Related papers: Improving Lexical Embeddings for Robust Question A…
Lexical semantics is concerned with both the multiple senses a word can adopt in different contexts, and the semantic relations that exist between meanings of different words. To investigate them, Contextualized Language Models are a…
Model editing techniques are essential for efficiently updating knowledge in large language models (LLMs). However, the effectiveness of existing approaches degrades in massive editing scenarios, particularly when evaluated with practical…
Self-supervised learned models have been found to be very effective for certain speech tasks such as automatic speech recognition, speaker identification, keyword spotting and others. While the features are undeniably useful in speech…
Learner-item cognitive modeling plays a central role in the web-based online intelligent education system by enabling cognitive diagnosis (CD) across diverse online educational scenarios. Although ID embedding remains the mainstream…
Question answering (QA) systems achieve impressive performance on standard benchmarks like SQuAD, but remain vulnerable to adversarial examples. This project investigates the adversarial robustness of transformer models on the AddSent…
In retrieval-augmented systems, context ranking techniques are commonly employed to reorder the retrieved contexts based on their relevance to a user query. A standard approach is to measure this relevance through the similarity between…
Commonsense knowledge is paramount to enable intelligent systems. Typically, it is characterized as being implicit and ambiguous, hindering thereby the automation of its acquisition. To address these challenges, this paper presents…
Lexical substitution is the task of generating meaningful substitutes for a word in a given textual context. Contextual word embedding models have achieved state-of-the-art results in the lexical substitution task by relying on contextual…
The latest advancements in unsupervised learning of sentence embeddings predominantly involve employing contrastive learning-based (CL-based) fine-tuning over pre-trained language models. In this study, we analyze the latest sentence…
Converting different modalities into general text, serving as input prompts for large language models (LLMs), is a common method to align multimodal models when there is limited pairwise data. This text-centric approach leverages the unique…
``Classical'' word embeddings, such as Word2Vec, have been shown to capture the semantics of words based on their distributional properties. However, their ability to represent the different meanings that a word may have is limited. Such…
Multimodal large language models (MLLMs) have demonstrated great performance on visual question answering (VQA). When it comes to knowledge-based Visual Question Answering (KB-VQA), MLLMs may lack the specialized domain knowledge needed to…
Relating speech to EEG holds considerable importance but is challenging. In this study, a deep convolutional network was employed to extract spatiotemporal features from EEG data. Self-supervised speech representation and contextual text…
Large language models (LLMs) have recently garnered significant interest. With in-context learning, LLMs achieve impressive results in various natural language tasks. However, the application of LLMs to sentence embeddings remains an area…
We experiment with two recent contextualized word embedding methods (ELMo and BERT) in the context of open-domain argument search. For the first time, we show how to leverage the power of contextualized word embeddings to classify and…
Text embedding models have significantly contributed to advancements in natural language processing by adeptly capturing semantic properties of textual data. However, the ability of these models to generalize across a wide range of…
Dense vector representations for sentences made significant progress in recent years as can be seen on sentence similarity tasks. Real-world phrase retrieval applications, on the other hand, still encounter challenges for effective use of…
Embodied Question Answering (EQA) combines visual scene understanding, goal-directed exploration, spatial and temporal reasoning under partial observability. A central challenge is to confine physical search to question-relevant subspaces…
Embodied Question Answering (EQA) is an essential yet challenging task for robot assistants. Large vision-language models (VLMs) have shown promise for EQA, but existing approaches either treat it as static video question answering without…
Reliable question answering with large language models (LLMs) is challenged by hallucinations, fluent but factually incorrect outputs arising from epistemic uncertainty. Existing entropy-based semantic-level uncertainty estimation methods…