English
Related papers

Related papers: Constrained Language Models Yield Few-Shot Semanti…

200 papers

Small Language Models (SLMs) have become increasingly important due to their efficiency and performance to perform various language tasks with minimal computational resources, making them ideal for various settings including on-device,…

Compositional vector space models of meaning promise new solutions to stubborn language understanding problems. This paper makes two contributions toward this end: (i) it uses automatically-extracted paraphrase examples as a source of…

Computation and Language · Computer Science 2018-02-01 Avneesh Saluja , Chris Dyer , Jean-David Ruvini

Lexical simplification (LS) methods based on pretrained language models have made remarkable progress, generating potential substitutes for a complex word through analysis of its contextual surroundings. However, these methods require…

Computation and Language · Computer Science 2023-07-31 Kang Liu , Jipeng Qiang , Yun Li , Yunhao Yuan , Yi Zhu , Kaixun Hua

Code comment generation aims at generating natural language descriptions for a code snippet to facilitate developers' program comprehension activities. Despite being studied for a long time, a bottleneck for existing approaches is that…

Software Engineering · Computer Science 2023-06-16 Mingyang Geng , Shangwen Wang , Dezun Dong , Haotian Wang , Ge Li , Zhi Jin , Xiaoguang Mao , Xiangke Liao

Large-scale pretraining instills large amounts of knowledge in deep neural networks. This, in turn, improves the generalization behavior of these models in downstream tasks. What exactly are the limits to the generalization benefits of…

Computation and Language · Computer Science 2022-12-23 A. Emin Orhan

Current models for Word Sense Disambiguation (WSD) struggle to disambiguate rare senses, despite reaching human performance on global WSD metrics. This stems from a lack of data for both modeling and evaluating rare senses in existing WSD…

Computation and Language · Computer Science 2021-02-17 Terra Blevins , Mandar Joshi , Luke Zettlemoyer

Few-shot semantic segmentation aims to learn to segment new object classes with only a few annotated examples, which has a wide range of real-world applications. Most existing methods either focus on the restrictive setting of one-way…

Computer Vision and Pattern Recognition · Computer Science 2022-12-05 Yongfei Liu , Xiangyi Zhang , Songyang Zhang , Xuming He

Conversational systems relying on text-based large language models (LLMs) often overlook paralinguistic cues, essential for understanding emotions and intentions. Speech-language models (SLMs), which use speech as input, are emerging as a…

Computation and Language · Computer Science 2025-08-12 Chun Wang , Chenyang Liu , Wenze Xu , Weihong Deng

English pretrained language models, which make up the backbone of many modern NLP systems, require huge amounts of unlabeled training data. These models are generally presented as being trained only on English text but have been found to…

Computation and Language · Computer Science 2022-11-18 Terra Blevins , Luke Zettlemoyer

Large language models trained primarily in a monolingual setting have demonstrated their ability to generalize to machine translation using zero- and few-shot examples with in-context learning. However, even though zero-shot translations…

Computation and Language · Computer Science 2023-11-07 Weiting Tan , Haoran Xu , Lingfeng Shen , Shuyue Stella Li , Kenton Murray , Philipp Koehn , Benjamin Van Durme , Yunmo Chen

While pre-trained language models have obtained state-of-the-art performance for several natural language understanding tasks, they are quite opaque in terms of their decision-making process. While some recent works focus on rationalizing…

Computation and Language · Computer Science 2021-09-20 Meghana Moorthy Bhat , Alessandro Sordoni , Subhabrata Mukherjee

Prompted models have demonstrated impressive few-shot learning abilities. Repeated interactions at test-time with a single model, or the composition of multiple models together, further expands capabilities. These compositions are…

Parameter-efficient (PE) methods (like Prompts or Adapters) for adapting pre-trained language models (PLM) to downstream tasks have been popular recently. However, hindrances still prevent these methods from reaching their full potential.…

Computation and Language · Computer Science 2024-05-31 Shih-Cheng Huang , Shih-Heng Wang , Min-Han Shih , Saurav Sahay , Hung-yi Lee

Disentangling the encodings of neural models is a fundamental aspect for improving interpretability, semantic control and downstream task performance in Natural Language Processing. Currently, most disentanglement methods are unsupervised…

Computation and Language · Computer Science 2023-02-17 Danilo S. Carvalho , Giangiacomo Mercatali , Yingji Zhang , Andre Freitas

Large Language Models (LLMs) have achieved strong performance across many downstream tasks, yet their effectiveness in extremely low-resource machine translation remains limited. Standard adaptation techniques typically rely on large-scale…

Computation and Language · Computer Science 2026-03-18 Aishwarya Ramasethu , Niyathi Allu , Rohin Garg , Harshwardhan Fartale , Dun Li Chan

We study model pruning methods applied to Transformer-based neural network language models for automatic speech recognition. We explore three aspects of the pruning frame work, namely criterion, method and scheduler, analyzing their…

Machine Learning · Computer Science 2023-10-06 Leonardo Emili , Thiago Fraga-Silva , Ernest Pusateri , Markus Nußbaum-Thom , Youssef Oualil

Building a dialogue system that can communicate naturally with humans is a challenging yet interesting problem of agent-based computing. The rapid growth in this area is usually hindered by the long-standing problem of data scarcity as…

Computation and Language · Computer Science 2021-04-23 Munazza Zaib , Quan Z. Sheng , Wei Emma Zhang

Despite serving as the foundation models for a wide range of NLP benchmarks, pre-trained language models have shown limited capabilities of acquiring implicit commonsense knowledge from self-supervision alone, compared to learning…

Computation and Language · Computer Science 2023-06-06 Wangchunshu Zhou , Ronan Le Bras , Yejin Choi

Finetuning large pre-trained language models with a task-specific head has advanced the state-of-the-art on many natural language understanding benchmarks. However, models with a task-specific head require a lot of training data, making…

Computation and Language · Computer Science 2022-05-23 Pride Kavumba , Ryo Takahashi , Yusuke Oda

We explore a new language model inversion problem under strict black-box, zero-shot, and limited data conditions. We propose a novel training-free framework that reconstructs prompts using only a limited number of text outputs from a…

Computation and Language · Computer Science 2025-02-18 Hanqing Li , Diego Klabjan