly focused on general domains (e.g. news domain, wikipedia domain), underestimating the importance of subdomains defined by the internal characteristics of QA datasets. In this paper, we extend the scope of "out-of-domain" by splitting QA examples into different subdomains according to their several internal characteristics including question type, text length, answer position. We then examine the performance of QA systems trained on the data from different subdomains. Experimental results show that the performance of QA systems can be significantly reduced when the train data and test data come from different subdomains. These results question the generalizability of current QA systems in multiple subdomains, suggesting the need to combat the bias introduced by the internal characteristics of QA datasets.
Open AccessExtending the Scope of Out-of-Domain: Examining QA models in multiple subdomains
Past works that investigate out-of-domain performance of QA systems have mainly focused on general domains (e.g. news domain, wikipedia domain), underestimating the importance of subdomains defined by the internal characteristics of QA datasets. In this paper, we extend the scope of "out-of-domain" by splitting QA examples into different subdomains according to their several internal characteristics including question type, text length, answer position. We then examine the performance of QA systems trained on the data from different subdomains. Experimental results show that the performance of QA systems can be significantly reduced when the train data and test data come from different subdomains. These results question the generalizability of current QA systems in multiple subdomains, suggesting the need to combat the bias introduced by the internal characteristics of QA datasets.
- Open Access
Any-gram Kernels for Sentence Classification: A Sentiment Analysis Case Study
Any-gram kernels are a flexible and efficient way to employ bag-of-n-gram features when learning from textual data. They are also compatible with the use of word embeddings so that word similarities can be accounted for. While the original any-gram kernels are implemented on top of tree kernels, we propose a new approach which is independent of tree kernels and is more efficient. We also propose a more effective way to make use of word embeddings than the original any-gram formulation. When applied to the task of sentiment classification, our new formulation achieves significantly better performance.
Open AccessAny-gram Kernels for Sentence Classification: A Sentiment Analysis Case Study
Any-gram kernels are a flexible and efficient way to employ bag-of-n-gram features when learning from textual data. They are also compatible with the use of word embeddings so that word similarities can be accounted for. While the original any-gram kernels are implemented on top of tree kernels, we propose a new approach which is independent of tree kernels and is more efficient. We also propose a more effective way to make use of word embeddings than the original any-gram formulation. When applied to the task of sentiment classification, our new formulation achieves significantly better performance.
- 17 August 2017
- Published by Springer Nature
- p. 97-103
Query Expansion for Sentence Retrieval Using Pseudo Relevance Feedback and Word Embedding
- 17 August 2017
- Published by Springer Nature
- p. 97-103
Query Expansion for Sentence Retrieval Using Pseudo Relevance Feedback and Word Embedding
- Open Access
- 1 January 2017
- Published by Association for Computational Linguistics (ACL)
If You Can't Beat Them Join Them: Handcrafted Features Complement Neural Nets for Non-Factoid Answer Reranking
- 1 January 2017
- Published by Association for Computational Linguistics (ACL)
Open AccessIf You Can't Beat Them Join Them: Handcrafted Features Complement Neural Nets for Non-Factoid Answer Reranking
- Open Access
- 1 January 2016
- Published by Association for Computational Linguistics (ACL)
- p. 1290-1295
This is how we do it: Answer Reranking for Open-domain How Questions with Paragraph Vectors and Minimal Feature Engineering
- 1 January 2016
- Published by Association for Computational Linguistics (ACL)
- p. 1290-1295
Open AccessThis is how we do it: Answer Reranking for Open-domain How Questions with Paragraph Vectors and Minimal Feature Engineering