Distilling Hypernymy Relations from Language Models: On the Effectiveness of Zero-Shot Taxonomy Induction (2022.starsem-1)
Copied to clipboard
| Challenge: | Earlier approaches to taxonomy learning focused on mining lexico-syntactic patterns from candidate pairs. |
| Approach: | They propose to use prompts to distill knowledge from language models to refine methods . they also show that linguistic properties of prompts dictate downstream performance . |
| Outcome: | The proposed methods outperform some supervised strategies and are competitive with the current state-of-the-art under adequate conditions. |
Similar Papers
Relevance, Diversity, and Exclusivity: Designing Keyword-augmentation Strategy for Zero-shot Classifiers (2024.starsem-1)
Copied to clipboard
| Challenge: | Existing methods incorporate semantically similar keywords related to class names, but the properties of effective keywords remain unclear. |
| Approach: | They propose a method for acquiring keywords that satisfy these properties without additional knowledge bases or data. |
| Outcome: | The proposed method outperforms existing methods in fully zero-shot and generalized zero- shot settings. |
Exploring Factual Entailment with NLI: A News Media Study (2024.starsem-1)
Copied to clipboard
| Challenge: | Recent studies have focused on the relationship between factuality and Natural Language Inference (NLI). |
| Approach: | They propose a novel annotation scheme that models factual rather than textual entailment and use it to annotate a dataset of naturally occurring sentences from news articles. |
| Outcome: | The proposed annotation scheme can be used to model factual relationships on a dataset of naturally occurring sentences from news articles. |
What do Large Language Models Learn about Scripts? (2022.starsem-1)
Copied to clipboard
| Challenge: | Script Knowledge is important for language understanding but expensive to produce manually and difficult to induce from text due to reporting bias. |
| Approach: | They propose a pipeline-based script induction framework which can generate good quality ESDs for unseen scenarios. |
| Outcome: | The proposed framework produces good quality ESDs for unseen scenarios, but manual evaluation shows there is room for improvement. |
PISA: A measure of Preference In Selection of Arguments to model verb argument recoverability (2020.starsem-1)
Copied to clipboard
| Challenge: | a computational model of the semantic recoverability of verb arguments is tested on direct objects and Instruments. |
| Approach: | They propose a computational model of the semantic recoverability of verb arguments . they use a selectional preference model to compute selectional preferences of verbs . |
| Outcome: | The proposed model can predict the recoverability of objects and Instruments at a much cheaper computational cost. |
Seeking Clozure: Robust Hypernym extraction from BERT with Anchored Prompts (2023.starsem-1)
Copied to clipboard
| Challenge: | Existing methods for extracting hypernym knowledge from large language models are unclear whether they fail due to a lack of knowledge or shortcomings. |
| Approach: | They propose to use pattern-based hypernym extraction as a diagnostic tool to examine hypernomy knowledge encoded in BERT. |
| Outcome: | The proposed method compares the results of two different methods on six English data sets and on challenge sets of rare and abstract concepts. |
Guiding Zero-Shot Paraphrase Generation with Fine-Grained Control Tokens (2023.starsem-1)
Copied to clipboard
| Challenge: | Sequence-to-sequence paraphrase generation models struggle with the generation of diverse paraphrases. |
| Approach: | They propose a translation-based guided paraphrase generation model that learns useful features for promoting surface form variation in generated paraphrases from cross-lingual parallel data. |
| Outcome: | The proposed model learns useful features for promoting surface form variation in generated paraphrases from cross-lingual parallel data. |
Teach the Rules, Provide the Facts: Targeted Relational-knowledge Enhancement for Textual Inference (2021.starsem-1)
Copied to clipboard
| Challenge: | InferBERT is a method to enhance transformer-based inference models with relevant relational knowledge. |
| Approach: | They propose to enhance transformer-based inference models with relevant relational knowledge by injecting relevant facts at test time into the model. |
| Outcome: | The proposed method outperforms existing models on the challenge datasets while outperforming existing models. |
A Generative Approach for Mitigating Structural Biases in Natural Language Inference (2022.starsem-1)
Copied to clipboard
| Challenge: | Natural language inference datasets contain artifacts and biases that allow models to perform poorly by using a biased subset of the input without considering the remainder features. |
| Approach: | They reformulate a natural language inference task as a generative task . they find that this approach is highly robust to large amounts of bias . |
| Outcome: | The proposed model is highly robust to large amounts of bias. |
When Polysemy Matters: Modeling Semantic Categorization with Word Embeddings (2022.starsem-1)
Copied to clipboard
| Challenge: | Recent work using word embeddings to model semantic categorization has shown that static models outperform contextual models. |
| Approach: | They consider polysemy as a possible confounding factor in categorization decisions . they compare sense-level embeddings with previously studied static embedds . |
| Outcome: | The proposed model outperforms static models on coarse- and fine-grained categorization tasks. |
Limits for learning with language models (2023.starsem-1)
Copied to clipboard
| Challenge: | Recent studies show that large language models fail to capture important aspects of linguistic meaning . authors argue that LLMs cannot learn fundamental semantic properties defined in formal semantics . |
| Approach: | They propose a theoretical explanation for some of the observed failings of large language models . they show that LLMs cannot learn certain fundamental semantic properties . |
| Outcome: | The proposed model fails to learn semantic entailment and consistency as defined in formal semantics, the authors argue . their model fails on tasks that require engorgements and deep linguistic understanding, they argue - but not on universal quantification. |