Parse Me if You Can: Artificial Treebanks for Parsing Experiments on Elliptical Constructions (L18-1)
Copied to clipboard
| Challenge: | ellipsis is a phenomenon present in many natural languages, but it complicates syntactic parsing of the content that is not omitted. |
| Approach: | They analyze outputs of state-of-the-art parsers to learn about parsing accuracy and typical errors from the perspective of elliptical constructions. |
| Outcome: | The proposed treebank is a semi-artificially constructed treebank of ellipsis. |
Similar Papers
Ellipsis-Dependent Reasoning: a New Challenge for Large Language Models (2023.acl-short)
Copied to clipboard
| Challenge: | a novel challenge for large language models is ellipsis-dependent reasoning . ellippsis occurs in all registers, where parts of sentences are omitted, but the missing parts are essential for understanding the meaning. |
| Approach: | They propose a challenge for large language models where ellipsis is paired with non-elliptical counterparts. |
| Outcome: | The proposed model performs well on non-elliptical examples but struggles with ellipsis structures . the proposed model fails on ellippsis-dependent reasoning . |
We Understand Elliptical Sentences, and Language Models should Too: A New Dataset for Studying Ellipsis and its Interaction with Thematic Fit (2023.acl-long)
Copied to clipboard
| Challenge: | ellipsis is a linguistic phenomenon characterized by the omission of one or more sentence elements. |
| Approach: | They investigated how prototypicality affects the ability of Language Models to handle elliptical sentences . they found that models were better suited to evaluating argument thematic fit . |
| Outcome: | The proposed dataset shows that the models perform better for typical events than for atypical ones in different elliptical contexts. |
Multitask Easy-First Dependency Parsing: Exploiting Complementarities of Different Dependency Representations (2020.coling-main)
Copied to clipboard
| Challenge: | Existing dependency parsing models for Arabic use complementary annotations, CATiB and UD treebanks, and partially created trees for one annotation are also available to the other as features for the score function. |
| Approach: | They propose to use Arabic dependency annotations to parse projective dependency trees using CATiB and UD treebanks. |
| Outcome: | The proposed model gives 9.9% error reduction on CATiB and 6.1% on UD compared to a strong baseline and ablation tests show that the main contribution is given by sharing tree representation between tasks, and not simply sharing biLSTM layers as is often performed in NLP multitask systems. |
Parser Training with Heterogeneous Treebanks (P18-2)
Copied to clipboard
| Challenge: | In the 2017 CoNLL Shared Task on Universal Dependency Parsing, 25 languages have more than one treebank . many teams did not take advantage of the multiple treebanks, however, and trained one model per treebank instead of one model for each language. |
| Approach: | They propose a method to make the most of heterogeneous treebanks when training a monolingual parser. |
| Outcome: | The proposed method improves on training with multiple treebanks for a single language. |
Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing: System Demonstrations (D18-2)
Copied to clipboard
| Challenge: | 77 submissions were received for the 2018 Conference on Empirical Methods in Natural Language Processing (EMNLP) 4 of the 73 valid submissions received were either invalid or withdrawn by the authors. |
| Approach: | The volume contains papers from the 2018 Conference on Empirical Methods in Natural Language Processing (EMNLP) 4 of the 77 submissions were either invalid or withdrawn by the authors. |
| Outcome: | The system demonstrations session included papers from the 2018 Conference on Empirical Methods in Natural Language Processing (EMNLP) 4 of the 73 valid submissions were either invalid or withdrawn by the authors. |
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations (2020.emnlp-demos)
Copied to clipboard
| Challenge: | 91 submissions were received, 10 of which were either invalid or withdrawn . |
| Approach: | 91 submissions were received for the system demonstrations session . 10 were either invalid or withdrawn by the authors . |
| Outcome: | The system demonstrations session was held at the 2020 conference on empirical methods in natural language processing . 91 submissions were accepted, 10 of which were either invalid or withdrawn . |
Dependency parsing with structure preserving embeddings (2021.eacl-main)
Copied to clipboard
| Challenge: | Modern neural approaches to dependency parsing are trained to predict a tree structure by learning a contextual representation for tokens in a sentence and a head–dependent scoring function. |
| Approach: | They propose to combine a contextual representation for tokens and a head–dependent scoring function to learn interpretable representations by training a parser to explicitly preserve structural properties of a tree. |
| Outcome: | The proposed approach yields strong tree distance preservation and parsing performance on par with a competitive graph-based parser. |
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing: System Demonstrations (2021.emnlp-demo)
Copied to clipboard
| Challenge: | . - (EN) |
| Approach: | . - (EN) |
| Outcome: | . - (EN) |
Evaluating Composition Models for Verb Phrase Elliptical Sentence Embeddings (N19-1)
Copied to clipboard
| Challenge: | ellipsis is a natural language phenomenon where part of a sentence is missing and its information must be recovered from its context. |
| Approach: | They develop models for embedding VP-elliptical sentences using word embeddments . they extend existing verb disambiguation and sentence similarity datasets to elliptic phrases . |
| Outcome: | The proposed models outperform existing models on verb disambiguation and sentence similarity datasets and their linear counterparts. |
NoEl: An Annotated Corpus for Noun Ellipsis in English (2020.lrec-1)
Copied to clipboard
| Challenge: | Ellipsis resolution is an important step to improve the accuracy of mainstream natural language processing tasks such as information retrieval, event extraction, dialog systems, etc. |
| Approach: | They extend the study of ellipsis by annotating a corpus for noun ellippsis and closely related phenomenon using the first hundred movies of Cornell Movie Dialogs Dataset. |
| Outcome: | The proposed corpus has 946 instances of exophoric and endophorical noun ellipsis, making it the biggest resource of nouns in English, to the best of our knowledge. |