相关论文: Modeling Context in Answer Sentence Selection Syst…

This paper explores the impact of context selection on the efficiency of Large Language Models (LLMs) in generating Artificial Intelligence (AI) research leaderboards, a task defined as the extraction of (Task, Dataset, Metric, Score)…

The recent advance in neural network architecture and training algorithms have shown the effectiveness of representation learning. The neural network-based models generate better representation than the traditional ones. They have the…

Retrieval-augmented generation supports language models to strengthen their factual groundings by providing external contexts. However, language models often face challenges when given extensive information, diminishing their effectiveness…

This paper delves into the challenging task of Active Speaker Detection (ASD), where the system needs to determine in real-time whether a person is speaking or not in a series of video frames. While previous works have made significant…

Large Language Models (LLMs) often experience performance degradation during long-running interactions due to increasing context length, memory saturation, and computational overhead. This paper presents an adaptive context compression…

We present Twin Answer Sentences Attack (TASA), an adversarial attack method for question answering (QA) models that produces fluent and grammatical adversarial contexts while maintaining gold answers. Despite phenomenal progress on general…

Sequence-to-Sequence (S2S) models have achieved remarkable success on various text generation tasks. However, learning complex structures with S2S models remains challenging as external neural modules and additional lexicons are often…

In this work we propose a simple and efficient framework for learning sentence representations from unlabelled data. Drawing inspiration from the distributional hypothesis and recent work on learning sentence representations, we reformulate…

Ever since the successful application of sequence to sequence learning for neural machine translation systems, interest has surged in its applicability towards language generation in other problem domains. Recent work has investigated the…

Semantic parsing using sequence-to-sequence models allows parsing of deeper representations compared to traditional word tagging based models. In spite of these advantages, widespread adoption of these models for real-time conversational…

Topic segmentation is important in understanding scientific documents since it can not only provide better readability but also facilitate downstream tasks such as information retrieval and question answering by creating appropriate…

We explore context representation learning methods in neural-based models for dialog act classification. We propose and compare extensively different methods which combine recurrent neural network architectures and attention mechanisms…

Answer sentence selection (AS2) modeling requires annotated data, i.e., hand-labeled question-answer pairs. We present a strategy to collect weakly supervised answers for a question based on its reference to improve AS2 modeling.…

Second language acquisition (SLA) modeling is to predict whether second language learners could correctly answer the questions according to what they have learned. It is a fundamental building block of the personalized learning system and…

Retrieval-augmented generation (RAG) and long-context language models (LCLMs) both address context limitations of LLMs in open-domain question answering (QA). However, optimal external context to retrieve remains an open problem: fixing the…

This paper addresses the limitations of large language models in understanding long-term context. It proposes a model architecture equipped with a long-term memory mechanism to improve the retention and retrieval of semantic information…

This thesis tackles the problem of learning efficient representations of complex, structured data with a natural application to web page and element classification. We hypothesise that the context around the element inside the web page is…

End-to-end modeling (E2E) of automatic speech recognition (ASR) blends all the components of a traditional speech recognition system into a unified model. Although it simplifies training and decoding pipelines, the unified model is hard to…

We propose a new architecture for adapting a sentence-level sequence-to-sequence transformer by incorporating multiple pretrained document context signals and assess the impact on translation performance of (1) different pretraining…

End-to-end (E2E) systems for automatic speech recognition (ASR), such as RNN Transducer (RNN-T) and Listen-Attend-Spell (LAS) blend the individual components of a traditional hybrid ASR system - acoustic model, language model, pronunciation…