Related papers: Par4Sim -- Adaptive Paraphrasing for Text Simplifi…

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…

Learning from implicit feedback is challenging because of the difficult nature of the one-class problem: we can observe only positive examples. Most conventional methods use a pairwise ranking approach and negative samplers to cope with the…

Recently, there has been an increasing interest in unsupervised parsers that optimize semantically oriented objectives, typically using reinforcement learning. Unfortunately, the learned trees often do not match actual syntax trees well.…

Detectability of failures of linear programming (LP) decoding and its potential for improvement by adding new constraints motivate the use of an adaptive approach in selecting the constraints for the LP problem. In this paper, we make a…

Large Language Models (LLMs) have been widely used as general-purpose AI agents showing comparable performance on many downstream tasks. However, existing work shows that it is challenging for LLMs to integrate structured data (e.g. KG,…

Speech model adaptation is crucial to handle the discrepancy between server-side proxy training data and actual data received on local devices of users. With the use of federated learning (FL), we introduce an efficient approach on…

Automatic generation of paraphrases from a given sentence is an important yet challenging task in natural language processing (NLP), and plays a key role in a number of applications such as question answering, search, and dialogue. In this…

Benchmark scores for Large Language Models (LLMs) can be inflated by memorization of test items or near duplicates. We present a simple, protocol that probes generalization by re-evaluating models on paraphrased versions of benchmark…

The dominating NLP paradigm of training a strong neural predictor to perform one task on a specific dataset has led to state-of-the-art performance in a variety of applications (eg. sentiment classification, span-prediction based question…

Pre-trained transformer language models have shown remarkable performance on a variety of NLP tasks. However, recent research has suggested that phrase-level representations in these models reflect heavy influences of lexical content, but…

NLP has achieved great progress in the past decade through the use of neural models and large labeled datasets. The dependence on abundant data prevents NLP models from being applied to low-resource settings or novel tasks where significant…

Adversarial attacks against language models(LMs) are a significant concern. In particular, adversarial samples exploit the model's sensitivity to small input changes. While these changes appear insignificant on the semantics of the input…

Sentence embeddings can be decoded to give approximations of the original texts used to create them. We explore this effect in the context of text simplification, demonstrating that reconstructed text embeddings preserve complexity levels.…

Natural language processing (NLP) applied to information retrieval (IR) and filtering problems may assign part-of-speech tags to terms and, more generally, modify queries and documents. Analytic models can predict the performance of a text…

Sentence simplification aims to reduce the complexity of a sentence while retaining its original meaning. Current models for sentence simplification adopted ideas from ma- chine translation studies and implicitly learned simplification…

Text simplification seeks to improve readability while retaining the original content and meaning. Our study investigates whether pre-trained classifiers also maintain such coherence by comparing their predictions on both original and…

Recent advance in deep learning has led to the rapid adoption of machine learning-based NLP models in a wide range of applications. Despite the continuous gain in accuracy, backward compatibility is also an important aspect for industrial…

Low-rank approximation is a fundamental technique in modern data analysis, widely utilized across various fields such as signal processing, machine learning, and natural language processing. Despite its ubiquity, the mechanics of low-rank…

Language models pretrained on text from a wide variety of sources form the foundation of today's NLP. In light of the success of these broad-coverage models, we investigate whether it is still helpful to tailor a pretrained model to the…

Web-scale pre-training datasets are the cornerstone of LLMs' success. However, text data curated from the Internet inevitably contains random noise caused by decoding errors or unregulated web content. In contrast to previous works that…