Related papers: Context Enhanced Short Text Matching using Clickth…
Most existing large language models (LLMs) are expensive to adapt after deployment, especially when a task requires newly produced information or niche domain knowledge. Recent work has shown that, by manipulating and optimizing their…
Automatic translation systems offer a powerful solution to bridge language barriers in scenarios where participants do not share a common language. However, these systems can introduce errors leading to misunderstandings and conversation…
Search engines leverage knowledge to improve information access. In order to effectively leverage knowledge, search engines should account for context, i.e., information about the user and query. In this thesis, we aim to support search…
In Machine Translation, considering the document as a whole can help to resolve ambiguities and inconsistencies. In this paper, we propose a simple yet promising approach to add contextual information in Neural Machine Translation. We…
An important, yet largely unstudied, problem in student data analysis is to detect misconceptions from students' responses to open-response questions. Misconception detection enables instructors to deliver more targeted feedback on the…
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…
Multiple-choice reading and listening comprehension tests are an important part of language assessment. Content creators for standard educational tests need to carefully curate questions that assess the comprehension abilities of candidates…
In this paper, we re-examine the task of cross-modal clip-sentence retrieval, where the clip is part of a longer untrimmed video. When the clip is short or visually ambiguous, knowledge of its local temporal context (i.e. surrounding video…
Document-level neural machine translation has yielded attractive improvements. However, majority of existing methods roughly use all context sentences in a fixed scope. They neglect the fact that different source sentences need different…
Open-domain multi-turn conversations mainly have three features, which are hierarchical semantic structure, redundant information, and long-term dependency. Grounded on these, selecting relevant context becomes a challenge step for…
Constituting highly informative network embeddings is an important tool for network analysis. It encodes network topology, along with other useful side information, into low-dimensional node-based feature representations that can be…
Context matters! Nevertheless, there has not been much research in exploiting contextual information in deep neural networks. For most part, the entire usage of contextual information has been limited to recurrent neural networks. Attention…
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…
Text generation system has made massive promising progress contributed by deep learning techniques and has been widely applied in our life. However, existing end-to-end neural models suffer from the problem of tending to generate…
Images with visual and scene text content are ubiquitous in everyday life. However, current image interpretation systems are mostly limited to using only the visual features, neglecting to leverage the scene text content. In this paper, we…
Recent advances in Named Entity Recognition (NER) show that document-level contexts can significantly improve model performance. In many application scenarios, however, such contexts are not available. In this paper, we propose to find…
Long text brings a big challenge to semantic matching due to their complicated semantic and syntactic structures. To tackle the challenge, we consider using prior knowledge to help identify useful information and filter out noise to…
Text classification must sometimes be applied in a low-resource language with no labeled training data. However, training data may be available in a related language. We investigate whether character-level knowledge transfer from a related…
Foundation Models (FMs) trained on Electronic Health Records (EHRs) have achieved state-of-the-art results on numerous clinical prediction tasks. However, most existing EHR FMs have context windows of <1k tokens. This prevents them from…
This study proposes a text classification algorithm based on large language models, aiming to address the limitations of traditional methods in capturing long-range dependencies, understanding contextual semantics, and handling class…