Search Results for author:
Found 32 papers, 7 papers with code
On the Effects of Video Grounding on Language Models
The results show that the smaller model benefits from video grounding in predicting highly imageable words, while the results for the larger model seem harder to interpret. of lack of grounding, e. g., addressing issues like models’ insufficient commonsense knowledge.
Tractable Parsing for CCGs of Bounded Degree
Unlike other mildly context-sensitive formalisms, Combinatory Categorial Grammar (CCG) cannot be parsed in polynomial time when the size of the grammar is taken into account.
Test Harder than You Train: Probing with Extrapolation Splits
Previous work on probing word representations for linguistic knowledge has focused on interpolation tasks.
Where Does Linguistic Information Emerge in Neural Language Models? Measuring Gains and Contributions across Layers
Probing studies have extensively explored where in neural language models linguistic information is located.
Fact Recall, Heuristics or Pure Guesswork? Precise Interpretations of Language Models for Fact Completion
Previous interpretations of language models (LMs) miss important distinctions in how these models process factual information.
NL2Plan: Robust LLM-Driven Planning from Minimal Text Descriptions
Today's classical planners are powerful, but modeling input tasks in formats such as PDDL is tedious and error-prone.
Properties and Challenges of LLM-Generated Explanations
The properties of the generated explanations are influenced by the pre-training corpus and by the target data used for instruction fine-tuning.
How Reliable Are Automatic Evaluation Methods for Instruction-Tuned LLMs?
In evaluating how well automatic methods align with human evaluations, correlation metrics are the most commonly employed method despite their inherent limitations when dealing with ties and different scales.
Flexible Distribution Alignment: Towards Long-tailed Semi-supervised Learning with Proper Calibration
Long-tailed semi-supervised learning (LTSSL) represents a practical scenario for semi-supervised applications, challenged by skewed labeled distributions that bias classifiers.
Surface-Based Retrieval Reduces Perplexity of Retrieval-Augmented Language Models
Inspired by this, we replace the semantic retrieval in Retro with a surface-level method based on BM25, obtaining a significant reduction in perplexity.
On the Generalization Ability of Retrieval-Enhanced Transformers
Recent work on the Retrieval-Enhanced Transformer (RETRO) model has shown that off-loading memory from trainable weights to a retrieval database can significantly improve language modeling and match the performance of non-retrieval models that are an order of magnitude larger in size.
Balanced Product of Calibrated Experts for Long-Tailed Recognition
We show how to properly define these distributions and combine the experts in order to achieve unbiased predictions, by proving that the ensemble is Fisher-consistent for minimizing the balanced error.
Long-tail Learning
Long-tail Learning on CIFAR-10-LT (ρ=100)
+1
Classifier Probes May Just Learn from Linear Context Features
Classifiers trained on auxiliary probing tasks are a popular tool to analyze the representations learned by neural sentence encoders such as BERT and ELMo.
End-to-End Negation Resolution as Graph Parsing
We present a neural end-to-end architecture for negation resolution based on a formulation of the task as a graph parsing problem.
MRP 2019: Cross-Framework Meaning Representation Parsing
The 2019 Shared Task at the Conference for Computational Language Learning (CoNLL) was devoted to Meaning Representation Parsing (MRP) across frameworks.
Improving Semantic Dependency Parsing with Syntactic Features
We extend a state-of-the-art deep neural architecture for semantic dependency parsing with features defined over syntactic dependency trees.
Exploiting Structure in Parsing to 1-Endpoint-Crossing Graphs
Deep dependency parsing can be cast as the search for maximum acyclic subgraphs in weighted digraphs.
On the Complexity of CCG Parsing
We study the parsing complexity of Combinatory Categorial Grammar (CCG) in the formalism of Vijay-Shanker and Weir (1994).
Towards Comparability of Linguistic Graph Banks for Semantic Parsing
We announce a new language resource for research on semantic parsing, a large, carefully curated collection of semantic dependency graphs representing multiple linguistic traditions.
Parsing to Noncrossing Dependency Graphs
We study the generalization of maximum spanning tree dependency parsing to maximum acyclic subgraphs.
A New Parsing Algorithm for Combinatory Categorial Grammar
We present a polynomial-time parsing algorithm for CCG, based on a new decomposition of derivations into small, shareable parts.
Efficient Parsing for Head-Split Dependency Trees
Head splitting techniques have been successfully exploited to improve the asymptotic runtime of parsing algorithms for projective dependency trees, under the arc-factored model.
