English
Related papers

Related papers: SenseBERT: Driving Some Sense into BERT

200 papers

This paper explores learning rich self-supervised entity representations from large amounts of the associated text. Once pre-trained, these models become applicable to multiple entity-centric tasks such as ranked retrieval, knowledge base…

Computation and Language · Computer Science 2021-03-01 Yury Zemlyanskiy , Sudeep Gandhe , Ruining He , Bhargav Kanagal , Anirudh Ravula , Juraj Gottweis , Fei Sha , Ilya Eckstein

Pre-trained contextual representations like BERT have achieved great success in natural language processing. However, the sentence embeddings from the pre-trained language models without fine-tuning have been found to poorly capture…

Computation and Language · Computer Science 2020-11-12 Bohan Li , Hao Zhou , Junxian He , Mingxuan Wang , Yiming Yang , Lei Li

Since 2017, the Transformer-based models play critical roles in various downstream Natural Language Processing tasks. However, a common limitation of the attention mechanism utilized in Transformer Encoder is that it cannot automatically…

Computation and Language · Computer Science 2022-04-20 Ziyang Luo , Yadong Xi , Jing Ma , Zhiwei Yang , Xiaoxi Mao , Changjie Fan , Rongsheng Zhang

Current language models are usually trained using a self-supervised scheme, where the main focus is learning representations at the word or sentence level. However, there has been limited progress in generating useful discourse-level…

Computation and Language · Computer Science 2021-09-13 Vladimir Araujo , Andrés Villa , Marcelo Mendoza , Marie-Francine Moens , Alvaro Soto

Although pre-trained contextualized language models such as BERT achieve significant performance on various downstream tasks, current language representation still only focuses on linguistic objective at a specific granularity, which may…

Computation and Language · Computer Science 2021-01-01 Yian Li , Hai Zhao

Reading comprehension is a challenging task in natural language processing and requires a set of skills to be solved. While current approaches focus on solving the task as a whole, in this paper, we propose to use a neural network `skill'…

Computation and Language · Computer Science 2017-11-13 Todor Mihaylov , Zornitsa Kozareva , Anette Frank

Prepositions are very common and very ambiguous, and understanding their sense is critical for understanding the meaning of the sentence. Supervised corpora for the preposition-sense disambiguation task are small, suggesting a…

Computation and Language · Computer Science 2016-11-29 Hila Gonen , Yoav Goldberg

This paper describes our system for Task 4 of SemEval-2021: Reading Comprehension of Abstract Meaning (ReCAM). We participated in all subtasks where the main goal was to predict an abstract word missing from a statement. We fine-tuned the…

Computation and Language · Computer Science 2021-04-06 Abhishek Mittal , Ashutosh Modi

In natural language processing, word-sense disambiguation (WSD) is an open problem concerned with identifying the correct sense of words in a particular context. To address this problem, we introduce a novel knowledge-based WSD system. We…

Computation and Language · Computer Science 2020-06-23 Sunjae Kwon , Dongsuk Oh , Youngjoong Ko

We present a neural network architecture based on bidirectional LSTMs to compute representations of words in the sentential contexts. These context-sensitive word representations are suitable for, e.g., distinguishing different word senses…

Computation and Language · Computer Science 2015-11-23 Kazuya Kawakami , Chris Dyer

Sense representations have gone beyond word representations like Word2Vec, GloVe and FastText and achieved innovative performance on a wide range of natural language processing tasks. Although very useful in many applications, the…

Computation and Language · Computer Science 2021-09-02 Jessica Rodrigues da Silva , Helena de Medeiros Caseli

The recently proposed BERT has shown great power on a variety of natural language understanding tasks, such as text classification, reading comprehension, etc. However, how to effectively apply BERT to neural machine translation (NMT) lacks…

Computation and Language · Computer Science 2020-02-18 Jinhua Zhu , Yingce Xia , Lijun Wu , Di He , Tao Qin , Wengang Zhou , Houqiang Li , Tie-Yan Liu

The goal of Word Sense Disambiguation (WSD) is to identify the sense of a polysemous word in a specific context. Deep-learning techniques using BERT have achieved very promising results in the field and different methods have been proposed…

Computation and Language · Computer Science 2021-10-15 Guan-Ting Lin , Manuel Giambi

With the capability of modeling bidirectional contexts, denoising autoencoding based pretraining like BERT achieves better performance than pretraining approaches based on autoregressive language modeling. However, relying on corrupting the…

Computation and Language · Computer Science 2020-01-03 Zhilin Yang , Zihang Dai , Yiming Yang , Jaime Carbonell , Ruslan Salakhutdinov , Quoc V. Le

Word sense induction (WSI) is the task of unsupervised clustering of word usages within a sentence to distinguish senses. Recent work obtain strong results by clustering lexical substitutes derived from pre-trained RNN language models…

Computation and Language · Computer Science 2019-06-03 Asaf Amrami , Yoav Goldberg

The lack of labeled data is a common challenge in speech classification tasks, particularly those requiring extensive subjective assessment, such as cognitive state classification. In this work, we propose a Semi-Supervised Learning (SSL)…

Audio and Speech Processing · Electrical Eng. & Systems 2025-05-01 Yuanchao Li , Zixing Zhang , Jing Han , Peter Bell , Catherine Lai

Existing methods for large-scale point cloud semantic segmentation require expensive, tedious and error-prone manual point-wise annotations. Intuitively, weakly supervised training is a direct solution to reduce the cost of labeling.…

Computer Vision and Pattern Recognition · Computer Science 2022-12-12 Yachao Zhang , Zonghao Li , Yuan Xie , Yanyun Qu , Cuihua Li , Tao Mei

Contextualized word embeddings (CWE) such as provided by ELMo (Peters et al., 2018), Flair NLP (Akbik et al., 2018), or BERT (Devlin et al., 2019) are a major recent innovation in NLP. CWEs provide semantic vector representations of words…

Computation and Language · Computer Science 2019-10-02 Gregor Wiedemann , Steffen Remus , Avi Chawla , Chris Biemann

Natural language understanding (NLU) has two core tasks: intent classification and slot filling. The success of pre-training language models resulted in a significant breakthrough in the two tasks. One of the promising solutions called BERT…

Computation and Language · Computer Science 2023-02-03 Yu Guo , Zhilong Xie , Xingyan Chen , Huangen Chen , Leilei Wang , Huaming Du , Shaopeng Wei , Yu Zhao , Qing Li , Gang Wu

Pre-trained language models such as BERT have exhibited remarkable performances in many tasks in natural language understanding (NLU). The tokens in the models are usually fine-grained in the sense that for languages like English they are…

Computation and Language · Computer Science 2021-05-28 Xinsong Zhang , Pengshuai Li , Hang Li