Related papers: Calibrated Seq2seq Models for Efficient and Genera…
We address the problem of \emph{quantification}, a supervised learning task whose goal is, given a class, to estimate the relative frequency (or \emph{prevalence}) of the class in a dataset of unlabelled items. Quantification has several…
Recognizing entities in texts is a central need in many information-seeking scenarios, and indeed, Named Entity Recognition (NER) is arguably one of the most successful examples of a widely adopted NLP task and corresponding NLP technology.…
We analyze the extent to which internal representations of language models (LMs) identify and distinguish mentions of named entities, focusing on the many-to-many correspondence between entities and their mentions. We first formulate two…
Although modern named entity recognition (NER) systems show impressive performance on standard datasets, they perform poorly when presented with noisy data. In particular, capitalization is a strong signal for entities in many languages,…
Explanations in Computer Vision are often desired, but most Deep Neural Networks can only provide saliency maps with questionable faithfulness. Self-Explaining Neural Networks (SENN) extract interpretable concepts with fidelity, diversity,…
Most of the achievements in artificial intelligence so far were accomplished by supervised learning which requires numerous annotated training data and thus costs innumerable manpower for labeling. Unsupervised learning is one of the…
Breaking down the structure of long texts into semantically coherent segments makes the texts more readable and supports downstream applications like summarization and retrieval. Starting from an apparent link between text coherence and…
With the rapid increase in the size of neural networks, model compression has become an important area of research. Quantization is an effective technique at decreasing the model size, memory access, and compute load of large models.…
This work presents a general unsupervised learning method to improve the accuracy of sequence to sequence (seq2seq) models. In our method, the weights of the encoder and decoder of a seq2seq model are initialized with the pretrained weights…
Current systems of fine-grained entity typing use distant supervision in conjunction with existing knowledge bases to assign categories (type labels) to entity mentions. However, the type labels so obtained from knowledge bases are often…
Semantic answer type prediction (SMART) is known to be a useful step towards effective question answering (QA) systems. The SMART task involves predicting the top-$k$ knowledge graph (KG) types for a given natural language question. This is…
Fine-grained Entity Recognition (FgER) is the task of detecting and classifying entity mentions to a large set of types spanning diverse domains such as biomedical, finance and sports. We observe that when the type set spans several…
Recent advances in large vision-language models (VLMs) have shown remarkable progress in solving the text-promptable object counting problem. Representative methods typically specify text prompts with object category information in images.…
Entity extraction is a key technology for obtaining information from massive texts in natural language processing. The further interaction between them does not meet the standards of human reading comprehension, thus limiting the…
Recent progress in semantic segmentation is driven by deep Convolutional Neural Networks and large-scale labeled image datasets. However, data labeling for pixel-wise segmentation is tedious and costly. Moreover, a trained model can only…
Citation plays a pivotal role in determining the associations among research articles. It portrays essential information in indicative, supportive, or contrastive studies. The task of inline citation classification aids in extrapolating…
Named entity recognition (NER) is an important research problem in natural language processing. There are three types of NER tasks, including flat, nested and discontinuous entity recognition. Most previous sequential labeling models are…
Prompt learning is a new paradigm for utilizing pre-trained language models and has achieved great success in many tasks. To adopt prompt learning in the NER task, two kinds of methods have been explored from a pair of symmetric…
Recent work has witnessed a paradigm shift from Seq2Seq to Seq2Edit in the field of text editing, with the aim of addressing the slow autoregressive inference problem posed by the former. Despite promising results, Seq2Edit approaches still…
When generating images from prompts that include specific entities, the model must retain as much entity-specific knowledge as possible. However, the number of entities is almost countless, and new entities emerge; memorizing all of them…