SLM: Learning a Discourse Language Representation with Sentence Unshuffling (2020.emnlp-main)
Copied to clipboard
| Challenge: | Recent models for learning discourse language representations focus on bottom or top-level representations, but they do not capture intermediate-size structures in natural languages such as sentences and the relationships among them. |
| Approach: | They propose a new objective for learning a discourse language representation in a self-supervised manner by shuffling the sequence of input sentences and training a hierarchical transformer model to reconstruct the original ordering. |
| Outcome: | The proposed model improves the original BERT model on downstream tasks by large margins. |
Similar Papers
Augmenting BERT-style Models with Predictive Coding to Improve Discourse-level Representations (2021.emnlp-main)
Copied to clipboard
| Challenge: | Existing language models do not produce suitable representations at the discourse level. |
| Approach: | They propose to augment BERT-style language models with a mechanism that allows them to learn suitable discourse-level representations by incorporating top-down connections that operate at the intermediate layers of the network. |
| Outcome: | The proposed approach improves in 6 out of 11 tasks by detecting discourse relationship detection. |
Pretrained Language Models for Sequential Sentence Classification (D19-1)
Copied to clipboard
| Challenge: | Recent successful models for document-level understanding have used hierarchical encoding and CRFs to capture dependencies between subsequent labels. |
| Approach: | They propose a pretrained language model that captures contextual dependencies without hierarchical encoding nor a CRF. |
| Outcome: | The proposed model captures contextual dependencies without hierarchical encoding nor a CRF on four datasets, including a new dataset of structured scientific abstracts. |
Discourse Representation Parsing for Sentences and Documents (P19-1)
Copied to clipboard
| Challenge: | Experimental results show that our model outperforms competitive baselines by a wide margin. |
| Approach: | They propose a neural model which parses discourse structures of arbitrary length and granularity. |
| Outcome: | The proposed model outperforms baseline models on sentence- and document-level benchmarks. |
A Language Model-based Generative Classifier for Sentence-level Discourse Parsing (2021.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods to consider textual coherence are limited in labeled data. |
| Approach: | They propose a language model-based generative classifier that uses labels as input and embeds labels into their representations. |
| Outcome: | The proposed classifier achieves state-of-the-art in discourse segmentation and relation F1 scores with gold boundaries and automatically segmented boundaries. |
Less Mature is More Adaptable for Sentence-level Language Modeling (2025.acl-long)
Copied to clipboard
| Challenge: | Existing studies fine-tune encoders or contrastive learning approaches to learn sentence representations. |
| Approach: | They propose to use sentence-level models to study how sentence representations influence downstream task performance. |
| Outcome: | The proposed models outperform token-level models in terms of time and data efficiency. |
Which *BERT? A Survey Organizing Contextualized Encoders (2020.emnlp-main)
Copied to clipboard
| Challenge: | a survey on language representation learning aims to highlight common themes . we focus on the areas of progress, compared to other fields, and discuss how each area is evaluated. |
| Approach: | They present a survey on language representation learning to highlight common themes . they compare contributions in contextualized text encoders to ideas from other fields . |
| Outcome: | The proposed survey aims to highlight common themes in the field of language representation learning. |
Can You Tell Me How to Get Past Sesame Street? Sentence-Level Pretraining Beyond Language Modeling (P19-1)
Copied to clipboard
Alex Wang, Jan Hula, Patrick Xia, Raghavendra Pappagari, R. Thomas McCoy, Roma Patel, Najoung Kim, Ian Tenney, Yinghui Huang, Katherin Yu, Shuning Jin, Berlin Chen, Benjamin Van Durme, Edouard Grave, Ellie Pavlick, Samuel R. Bowman
| Challenge: | State-of-the-art models in natural language processing (NLP) often incorporate sentence encoder functions which generate a sequence of vectors intended to represent the in-context meaning of each word in an input text. |
| Approach: | They conduct the first large-scale systematic study of candidate pretraining tasks, comparing 19 different tasks as alternatives and complements to language modeling. |
| Outcome: | The proposed model can be used to train sentences on language modeling tasks. |
Sentence Bottleneck Autoencoders from Transformer Language Models (2021.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for pretraining a language model on text have been used for building models in NLP, but they do not work for sentence representations derived from pretrainer models based on tokens or basic pooling operations. |
| Approach: | They propose to build a sentence-level autoencoder from a pretrained transformer language model. |
| Outcome: | The proposed model achieves better quality than previous methods on text similarity and style transfer tasks while using fewer parameters than large pretrained models. |
Discourse Probing of Pretrained Language Models (2021.naacl-main)
Copied to clipboard
| Challenge: | Existing work on probing of pretrained language models has focused on sentence-level syntactic tasks. |
| Approach: | They introduce document-level discourse probing to evaluate the ability of pretrained LMs to capture document- level relations. |
| Outcome: | The proposed model performs best in encoder, but only in the encoder layer. |
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding (N19-1)
Copied to clipboard
| Challenge: | Existing language representation models pre-train deep bidirectional representations from unlabeled text without significant task-specific architecture modifications. |
| Approach: | They propose a language representation model that pre-trains bidirectional representations from unlabeled text by jointly conditioning on both left and right context in all layers. |
| Outcome: | The proposed model achieves state-of-the-art results on eleven natural language processing tasks, pushing the GLUE score to 80.5 (7.7 point absolute improvement), MultiNLI accuracy to 86.7% (4.6% absolute improvement) |