TaxiNLI: Taking a Ride up the NLU Hill

• URL: http://arxiv.org/abs/2009.14505v3
• Date: Fri, 9 Oct 2020 11:07:49 GMT
• Title: TaxiNLI: Taking a Ride up the NLU Hill
• Authors: Pratik Joshi, Somak Aditya, Aalok Sathe, Monojit Choudhury
• Abstract summary: Pre-trained Transformer-based neural architectures have consistently achieved state-of-the-art performance in the Natural Language Inference (NLI) task. We propose a taxonomic hierarchy of categories that are relevant for the NLI task. We observe that whereas for certain categories SOTA neural models have achieved near perfect accuracies, some categories still remain difficult.
• Score: 11.022738161410157
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Pre-trained Transformer-based neural architectures have consistently achieved state-of-the-art performance in the Natural Language Inference (NLI) task. Since NLI examples encompass a variety of linguistic, logical, and reasoning phenomena, it remains unclear as to which specific concepts are learnt by the trained systems and where they can achieve strong generalization. To investigate this question, we propose a taxonomic hierarchy of categories that are relevant for the NLI task. We introduce TAXINLI, a new dataset, that has 10k examples from the MNLI dataset (Williams et al., 2018) with these taxonomic labels. Through various experiments on TAXINLI, we observe that whereas for certain taxonomic categories SOTA neural models have achieved near perfect accuracies - a large jump over the previous models - some categories still remain difficult. Our work adds to the growing body of literature that shows the gaps in the current NLI systems and datasets through a systematic presentation and analysis of reasoning categories.

Related papers

• Are Large Language Models Good Classifiers? A Study on Edit Intent Classification in Scientific Document Revisions [62.12545440385489]
  Large language models (LLMs) have brought substantial advancements in text generation, but their potential for enhancing classification tasks remains underexplored. We propose a framework for thoroughly investigating fine-tuning LLMs for classification, including both generation- and encoding-based approaches. We instantiate this framework in edit intent classification (EIC), a challenging and underexplored classification task.
  arXiv  Detail & Related papers  (2024-10-02T20:48:28Z)
• Understanding Survey Paper Taxonomy about Large Language Models via Graph Representation Learning [2.88268082568407]
  We develop a method to automatically assign survey papers to a taxonomy. Our work indicates that leveraging graph structure information on co-category graphs can significantly outperform the language models.
  arXiv  Detail & Related papers  (2024-02-16T02:21:59Z)
• Natural Language Processing for Dialects of a Language: A Survey [56.93337350526933]
  State-of-the-art natural language processing (NLP) models are trained on massive training corpora, and report a superlative performance on evaluation datasets. This survey delves into an important attribute of these datasets: the dialect of a language. Motivated by the performance degradation of NLP models for dialectic datasets and its implications for the equity of language technologies, we survey past research in NLP for dialects in terms of datasets, and approaches.
  arXiv  Detail & Related papers  (2024-01-11T03:04:38Z)
• Prompting or Fine-tuning? A Comparative Study of Large Language Models for Taxonomy Construction [0.8670827427401335]
  We present a general framework for taxonomy construction that takes into account structural constraints. We compare the prompting and fine-tuning approaches performed on a hypernym taxonomy and a novel computer science taxonomy dataset.
  arXiv  Detail & Related papers  (2023-09-04T16:53:17Z)
• Taxonomy Enrichment with Text and Graph Vector Representations [61.814256012166794]
  We address the problem of taxonomy enrichment which aims at adding new words to the existing taxonomy. We present a new method that allows achieving high results on this task with little effort. We achieve state-of-the-art results across different datasets and provide an in-depth error analysis of mistakes.
  arXiv  Detail & Related papers  (2022-01-21T09:01:12Z)
• Dynamic Inference with Neural Interpreters [72.90231306252007]
  We present Neural Interpreters, an architecture that factorizes inference in a self-attention network as a system of modules. inputs to the model are routed through a sequence of functions in a way that is end-to-end learned. We show that Neural Interpreters perform on par with the vision transformer using fewer parameters, while being transferrable to a new task in a sample efficient manner.
  arXiv  Detail & Related papers  (2021-10-12T23:22:45Z)
• Unsupervised Pre-training with Structured Knowledge for Improving Natural Language Inference [22.648536283569747]
  We propose models that leverage structured knowledge in different components of pre-trained models. Our results show that the proposed models perform better than previous BERT-based state-of-the-art models.
  arXiv  Detail & Related papers  (2021-09-08T21:28:12Z)
• The NLP Cookbook: Modern Recipes for Transformer based Deep Learning Architectures [0.0]
  Natural Language Processing models have achieved phenomenal success in linguistic and semantic tasks. Recent NLP architectures have utilized concepts of transfer learning, pruning, quantization, and knowledge distillation to achieve moderate model sizes. Knowledge Retrievers have been built to extricate explicit data documents from a large corpus of databases with greater efficiency and accuracy.
  arXiv  Detail & Related papers  (2021-03-23T22:38:20Z)
• Discriminatively-Tuned Generative Classifiers for Robust Natural Language Inference [59.62779187457773]
  We propose a generative classifier for natural language inference (NLI) We compare it to five baselines, including discriminative models and large-scale pretrained language representation models like BERT. Experiments show that GenNLI outperforms both discriminative and pretrained baselines across several challenging NLI experimental settings.
  arXiv  Detail & Related papers  (2020-10-08T04:44:00Z)
• Reading Comprehension as Natural Language Inference: A Semantic Analysis [15.624486319943015]
  We explore the utility of Natural language Inference (NLI) for Question Answering (QA) We transform the one of the largest available MRC dataset (RACE) to an NLI form, and compare the performances of a state-of-the-art model (RoBERTa) on both forms. We highlight clear categories for which the model is able to perform better when the data is presented in a coherent entailment form, and a structured question-answer concatenation form.
  arXiv  Detail & Related papers  (2020-10-04T22:50:59Z)
• Logical Natural Language Generation from Open-Domain Tables [107.04385677577862]
  We propose a new task where a model is tasked with generating natural language statements that can be emphlogically entailed by the facts. To facilitate the study of the proposed logical NLG problem, we use the existing TabFact dataset citechen 2019tabfact featured with a wide range of logical/symbolic inferences. The new task poses challenges to the existing monotonic generation frameworks due to the mismatch between sequence order and logical order.
  arXiv  Detail & Related papers  (2020-04-22T06:03:10Z)

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.