相关论文: LLM-Guided Semantic Bootstrapping for Interpretabl…

Tsetlin Machine (TM) is an interpretable pattern recognition algorithm based on propositional logic, which has demonstrated competitive performance in many Natural Language Processing (NLP) tasks, including sentiment analysis, text…

Contextual word embeddings obtained from pre-trained language model (PLM) have proven effective for various natural language processing tasks at the word level. However, interpreting the hidden aspects within embeddings, such as syntax and…

Fine-tuning Large Language Models (LLMs) is now a common approach for text classification in a wide range of applications. When labeled documents are scarce, active learning helps save annotation efforts but requires retraining of massive…

Recently, BERT has become an essential ingredient of various NLP deep models due to its effectiveness and universal-usability. However, the online deployment of BERT is often blocked by its large-scale parameters and high computational…

How does the input segmentation of pretrained language models (PLMs) affect their interpretations of complex words? We present the first study investigating this question, taking BERT as the example PLM and focusing on its semantic…

Black-box deep neural networks excel in text classification, yet their application in high-stakes domains is hindered by their lack of interpretability. To address this, we propose Text Bottleneck Models (TBM), an intrinsically…

Knowledge Tracing (KT) models students' evolving knowledge states to predict future performance, serving as a foundation for personalized education. While traditional deep learning models achieve high accuracy, they often lack…

Prompting robots with natural language (NL) has largely been studied as what task to execute (goal selection, skill sequencing) rather than how to execute that task safely and efficiently in semantically rich, human-centric spaces. We…

Despite cross-lingual generalization demonstrated by pre-trained multilingual models, the translate-train paradigm of transferring English datasets across multiple languages remains to be a key mechanism for training task-specific…

Large Transformer-based language models such as BERT have led to broad performance improvements on many NLP tasks. Domain-specific variants of these models have demonstrated excellent performance on a variety of specialised tasks. In legal…

Visual storytelling is a creative and challenging task, aiming to automatically generate a story-like description for a sequence of images. The descriptions generated by previous visual storytelling approaches lack coherence because they…

We propose a lightly-supervised approach for information extraction, in particular named entity classification, which combines the benefits of traditional bootstrapping, i.e., use of limited annotations and interpretability of extraction…

Building conversational speech recognition systems for new languages is constrained by the availability of utterances that capture user-device interactions. Data collection is both expensive and limited by the speed of manual transcription.…

For both human readers and pre-trained language models (PrLMs), lexical diversity may lead to confusion and inaccuracy when understanding the underlying semantic meanings of given sentences. By substituting complex words with simple…

Pre-trained Language Models (PLMs) have been widely used in various natural language processing (NLP) tasks, owing to their powerful text representations trained on large-scale corpora. In this paper, we propose a new PLM called PERT for…

Trained on the large corpus, pre-trained language models (PLMs) can capture different levels of concepts in context and hence generate universal language representations. They can benefit multiple downstream natural language processing…

Recent progress in semantic parsing scarcely considers languages other than English but professional translation can be prohibitively expensive. We adapt a semantic parser trained on a single language, such as English, to new languages and…

End-to-end Spoken Language Understanding (SLU) is proposed to infer the semantic meaning directly from audio features without intermediate text representation. Although the acoustic model component of an end-to-end SLU system can be…

Long context reasoning in large language models (LLMs) has demonstrated enhancement of their cognitive capabilities via chain-of-thought (CoT) inference. Training such models is usually done via reinforcement learning with verifiable…

Pretrained language models (PLMs) form the basis of most state-of-the-art NLP technologies. Nevertheless, they are essentially black boxes: Humans do not have a clear understanding of what knowledge is encoded in different parts of the…