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. |
Similar Papers
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. |
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. |
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 . |
Quantifying Compositionality of Classic and State-of-the-Art Embeddings (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Static word embeddings make strong claims about compositionality, but the SOTA generative models go too far in the other direction. |
| Approach: | a new study evaluates the compositionality of word embeddings by canonical correlation analysis . strong compositional signals are observed in later training stages across data modalities . |
| Outcome: | a new evaluation of compositional models shows that they exploit access meanings when justified . strong compositional signals are observed in later training stages and in deeper layers of the transformer-based model before a decline at the top layer. |
Are the Best Multilingual Document Embeddings simply Based on Sentence Embeddings? (2023.findings-eacl)
Copied to clipboard
| Challenge: | obtaining document embeddings at document level is challenging due to computational requirements and lack of appropriate data. |
| Approach: | They compare methods to produce document-level representations from sentences based on LASER, LaBSE, and Sentence BERT pre-trained multilingual models. |
| Outcome: | The proposed methods produce document-level representations from sentences in 8 languages . the results show that a clever combination of sentence embeddings is usually better than encoding the full document as a single unit. |
Exploring Statistical and Neural Models for Noun Ellipsis Detection and Resolution in English (2020.aacl-srw)
Copied to clipboard
| Challenge: | Existing approaches to noun ellipsis resolution have been sparse, using syntactic feature constraints for marking licensors and selecting their antecedents. |
| Approach: | They propose to use supervised machine learning to improve the existing F1 score by 16.55% and resolution by 14.97% for noun ellipsis subtasks. |
| Outcome: | The proposed framework improves the existing F1 score by 16.55% and the resolution subtask by 14.97%. |
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. |
Additive Compositionality of Word Vectors (D19-55)
Copied to clipboard
| Challenge: | Existing research on justifying additive compositionality of word embedding models requires a rather strong assumption of uniform word distribution. |
| Approach: | They propose to relax the assumption of uniform word distribution and propose more realistic conditions for proving additive compositionality. |
| Outcome: | The proposed model improves on word similarity and noisy sentence similarity. |
Sentence Representations via Gaussian Embedding (2024.eacl-short)
Copied to clipboard
| Challenge: | Sentence embeddings represent a sentence's meaning as a point in a vector space and primarily use symmetric measures such as the cosine similarity to measure the similarity between sentences, they cannot capture asymmetric relationships between two sentences, such as entailment and hierarchical relations. |
| Approach: | They propose a Gaussian-distribution-based contrastive learning framework for sentence embedding that can handle asymmetric inter-sentential relations and a similarity measure for identifying entailment relations. |
| Outcome: | The proposed framework performs comparable to that of previous methods on natural language inference tasks and estimates direction of entailment relations, which is difficult with point representations. |
Is Language Modeling Enough? Evaluating Effective Embedding Combinations (2020.lrec-1)
Copied to clipboard
Rudolf Schneider, Tom Oberhauser, Paul Grundmann, Felix Alexander Gers, Alexander Loeser, Steffen Staab
| Challenge: | specialized embeddings are not available for tasks like entity linking or paragraph classification. |
| Approach: | They evaluate whether universal embeddings can be complemented by specialized embeddables. |
| Outcome: | The proposed embeddings outperform state-of-the-art embeddables without any fine-tuning. |