相关论文: Label Confidence Weighted Learning for Target-leve…

We extend our previous work on Inductive Conformal Prediction (ICP) for multi-label text classification and present a novel approach for addressing the computational inefficiency of the Label Powerset (LP) ICP, arrising when dealing with a…

Dynamic evaluation of language models (LMs) adapts model parameters at test time using gradient information from previous tokens and substantially improves LM performance. However, it requires over 3x more compute than standard inference.…

Curriculum learning and self-paced learning are the training strategies that gradually feed the samples from easy to more complex. They have captivated increasing attention due to their excellent performance in robotic vision. Most recent…

This paper presents a novel training method, Conditional Masked Language Modeling (CMLM), to effectively learn sentence representations on large scale unlabeled corpora. CMLM integrates sentence representation learning into MLM training by…

We introduce a method for efficient multi-label text classification with large language models (LLMs), built on reformulating classification tasks as sequences of dichotomic (yes/no) decisions. Instead of generating all labels in a single…

Representing a true label as a one-hot vector is a common practice in training text classification models. However, the one-hot representation may not adequately reflect the relation between the instances and labels, as labels are often not…

There is a family of label modification approaches including self and non-self label correction (LC), and output regularisation. They are widely used for training robust deep neural networks (DNNs), but have not been mathematically and…

Hallucination remains a major challenge for the safe and trustworthy deployment of large language models (LLMs) in factual content generation. Prior work has explored confidence estimation as an effective approach to hallucination…

Linguistic sequence labeling is a general modeling approach that encompasses a variety of problems, such as part-of-speech tagging and named entity recognition. Recent advances in neural networks (NNs) make it possible to build reliable…

Lexical normalisation (LN) is the process of correcting each word in a dataset to its canonical form so that it may be more easily and more accurately analysed. Most lexical normalisation systems operate at the character-level, while…

Sentence simplification aims to make sentences easier to read and understand. Most recent approaches draw on insights from machine translation to learn simplification rewrites from monolingual corpora of complex and simple sentences. We…

Automatic evaluation for sentence simplification remains a challenging problem. Most popular evaluation metrics require multiple high-quality references -- something not readily available for simplification -- which makes it difficult to…

Neural attention, especially the self-attention made popular by the Transformer, has become the workhorse of state-of-the-art natural language processing (NLP) models. Very recent work suggests that the self-attention in the Transformer…

Sentence scoring aims at measuring the likelihood score of a sentence and is widely used in many natural language processing scenarios, like reranking, which is to select the best sentence from multiple candidates. Previous works on…

Learning from implicit feedback has become the standard paradigm for modern recommender systems. However, this setting is fraught with the persistent challenge of false negatives, where unobserved user-item interactions are not necessarily…

The evaluation of cross-lingual semantic search models is often limited to existing datasets from tasks such as information retrieval and semantic textual similarity. We introduce Cross-Lingual Semantic Discrimination (CLSD), a lightweight…

Large Language Models (LLMs) have achieved remarkable advancements in reasoning capabilities empowered by Reinforcement Learning with Verifiable Rewards (RLVR). Nonetheless, RLVR intrinsically relies on ground-truth labels for reward…

Training deep neural networks requires massive amounts of training data, but for many tasks only limited labeled data is available. This makes weak supervision attractive, using weak or noisy signals like the output of heuristic methods or…

In self-supervised learning for speaker recognition, pseudo labels are useful as the supervision signals. It is a known fact that a speaker recognition model doesn't always benefit from pseudo labels due to their unreliability. In this…

Large Language Models (LLMs) have the impressive ability to perform in-context learning (ICL) from only a few examples, but the success of ICL varies widely from task to task. Thus, it is important to quickly determine whether ICL is…