Page: 1 2 3 4 5 6 7 8 9... 156
81 |
RuleBERT: Teaching Soft Rules to Pre-Trained Language Models ...
|
|
|
|
BASE
|
|
Show details
|
|
83 |
Implicit Premise Generation with Discourse-aware Commonsense Knowledge Models ...
|
|
|
|
BASE
|
|
Show details
|
|
84 |
The expression of emotions and their cultural ties to Pakistani, Somali and Yemeni patients' views of the world in cross-cultural therapy ...
|
|
|
|
BASE
|
|
Show details
|
|
85 |
On the Challenges of Evaluating Compositional Explanations in Multi-Hop Inference: Relevance, Completeness, and Expert Ratings ...
|
|
|
|
Abstract:
Anthology paper link: https://aclanthology.org/2021.emnlp-main.596/ Abstract: Building compositional explanations requires models to combine two or more facts that, together, describe why the answer to a question is correct. Typically, these "multi-hop" explanations are evaluated relative to one (or a small number of) gold explanations. In this work, we show these evaluations substantially underestimate model performance, both in terms of the relevance of included facts, as well as the completeness of model-generated explanations, because models regularly discover and produce valid explanations that are different than gold explanations. To address this, we construct a large corpus of 126k domain-expert (science teacher) relevance ratings that augment a corpus of explanations to standardized science exam questions, discovering 80k additional relevant facts not rated as gold. We build three strong models based on different methodologies (generation, ranking, and schemas), and empirically show that while ...
|
|
Keyword:
Language Models; Natural Language Processing; Semantic Evaluation; Sociolinguistics
|
|
URL: https://underline.io/lecture/37605-on-the-challenges-of-evaluating-compositional-explanations-in-multi-hop-inference-relevance,-completeness,-and-expert-ratings https://dx.doi.org/10.48448/0bb7-n351
|
|
BASE
|
|
Hide details
|
|
86 |
Is Everything in Order? A Simple Way to Order Sentences ...
|
|
|
|
BASE
|
|
Show details
|
|
87 |
Figures from "Perceptual Dialectology between Varieties of Irish English: Towards an Isogloss of Linguistic Boundaries on the Island of Ireland" ...
|
|
|
|
BASE
|
|
Show details
|
|
89 |
Presenting aggregate fieldwork data with statistical measures for the study of prepositional adverbials in Romance: a template. Tables to be filled in by the fieldworkers ...
|
|
|
|
BASE
|
|
Show details
|
|
90 |
Presenting aggregate fieldwork data with statistical measures for the study of prepositional adverbials in Romance: a template. Tables to be filled in by the fieldworkers ...
|
|
|
|
BASE
|
|
Show details
|
|
91 |
Rasgos del español guatemalteco en dos obras atribuidas a Sor Juana de Maldonado y Paz ...
|
|
|
|
BASE
|
|
Show details
|
|
92 |
Enhanced Language Representation with Label Knowledge for Span Extraction ...
|
|
|
|
BASE
|
|
Show details
|
|
93 |
Figures from "Perceptual Dialectology between Varieties of Irish English: Towards an Isogloss of Linguistic Boundaries on the Island of Ireland" ...
|
|
|
|
BASE
|
|
Show details
|
|
94 |
Gender-inclusive language among Italian non-binary individuals: a survey ...
|
|
|
|
BASE
|
|
Show details
|
|
95 |
The Devil is in the Detail: Simple Tricks Improve Systematic Generalization of Transformers ...
|
|
|
|
BASE
|
|
Show details
|
|
96 |
VeeAlign: Multifaceted Context Representation Using Dual Attention for Ontology Alignment ...
|
|
|
|
BASE
|
|
Show details
|
|
97 |
Shortcutted Commonsense: Data Spuriousness in Deep Learning of Commonsense Reasoning ...
|
|
|
|
BASE
|
|
Show details
|
|
98 |
On Classifying whether Two Texts are on the Same Side of an Argument ...
|
|
|
|
BASE
|
|
Show details
|
|
99 |
Causal Direction of Data Collection Matters: Implications of Causal and Anticausal Learning for NLP ...
|
|
|
|
BASE
|
|
Show details
|
|
100 |
MTAdam: Automatic Balancing of Multiple Training Loss Terms ...
|
|
|
|
BASE
|
|
Show details
|
|
Page: 1 2 3 4 5 6 7 8 9... 156
|
|