English
Related papers

Related papers: A BERT Baseline for the Natural Questions

200 papers

We introduce a new language representation model called BERT, which stands for Bidirectional Encoder Representations from Transformers. Unlike recent language representation models, BERT is designed to pre-train deep bidirectional…

Computation and Language · Computer Science 2019-05-28 Jacob Devlin , Ming-Wei Chang , Kenton Lee , Kristina Toutanova

In this paper, we describe a dataset and baseline result for a question answering that utilizes web tables. It contains commonly asked questions on the web and their corresponding answers found in tables on websites. Our dataset is novel in…

Computation and Language · Computer Science 2019-04-17 Bhavya Karki , Fan Hu , Nithin Haridas , Suhail Barot , Zihua Liu , Lucile Callebert , Matthias Grabmair , Anthony Tomasic

There is a huge performance gap between formal and informal language understanding tasks. The recent pre-trained models that improved the performance of formal language understanding tasks did not achieve a comparable result on informal…

Computation and Language · Computer Science 2020-04-30 Jing Gu , Zhou Yu

Natural Language Processing (NLP) has recently achieved great success by using huge pre-trained models with hundreds of millions of parameters. However, these models suffer from heavy model sizes and high latency such that they cannot be…

Computation and Language · Computer Science 2020-04-16 Zhiqing Sun , Hongkun Yu , Xiaodan Song , Renjie Liu , Yiming Yang , Denny Zhou

Contextual word embeddings such as BERT have achieved state of the art performance in numerous NLP tasks. Since they are optimized to capture the statistical properties of training data, they tend to pick up on and amplify social…

Computation and Language · Computer Science 2019-06-19 Keita Kurita , Nidhi Vyas , Ayush Pareek , Alan W Black , Yulia Tsvetkov

Pretrained language models are publicly available and constantly finetuned for various real-life applications. As they become capable of grasping complex contextual information, harmful biases are likely increasingly intertwined with those…

Computation and Language · Computer Science 2023-06-28 Sophie Jentzsch , Cigdem Turan

Large-scale pre-trained language models have been shown to be helpful in improving the naturalness of text-to-speech (TTS) models by enabling them to produce more naturalistic prosodic patterns. However, these models are usually word-level…

Computation and Language · Computer Science 2023-01-24 Yinghao Aaron Li , Cong Han , Xilin Jiang , Nima Mesgarani

Developing AI systems capable of nuanced ethical reasoning is critical as they increasingly influence human decisions, yet existing models often rely on superficial correlations rather than principled moral understanding. This paper…

Computers and Society · Computer Science 2025-10-16 Mahamodul Hasan Mahadi , Md. Nasif Safwan , Souhardo Rahman , Shahnaj Parvin , Aminun Nahar , Kamruddin Nur

We present a novel supervised word alignment method based on cross-language span prediction. We first formalize a word alignment problem as a collection of independent predictions from a token in the source sentence to a span in the target…

Computation and Language · Computer Science 2020-05-01 Masaaki Nagata , Chousa Katsuki , Masaaki Nishino

We introduce FaBERT, a Persian BERT-base model pre-trained on the HmBlogs corpus, encompassing both informal and formal Persian texts. FaBERT is designed to excel in traditional Natural Language Understanding (NLU) tasks, addressing the…

Computation and Language · Computer Science 2024-02-12 Mostafa Masumi , Seyed Soroush Majd , Mehrnoush Shamsfard , Hamid Beigy

Natural Language Processing (NLP) has witnessed a transformative leap with the advent of transformer-based architectures, which have significantly enhanced the ability of machines to understand and generate human-like text. This paper…

Computation and Language · Computer Science 2025-03-27 Tianhao Wu , Yu Wang , Ngoc Quach

Large pre-trained language models help to achieve state of the art on a variety of natural language processing (NLP) tasks, nevertheless, they still suffer from forgetting when incrementally learning a sequence of tasks. To alleviate this…

Computation and Language · Computer Science 2023-03-03 Mingxu Tao , Yansong Feng , Dongyan Zhao

Large pre-trained language models have shown promise for few-shot learning, completing text-based tasks given only a few task-specific examples. Will models soon solve classification tasks that have so far been reserved for human research…

Given the increasingly prominent role NLP models (will) play in our lives, it is important for human expectations of model behavior to align with actual model behavior. Using Natural Language Inference (NLI) as a case study, we investigate…

Computation and Language · Computer Science 2021-09-20 Grusha Prasad , Yixin Nie , Mohit Bansal , Robin Jia , Douwe Kiela , Adina Williams

Fine-tuning pre-trained models have achieved impressive performance on standard natural language processing benchmarks. However, the resultant model generalizability remains poorly understood. We do not know, for example, how excellent…

Computation and Language · Computer Science 2023-01-26 Luoqiu Li , Xiang Chen , Hongbin Ye , Zhen Bi , Shumin Deng , Ningyu Zhang , Huajun Chen

We are surprised to find that BERT's peak performance of 77% on the Argument Reasoning Comprehension Task reaches just three points below the average untrained human baseline. However, we show that this result is entirely accounted for by…

Computation and Language · Computer Science 2019-09-17 Timothy Niven , Hung-Yu Kao

Although large pre-trained language models have achieved great success in many NLP tasks, it has been shown that they reflect human biases from their pre-training corpora. This bias may lead to undesirable outcomes when these models are…

Computation and Language · Computer Science 2022-11-29 Aristides Milios , Parishad BehnamGhader

Building query graphs from natural language questions is an important step in complex question answering over knowledge graph (Complex KGQA). In general, a question can be correctly answered if its query graph is built correctly and the…

Computation and Language · Computer Science 2022-09-23 Mingchen Li , Shihao Ji

Pretrained language models such as BERT, GPT have shown great effectiveness in language understanding. The auxiliary predictive tasks in existing pretraining approaches are mostly defined on tokens, thus may not be able to capture…

Computation and Language · Computer Science 2020-06-19 Hongchao Fang , Sicheng Wang , Meng Zhou , Jiayuan Ding , Pengtao Xie

We show that BERT (Devlin et al., 2018) is a Markov random field language model. This formulation gives way to a natural procedure to sample sentences from BERT. We generate from BERT and find that it can produce high-quality, fluent…

Computation and Language · Computer Science 2019-04-11 Alex Wang , Kyunghyun Cho