Search Results for author:
Found 18 papers, 10 papers with code
Monotonic Representation of Numeric Properties in Language Models
Language models (LMs) can express factual knowledge involving numeric properties such as Karl Popper was born in 1902.
Test-time Augmentation for Factual Probing
Factual probing is a method that uses prompts to test if a language model "knows" certain world knowledge facts.
Prompting for explanations improves Adversarial NLI. Is this true? {Yes} it is {true} because {it weakens superficial cues}
Explanation prompts ask language models to not only assign a particular label to a giveninput, such as true, entailment, or contradiction in the case of natural language inference but also to generate a free-text explanation that supports this label.
Ranked #1 on
Natural Language Inference
on ANLI test
Tracing and Manipulating Intermediate Values in Neural Math Problem Solvers
Previous research has shown that information about intermediate values of these inputs can be extracted from the activations of the models, but it is unclear where that information is encoded and whether that information is indeed used during inference.
BLOOM: A 176B-Parameter Open-Access Multilingual Language Model
Large language models (LLMs) have been shown to be able to perform new tasks based on a few demonstrations or natural language instructions.
Cross-stitching Text and Knowledge Graph Encoders for Distantly Supervised Relation Extraction
They either do not allow any sharing between the text encoder and the KG encoder at all, or, in case of models with KG-to-text attention, only share information in one direction.
COPA-SSE: Semi-structured Explanations for Commonsense Reasoning
We present Semi-Structured Explanations for COPA (COPA-SSE), a new crowdsourced dataset of 9, 747 semi-structured, English common sense explanations for Choice of Plausible Alternatives (COPA) questions.
Learning to Learn to be Right for the Right Reasons
Here, we propose to explicitly learn a model that does well on both the easy test set with superficial cues and hard test set without superficial cues.
Language Models as Knowledge Bases: On Entity Representations, Storage Capacity, and Paraphrased Queries
Pretrained language models have been suggested as a possible alternative or complement to structured knowledge bases.
When Choosing Plausible Alternatives, Clever Hans can be Clever
Pretrained language models, such as BERT and RoBERTa, have shown large improvements in the commonsense reasoning benchmark COPA.
Riposte! A Large Corpus of Counter-Arguments
Counter-arguments (CAs), one form of constructive feedback, have been proven to be useful for critical thinking skills.
On the Importance of Subword Information for Morphological Tasks in Truly Low-Resource Languages
Recent work has validated the importance of subword information for word representation learning.
Fine-Grained Entity Typing in Hyperbolic Space
How can we represent hierarchical information present in large type inventories for entity typing?
Sequence Tagging with Contextual and Non-Contextual Subword Representations: A Multilingual Evaluation
Pretrained contextual and non-contextual subword embeddings have become available in over 250 languages, allowing massively multilingual NLP.
Ranked #3 on
Part-Of-Speech Tagging
on UD
BPEmb: Tokenization-free Pre-trained Subword Embeddings in 275 Languages
We present BPEmb, a collection of pre-trained subword unit embeddings in 275 languages, based on Byte-Pair Encoding (BPE).
Revisiting Selectional Preferences for Coreference Resolution
Selectional preferences have long been claimed to be essential for coreference resolution.
Trust, but Verify! Better Entity Linking through Automatic Verification
We introduce automatic verification as a post-processing step for entity linking (EL).
