English
Related papers

Related papers: On the Sentence Embeddings from Pre-trained Langua…

200 papers

Dense vector representations for textual data are crucial in modern NLP. Word embeddings and sentence embeddings estimated from raw texts are key in achieving state-of-the-art results in various tasks requiring semantic understanding.…

Computation and Language · Computer Science 2023-07-06 Sonal Sannigrahi , Josef van Genabith , Cristina Espana-Bonet

Most state-of-the-art models in natural language processing (NLP) are neural models built on top of large, pre-trained, contextual language models that generate representations of words in context and are fine-tuned for the task at hand.…

Computation and Language · Computer Science 2020-10-13 Brian Lester , Daniel Pressel , Amy Hemmeter , Sagnik Ray Choudhury , Srinivas Bangalore

We use paraphrases as a unique source of data to analyze contextualized embeddings, with a particular focus on BERT. Because paraphrases naturally encode consistent word and phrase semantics, they provide a unique lens for investigating…

Computation and Language · Computer Science 2022-07-13 Laura Burdick , Jonathan K. Kummerfeld , Rada Mihalcea

Pre-trained language models like BERT achieve superior performances in various NLP tasks without explicit consideration of syntactic information. Meanwhile, syntactic information has been proved to be crucial for the success of NLP…

Computation and Language · Computer Science 2021-03-09 Jiangang Bai , Yujing Wang , Yiren Chen , Yaming Yang , Jing Bai , Jing Yu , Yunhai Tong

Language model pre-training, such as BERT, has achieved remarkable results in many NLP tasks. However, it is unclear why the pre-training-then-fine-tuning paradigm can improve performance and generalization capability across different…

Computation and Language · Computer Science 2019-08-16 Yaru Hao , Li Dong , Furu Wei , Ke Xu

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

Language models have been supervised with both language-only objective and visual grounding in existing studies of visual-grounded language learning. However, due to differences in the distribution and scale of visual-grounded datasets and…

Computation and Language · Computer Science 2024-01-10 Cong-Duy Nguyen , The-Anh Vu-Le , Thong Nguyen , Tho Quan , Luu Anh Tuan

Neural machine translation models are often biased toward the limited translation references seen during training. To amend this form of overfitting, in this paper we propose fine-tuning the models with a novel training objective based on…

Computation and Language · Computer Science 2021-06-07 Inigo Jauregi Unanue , Jacob Parnell , Massimo Piccardi

Pretraining deep neural network architectures with a language modeling objective has brought large improvements for many natural language processing tasks. Exemplified by BERT, a recently proposed such architecture, we demonstrate that…

Computation and Language · Computer Science 2019-12-05 Timo Schick , Hinrich Schütze

Semantic textual similarity is one of the open research challenges in the field of Natural Language Processing. Extensive research has been carried out in this field and near-perfect results are achieved by recent transformer-based models…

Computation and Language · Computer Science 2021-07-13 Dhivya Chandrasekaran , Vijay Mago

Pre-trained language models (PLMs) have consistently demonstrated outstanding performance across a diverse spectrum of natural language processing tasks. Nevertheless, despite their success with unseen data, current PLM-based…

Computation and Language · Computer Science 2024-03-19 Javad Rafiei Asl , Prajwal Panzade , Eduardo Blanco , Daniel Takabi , Zhipeng Cai

Despite prosody is related to the linguistic information up to the discourse structure, most text-to-speech (TTS) systems only take into account that within each sentence, which makes it challenging when converting a paragraph of texts into…

Audio and Speech Processing · Electrical Eng. & Systems 2020-11-11 Guanghui Xu , Wei Song , Zhengchen Zhang , Chao Zhang , Xiaodong He , Bowen Zhou

Recent work has found evidence that Multilingual BERT (mBERT), a transformer-based multilingual masked language model, is capable of zero-shot cross-lingual transfer, suggesting that some aspects of its representations are shared…

Computation and Language · Computer Science 2020-05-21 Ethan A. Chi , John Hewitt , Christopher D. Manning

Real-world NLP applications often deal with nonstandard text (e.g., dialectal, informal, or misspelled text). However, language models like BERT deteriorate in the face of dialect variation or noise. How do we push BERT's modeling…

Computation and Language · Computer Science 2023-11-02 Aarohi Srivastava , David Chiang

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

Intent classification and slot filling are two essential tasks for natural language understanding. They often suffer from small-scale human-labeled training data, resulting in poor generalization capability, especially for rare words.…

Computation and Language · Computer Science 2019-03-01 Qian Chen , Zhu Zhuo , Wen Wang

In this paper we investigate the linguistic knowledge learned by a Neural Language Model (NLM) before and after a fine-tuning process and how this knowledge affects its predictions during several classification problems. We use a wide set…

Computation and Language · Computer Science 2024-02-27 Alessio Miaschi , Dominique Brunato , Felice Dell'Orletta , Giulia Venturi

Models trained to estimate word probabilities in context have become ubiquitous in natural language processing. How do these models use lexical cues in context to inform their word probabilities? To answer this question, we present a case…

Computation and Language · Computer Science 2021-04-23 Kanishka Misra , Allyson Ettinger , Julia Taylor Rayz

Textual representation learners trained on large amounts of data have achieved notable success on downstream tasks; intriguingly, they have also performed well on challenging tests of syntactic competence. Given this success, it remains an…

Computation and Language · Computer Science 2020-05-28 Adhiguna Kuncoro , Lingpeng Kong , Daniel Fried , Dani Yogatama , Laura Rimell , Chris Dyer , Phil Blunsom

We present SpanBERT, a pre-training method that is designed to better represent and predict spans of text. Our approach extends BERT by (1) masking contiguous random spans, rather than random tokens, and (2) training the span boundary…

Computation and Language · Computer Science 2020-01-22 Mandar Joshi , Danqi Chen , Yinhan Liu , Daniel S. Weld , Luke Zettlemoyer , Omer Levy