Related papers: More Embeddings, Better Sequence Labelers?

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…

Fine-grained multi-label classification models have broad applications in e-commerce, such as visual based label predictions ranging from fashion attribute detection to brand recognition. One challenge to achieve satisfactory performance…

Examining the effect of different encoding techniques on entity and context embeddings, the goal of this work is to challenge commonly used Ordinal encoding for tabular learning. Applying different preprocessing methods and network…

Sense embedding learning methods learn different embeddings for the different senses of an ambiguous word. One sense of an ambiguous word might be socially biased while its other senses remain unbiased. In comparison to the numerous prior…

Cross-lingual embeddings aim to represent words in multiple languages in a shared vector space by capturing semantic similarities across languages. They are a crucial component for scaling tasks to multiple languages by transferring…

Large language models are able to learn new tasks in context, where they are provided with instructions and a few annotated examples. However, the effectiveness of in-context learning is dependent on the provided context, and the…

Creating accurate meta-embeddings from pre-trained source embeddings has received attention lately. Methods based on global and locally-linear transformation and concatenation have shown to produce accurate meta-embeddings. In this paper,…

Sequence labeling is a fundamental framework for various natural language processing problems. Its performance is largely influenced by the annotation quality and quantity in supervised learning scenarios, and obtaining ground truth labels…

Constrained clustering allows the training of classification models using pairwise constraints only, which are weak and relatively easy to mine, while still yielding full-supervision-level model performance. While they perform well even in…

Static and contextual multilingual embeddings have complementary strengths. Static embeddings, while less expressive than contextual language models, can be more straightforwardly aligned across multiple languages. We combine the strengths…

Sequence labeling is a core task in text understanding for IE/IR systems. Text generation models have increasingly become the go-to solution for such tasks (e.g., entity extraction and dialog slot filling). While most research has focused…

Position embeddings, encoding the positional relationships among tokens in text sequences, make great contributions to modeling local context features in Transformer-based pre-trained language models. However, in Extractive Question…

Pretrained, large, generative language models (LMs) have had great success in a wide range of sequence tagging and structured prediction tasks. Casting a sequence tagging task as a Seq2Seq one requires deciding the formats of the input and…

In recent years, multi-label classification problem has become a controversial issue. In this kind of classification, each sample is associated with a set of class labels. Ensemble approaches are supervised learning algorithms in which an…

Large Language Models (LLMs) have made significant strides in handling long sequences. Some models like Gemini could even to be capable of dealing with millions of tokens. However, their performance evaluation has largely been confined to…

Many tasks in Natural Language Processing involve recognizing lexical entailment. Two different approaches to this problem have been proposed recently that are quite different from each other. The first is an asymmetric similarity measure…

How to make the most of multiple heterogeneous treebanks when training a monolingual dependency parser is an open question. We start by investigating previously suggested, but little evaluated, strategies for exploiting multiple treebanks…

Gestures are integral components of face-to-face communication. They unfold over time, often following predictable movement phases of preparation, stroke, and retraction. Yet, the prevalent approach to automatic gesture detection treats the…

Work on retrieval-based chatbots, like most sequence pair matching tasks, can be divided into Cross-encoders that perform word matching over the pair, and Bi-encoders that encode the pair separately. The latter has better performance,…

Although models using contextual word embeddings have achieved state-of-the-art results on a host of NLP tasks, little is known about exactly what information these embeddings encode about the context words that they are understood to…