Related papers: SLATE: A Sequence Labeling Approach for Task Extra…
Slot filling and intent detection are two fundamental tasks in the field of natural language understanding. Due to the strong correlation between these two tasks, previous studies make efforts on modeling them with multi-task learning or…
Keyphrases are capable of providing semantic metadata characterizing documents and producing an overview of the content of a document. Since keyphrase extraction is able to facilitate the management, categorization, and retrieval of…
Automating table extraction (TE) from business documents is critical for industrial workflows but remains challenging due to sparse annotations and error-prone multi-stage pipelines. While semi-supervised learning (SSL) can leverage…
Segmenting text into fine-grained units of meaning is important to a wide range of NLP applications. The default approach of segmenting text into sentences is often insufficient, especially since sentences are usually complex enough to…
Instance segmentation methods often require costly per-pixel labels. We propose a method that only requires point-level annotations. During training, the model only has access to a single pixel label per object, yet the task is to output…
Sentence embedding tasks are important in natural language processing (NLP), but improving their performance while keeping them reliable is still hard. This paper presents a framework that combines pseudo-label generation and model ensemble…
Training high-quality instance segmentation models requires an abundance of labeled images with instance masks and classifications, which is often expensive to procure. Active learning addresses this challenge by striving for optimum…
Extracting structured information from HTML documents is a long-studied problem with a broad range of applications, including knowledge base construction, faceted search, and personalized recommendation. Prior works rely on a few…
Standard evaluation in NLP typically indicates that system A is better on average than system B, but it provides little info on how to improve performance and, what is worse, it should not come as a surprise if B ends up being better than A…
As agent capabilities advance, existing benchmarks, such as $\tau^2$-Bench, are becoming increasingly saturated. Yet constructing new benchmark tasks remains complex, costly, and labor-intensive. Moreover, the standard approach, in which…
Semantic Segmentation is one of the most challenging vision tasks, usually requiring large amounts of training data with expensive pixel level annotations. With the success of foundation models and especially vision-language models, recent…
The ability to understand visual information from limited labeled data is an important aspect of machine learning. While image-level classification has been extensively studied in a semi-supervised setting, dense pixel-level classification…
Prompting is used to guide or steer a language model in generating an appropriate response that is consistent with the desired outcome. Chaining is a strategy used to decompose complex tasks into smaller, manageable components. In this…
Scribble-based weakly supervised semantic segmentation leverages only a few annotated pixels as labels to train a segmentation model, presenting significant potential for reducing the human labor involved in the annotation process. This…
We present Simplified Text-Attributed Graph Embeddings (STAGE), a straightforward yet effective method for enhancing node features in Graph Neural Network (GNN) models that encode Text-Attributed Graphs (TAGs). Our approach leverages…
Recent years the task of incomplete utterance rewriting has raised a large attention. Previous works usually shape it as a machine translation task and employ sequence to sequence based architecture with copy mechanism. In this paper, we…
Unconstrained handwritten text recognition is a challenging computer vision task. It is traditionally handled by a two-step approach, combining line segmentation followed by text line recognition. For the first time, we propose an…
Human annotation cost and time remain significant bottlenecks in Natural Language Processing (NLP), with test data annotation being particularly expensive due to the stringent requirement for low-error and high-quality labels necessary for…
This paper proposes a new active learning method for semantic segmentation. The core of our method lies in a new annotation query design. It samples informative local image regions (e.g., superpixels), and for each of such regions, asks an…
Sentence embedding refers to a set of effective and versatile techniques for converting raw text into numerical vector representations that can be used in a wide range of natural language processing (NLP) applications. The majority of these…