Related papers: Cognitive-aware Short-text Understanding for Infer…
Concept Bottleneck Models (CBMs) are regarded as inherently interpretable because they first predict a set of human-defined concepts which are used to predict a task label. For inherent interpretability to be fully realised, and ensure…
Systems like ChatGPT and Claude assist billions through proactive dialogue-offering unsolicited, task-relevant information. Drawing on Cognitive Load Theory, we study how cognitive load shapes performance in AI-assisted knowledge work. We…
The effectiveness of a language model is influenced by its token representations, which must encode contextual information and handle the same word form having a plurality of meanings (polysemy). Currently, none of the common language…
There are two types of information in each handwritten word image: explicit information which can be easily read or derived directly, such as lexical content or word length, and implicit attributes such as the author's identity. Whether…
The multimedia communications with texts and images are popular on social media. However, limited studies concern how images are structured with texts to form coherent meanings in human cognition. To fill in the gap, we present a novel…
The paraphrase identification task involves measuring semantic similarity between two short sentences. It is a tricky task, and multilingual paraphrase identification is even more challenging. In this work, we train a bi-encoder model in a…
Content-dense news report important factual information about an event in direct, succinct manner. Information seeking applications such as information extraction, question answering and summarization normally assume all text they deal with…
Large language models (LLMs) achieved remarkable performance across various tasks. However, they face challenges in managing long documents and extended conversations, due to significantly increased computational requirements, both in…
To advance argumentative stance prediction as a multimodal problem, the First Shared Task in Multimodal Argument Mining hosted stance prediction in crucial social topics of gun control and abortion. Our exploratory study attempts to…
Despite substantial interest in applications of neural networks to information retrieval, neural ranking models have only been applied to standard ad hoc retrieval tasks over web pages and newswire documents. This paper proposes MP-HCNN…
Contemporary predictive models are hard to interpret as their deep nets exploit numerous complex relations between input elements. This work suggests a theoretical framework for model interpretability by measuring the contribution of…
Neural networks have achieved remarkable success across various fields. However, the lack of interpretability limits their practical use, particularly in critical decision-making scenarios. Post-hoc interpretability, which provides…
Concept-based Models are neural networks that learn a concept extractor to map inputs to high-level concepts and an inference layer to translate these into predictions. Ensuring these modules produce interpretable concepts and behave…
Despite significant improvements in enhancing the quality of translation, context-aware machine translation (MT) models underperform in many cases. One of the main reasons is that they fail to utilize the correct features from context when…
In this paper, we aim to learn associations between visual attributes of fonts and the verbal context of the texts they are typically applied to. Compared to related work leveraging the surrounding visual context, we choose to focus only on…
Person-job fit is an essential part of online recruitment platforms in serving various downstream applications like Job Search and Candidate Recommendation. Recently, pretrained large language models have further enhanced the effectiveness…
Despite large-scale pre-trained language models have achieved striking results for text classificaion, recent work has raised concerns about the challenge of shortcut learning. In general, a keyword is regarded as a shortcut if it creates a…
We compare sequential fine-tuning with a model for multi-task learning in the context where we are interested in boosting performance on two tasks, one of which depends on the other. We test these models on the FigLang2022 shared task which…
Stance detection determines whether the author of a piece of text is in favor of, against, or neutral towards a specified target, and can be used to gain valuable insights into social media. The ubiquitous indirect referral of targets makes…
When language models answer open-ended problems, they implicitly make hidden decisions that shape their outputs, leaving users with uncontextualized answers rather than a working map of the problem; drawing on multiverse analysis from…