paper-with-me

Papers

Augmenting BERT-style Models with Predictive Coding to Improve Discourse-level Representations

2021-09-10 · EMNLP 2021 11 · Vladimir Araujo, Andrés Villa, Marcelo Mendoza, Marie-Francine Moens, Alvaro Soto

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 representations. In this work, we propose to use ideas from predictive coding theory to augment BERT-style language models with a mechanism that allows them to learn suitable discourse-level representations. As a result, our proposed approach is able to predict future sentences using explicit top-down connections that operate at the intermediate layers of the network. By experimenting with benchmarks designed to evaluate discourse-related knowledge using pre-trained sentence representations, we demonstrate that our approach improves performance in 6 out of 11 tasks by excelling in discourse relationship detection.

📄 PDF Abstract BibTeX arXiv:2109.04602

Code (0)

등록된 구현이 없습니다.

Tasks

Relationship DetectionSentence

Similar Papers 제목 키워드 기반

Learning Speech Representations with Variational Predictive Coding

2025-12-31 · Sung-Lin Yeh, Peter Bell, Hao Tang arxiv

Despite being the best known objective for learning speech representations, the HuBERT objective has not been further developed and improved. We argue that it is the lack of an underlying principle that stalls the develo…

Speaker RecognitionSpeech Recognition

Towards High-fidelity Singing Voice Conversion with Acoustic Reference and Contrastive Predictive Coding

2021-10-10 · Chao Wang, Zhonghao Li, Benlai Tang, Xiang Yin 외

Recently, phonetic posteriorgrams (PPGs) based methods have been quite popular in non-parallel singing voice conversion systems. However, due to the lack of acoustic information in PPGs, style and naturalness of the conv…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)speech-recognitionSpeech Recognition+1

A BERT-based Universal Model for Both Within- and Cross-sentence Clinical Temporal Relation Extraction

2019-06-01 · WS 2019 6 · Chen Lin, Timothy Miller, Dmitriy Dligach, Steven Bethard 외

Classic methods for clinical temporal relation extraction focus on relational candidates within a sentence. On the other hand, break-through Bidirectional Encoder Representations from Transformers (BERT) are trained on l…

RelationRelation ExtractionSentenceTemporal Relation Extraction

iBERT: Interpretable Embeddings via Sense Decomposition

2025-10-10 · Vishal Anand, Milad Alshomary, Kathleen McKeown arxiv

We present iBERT (interpretable-BERT), an encoder to produce inherently interpretable and controllable embeddings - designed to modularize and expose the discriminative cues present in language, such as semantic or styli…

Cracking the Contextual Commonsense Code: Understanding Commonsense Reasoning Aptitude of Deep Contextual Representations

2019-10-02 · WS 2019 11 · Jeff Da, Jungo Kasai

Pretrained deep contextual representations have advanced the state-of-the-art on various commonsense NLP tasks, but we lack a concrete understanding of the capability of these models. Thus, we investigate and challenge s…

Knowledge Graphs