paper-with-me

홈 › Papers

Do sentence embeddings capture discourse properties of sentences from Scientific Abstracts ?

2020-11-01 · EMNLP (CODI) 2020 11 · Laurine Huber, Chaker Memmadi, Mathilde Dargnat, Yannick Toussaint

We introduce four tasks designed to determine which sentence encoders best capture discourse properties of sentences from scientific abstracts, namely coherence and cohesion between clauses of a sentence, and discourse relations within sentences. We show that even if contextual encoders such as BERT or SciBERT encodes the coherence in discourse units, they do not help to predict three discourse relations commonly used in scientific abstracts. We discuss what these results underline, namely that these discourse relations are based on particular phrasing that allow non-contextual encoders to perform well.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

SentenceSentence Embeddings

Similar Papers 제목 키워드 기반

A Review of Discourse-level Machine Translation

2020-12-01 · AACL (iwdp) 2020 12 · Xiaojun Zhang

Machine translation (MT) models usually translate a text at sentence level by considering isolated sentences, which is based on a strict assumption that the sentences in a text are independent of one another. However, th…

Machine TranslationNMTSentenceTranslation

DisSent: Sentence Representation Learning from Explicit Discourse Relations

2017-10-12 · Allen Nie, Erin D. Bennett, Noah D. Goodman

Learning effective representations of sentences is one of the core missions of natural language understanding. Existing models either train on a vast amount of text, or require costly, manually curated sentence relation …

Dependency ParsingNatural Language UnderstandingRelationRelation Prediction+3

Recurrent Convolutional Neural Networks for Discourse Compositionality

2013-06-15 · WS 2013 8 · Nal Kalchbrenner, Phil Blunsom

The compositionality of meaning extends beyond the single sentence. Just as words combine to form the meaning of sentences, so do sentences combine to form the meaning of paragraphs, dialogues and general discourse. We i…

Dialogue Act ClassificationFeature EngineeringSentence

DisSent: Learning Sentence Representations from Explicit Discourse Relations

2019-07-01 · ACL 2019 7 · Allen Nie, Erin Bennett, Noah Goodman

Learning effective representations of sentences is one of the core missions of natural language understanding. Existing models either train on a vast amount of text, or require costly, manually curated sentence relation …

Dependency ParsingNatural Language UnderstandingRelationRelation Prediction+2

Correcting the Common Discourse Bias in Linear Representation of Sentences using Conceptors

2018-11-17 · Liu Tianlin, Sedoc João, Ungar Lyle

Distributed representations of words, better known as word embeddings, have become important building blocks for natural language processing tasks. Numerous studies are devoted to transferring the success of unsupervised…

Semantic Textual SimilaritySentenceSentence EmbeddingSentence-Embedding+2