Challenge: Recent models for unsupervised representation learning of text have put little focus on discourse-level representations.
Approach: They propose an inter-sentence objective for pretraining language models that models discourse coherence and the distance between sentences.
Outcome: The proposed model outperforms the BERT-Large model on the discourse representation benchmark DiscoEval and yields gains of 2%-6% absolute even for tasks that do not explicitly evaluate discourse.

Similar Papers

Evaluation Benchmarks and Learning Criteria for Discourse-Aware Sentence Representations (D19-1)

Copied to clipboard

Challenge: Prior work on pretrained sentence embeddings and benchmarks focused on the capabilities of stand-alone sentences.
Approach: They propose a test suite of tasks to evaluate whether sentence representations include broader context information.
Outcome: The proposed training objectives help to encode different aspects of information in document structures.
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.
Sentence Representation Learning with Generative Objective rather than Contrastive Objective (2022.emnlp-main)

Copied to clipboard

Challenge: Existing sentences-level training objectives focus on acquiring sentence-level representations, but they lack effective self-supervised objectives.
Approach: They propose a generative self-supervised learning objective based on phrase reconstruction to improve sentence representation.
Outcome: Empirical results show that the proposed objective outperforms current methods on STS benchmarks and retrieval and reranking tasks.
ConSERT: A Contrastive Framework for Self-Supervised Sentence Representation Transfer (2021.acl-long)

Copied to clipboard

Challenge: Existing BERT-based pre-trained language models achieve high performance on many downstream tasks, but native derived sentence representations are collapsed and thus poor performance on semantic textual similarity (STS) tasks.
Approach: They propose a framework for self-supervised Sentence Representation Transfer that adopts contrastive learning to fine-tune BERT in an unsupervised way.
Outcome: The proposed framework improves on the BERT-derived representations by 8% on STS datasets and shows robustness in data scarcity scenarios.
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.
Can You Tell Me How to Get Past Sesame Street? Sentence-Level Pretraining Beyond Language Modeling (P19-1)

Copied to clipboard

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.
Multilingual Constituency Parsing with Self-Attention and Pre-Training (P19-1)

Copied to clipboard

Challenge: a range of pre-training conditions can be used for constituency parsing, but large model sizes make it expensive to train separate models for each language.
Approach: They compare the benefits of no pre-training, fastText, ELMo, and BERT for English . they also find that pre- training is beneficial across all 11 languages tested .
Outcome: The proposed model outperforms fastText, ELMo, and BERT for English . but large model sizes make it expensive to train separate models for each language .
Pretraining Methods for Dialog Context Representation Learning (P19-1)

Copied to clipboard

Challenge: Existing methods for pretraining dialog context encoders are still in their infancy.
Approach: They propose to use unsupervised pretraining objectives for dialog context representations to fine-tune and evaluate them on a set of downstream dialog tasks.
Outcome: The proposed methods improve performance on a set of dialog tasks and are less data hungry.
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.
Coherence boosting: When your pretrained language model is not paying enough attention (2022.acl-long)

Copied to clipboard

Challenge: Long-range semantic coherence remains a challenge in automatic language generation and understanding.
Approach: They propose a procedure that increases a model’s focus on a long context by distributional analyses of generated ordinary text and dialog responses.
Outcome: The proposed procedure increases the model's focus on a long context.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations