A Language Model-based Generative Classifier for Sentence-level Discourse Parsing

Zhang, Ying; Kamigaito, Hidetaka; Okumura, Manabu

doi:10.18653/v1/2021.emnlp-main.188

Cited by 8 publications

(4 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Conversely, sentences ( 39) and ( 40) presuppose a single, definite horse being described. It is suggested that this discrepancy between ( 38) and ( 39) and (40) gives rise to divergent interpretations. The resulting challenge in processing relative clauses is attributed to this disparity rather than to syntactic predilections.…”

Section: Theory and Practice In Language Studiesmentioning

confidence: 98%

“…In light of these presuppositions, it becomes implausible to interpret the past verb as a reduced relative clause, unless there is further contextual information available to support such an interpretation. It is suggested that these presuppositions arise primarily because the relative clause in sentence ( 38) is restrictive, whereas in sentence (40) it is not. (40) The horse, (which was) raced past the barn fall.…”

Section: Theory and Practice In Language Studiesmentioning

confidence: 99%

“…It is suggested that these presuppositions arise primarily because the relative clause in sentence ( 38) is restrictive, whereas in sentence (40) it is not. (40) The horse, (which was) raced past the barn fall. They proposed a Referential Hypothesis, which argued that in sentence structure (38), a set of potential horses is assumed, with the horse specified by the relative clause being the one in question.…”

Section: Theory and Practice In Language Studiesmentioning

confidence: 99%

See 2 more Smart Citations

Immediate Processing of Sentences in Language Communication

Zhu,

Ren,

2024

tpls

View full text Add to dashboard Cite

Sentence processing is a fundamental and critical area of inquiry within the field of language processing, as it plays an essential role in facilitating effective communication. The present study focuses on the immediate processing of sentences in English language communication. The article begins by providing an overview of the basic principles underlying sentence processing. It then delves into the various parsing strategies, including the late closure strategy and the minimal attachment strategy. The modular and interactive models of sentence processing are also presented and discussed. Additionally, the relationship between sentence processing and meaning is explored, with an examination of the role of factors such as presupposition and plausibility in language communication process. Finally, the role of prosody in language processing is expounded upon. The paper draws several conclusions regarding the nature of immediate sentence processing in language communication.

show abstract

Section: Theory and Practice In Language Studiesmentioning

confidence: 98%

Section: Theory and Practice In Language Studiesmentioning

confidence: 99%

Section: Theory and Practice In Language Studiesmentioning

confidence: 99%

See 1 more Smart Citation

Immediate Processing of Sentences in Language Communication

Zhu,

Ren,

2024

tpls

View full text Add to dashboard Cite

show abstract

“…To address the problem, Nguyen et al (2021) introduced an end-to-end parsing model, relying on specific frameworks for different tasks. Zhang et al (2021b) proposed a system with rerankers to improve the performance.…”

Section: Related Workmentioning

confidence: 99%

Exploring Discourse Structure in Document-level Machine Translation

Hu,

Wan

2023

Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing

View full text Add to dashboard Cite

Neural machine translation has achieved great success in the past few years with the help of transformer architectures and large-scale bilingual corpora. However, when the source text gradually grows into an entire document, the performance of current methods for documentlevel machine translation (DocMT) is less satisfactory. Although the context is beneficial to the translation in general, it is difficult for traditional methods to utilize such long-range information. Previous studies on DocMT have concentrated on extra contents such as multiple surrounding sentences and input instances divided by a fixed length. We suppose that they ignore the structure inside the source text, which leads to under-utilization of the context. In this paper, we present a more sound paragraph-to-paragraph translation mode and explore whether discourse structure can improve DocMT. We introduce several methods from different perspectives, among which our RST-Att model with a multi-granularity attention mechanism based on the RST parsing tree works best. The experiments show that our method indeed utilizes discourse information and performs better than previous work.

show abstract

Bidirectional Macro-level Discourse Parser Based on Oracle Selection

Jiang

Bao

et al. 2022

Lecture Notes in Computer Science

View full text Add to dashboard Cite

A Language Model-based Generative Classifier for Sentence-level Discourse Parsing

Cited by 8 publications

References 23 publications

Immediate Processing of Sentences in Language Communication

Immediate Processing of Sentences in Language Communication

Exploring Discourse Structure in Document-level Machine Translation

Bidirectional Macro-level Discourse Parser Based on Oracle Selection

Contact Info

Product

Resources

About