Superlatives in Context: Explicit and Implicit Domain Restrictions for Superlative Frames
- URL: http://arxiv.org/abs/2405.20967v1
- Date: Fri, 31 May 2024 16:14:06 GMT
- Title: Superlatives in Context: Explicit and Implicit Domain Restrictions for Superlative Frames
- Authors: Valentina Pyatkin, Bonnie Webber, Ido Dagan, Reut Tsarfaty,
- Abstract summary: Superlatives are used to single out elements with a maximal/minimal property.
Superlatives provide an ideal phenomenon for studying implicit phenomena and discourse restrictions.
We show that the fine-grained semantics of superlatives in context can be challenging for contemporary models.
- Score: 31.063753498947346
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Superlatives are used to single out elements with a maximal/minimal property. Semantically, superlatives perform a set comparison: something (or some things) has the min/max property out of a set. As such, superlatives provide an ideal phenomenon for studying implicit phenomena and discourse restrictions. While this comparison set is often not explicitly defined, its (implicit) restrictions can be inferred from the discourse context the expression appears in. In this work we provide an extensive computational study on the semantics of superlatives. We propose a unified account of superlative semantics which allows us to derive a broad-coverage annotation schema. Using this unified schema we annotated a multi-domain dataset of superlatives and their semantic interpretations. We specifically focus on interpreting implicit or ambiguous superlative expressions, by analyzing how the discourse context restricts the set of interpretations. In a set of experiments we then analyze how well models perform at variations of predicting superlative semantics, with and without context. We show that the fine-grained semantics of superlatives in context can be challenging for contemporary models, including GPT-4.
Related papers
- UltraWiki: Ultra-fine-grained Entity Set Expansion with Negative Seed Entities [38.85274314130823]
We introduce negative seed entities in the inputs, which belong to the same fine-grained semantic class as the positive seed entities but differ in certain attributes.
Negative seed entities eliminate the semantic ambiguity by contrast between positive and negative attributes.
We devised three strategies to enhance models' comprehension of ultra-fine-grained entities semantics.
arXiv Detail & Related papers (2024-03-07T06:10:02Z) - Syntax and Semantics Meet in the "Middle": Probing the Syntax-Semantics
Interface of LMs Through Agentivity [68.8204255655161]
We present the semantic notion of agentivity as a case study for probing such interactions.
This suggests LMs may potentially serve as more useful tools for linguistic annotation, theory testing, and discovery.
arXiv Detail & Related papers (2023-05-29T16:24:01Z) - Entity Disambiguation with Entity Definitions [50.01142092276296]
Local models have recently attained astounding performances in Entity Disambiguation (ED)
Previous works limited their studies to using, as the textual representation of each candidate, only its Wikipedia title.
In this paper, we address this limitation and investigate to what extent more expressive textual representations can mitigate it.
We report a new state of the art on 2 out of 6 benchmarks we consider and strongly improve the generalization capability over unseen patterns.
arXiv Detail & Related papers (2022-10-11T17:46:28Z) - SDA: Simple Discrete Augmentation for Contrastive Sentence Representation Learning [14.028140579482688]
SimCSE surprisingly dominates discrete augmentations such as cropping, word deletion, and synonym replacement as reported.
We develop three simple yet effective discrete sentence augmentation schemes: punctuation insertion, modal verbs, and double negation.
Results support the superiority of the proposed methods consistently.
arXiv Detail & Related papers (2022-10-08T08:07:47Z) - UCTopic: Unsupervised Contrastive Learning for Phrase Representations
and Topic Mining [27.808028645942827]
UCTopic is a novel unsupervised contrastive learning framework for context-aware phrase representations and topic mining.
It is pretrained in a large scale to distinguish if the contexts of two phrase mentions have the same semantics.
It outperforms the state-of-the-art phrase representation model by 38.2% NMI in average on four entity cluster-ing tasks.
arXiv Detail & Related papers (2022-02-27T22:43:06Z) - Clustering and Network Analysis for the Embedding Spaces of Sentences
and Sub-Sentences [69.3939291118954]
This paper reports research on a set of comprehensive clustering and network analyses targeting sentence and sub-sentence embedding spaces.
Results show that one method generates the most clusterable embeddings.
In general, the embeddings of span sub-sentences have better clustering properties than the original sentences.
arXiv Detail & Related papers (2021-10-02T00:47:35Z) - Infusing Finetuning with Semantic Dependencies [62.37697048781823]
We show that, unlike syntax, semantics is not brought to the surface by today's pretrained models.
We then use convolutional graph encoders to explicitly incorporate semantic parses into task-specific finetuning.
arXiv Detail & Related papers (2020-12-10T01:27:24Z) - MAIRE -- A Model-Agnostic Interpretable Rule Extraction Procedure for
Explaining Classifiers [5.02231401459109]
The paper introduces a novel framework for extracting model-agnostic human interpretable rules to explain a classifier's output.
The framework is model agnostic, can be applied to any arbitrary classifier, and all types of attributes (including continuous, ordered, and unordered discrete)
arXiv Detail & Related papers (2020-11-03T06:53:06Z) - Recursive Rules with Aggregation: A Simple Unified Semantics [0.6662800021628273]
This paper describes a unified semantics for recursion with aggregation.
We present a formal definition of the semantics, prove important properties of the semantics, and compare with prior semantics.
We show that our semantics is simple and matches the desired results in all cases.
arXiv Detail & Related papers (2020-07-26T04:42:44Z) - How Far are We from Effective Context Modeling? An Exploratory Study on
Semantic Parsing in Context [59.13515950353125]
We present a grammar-based decoding semantic parsing and adapt typical context modeling methods on top of it.
We evaluate 13 context modeling methods on two large cross-domain datasets, and our best model achieves state-of-the-art performances.
arXiv Detail & Related papers (2020-02-03T11:28:10Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.