Papers by Felix Hill

5 papers
Can language models learn from explanations in context? (2022.findings-emnlp)

Copied to clipboard

Challenge: Language Models can adapt to a few in-context examples, but without training.
Approach: They examine how explanations of few-shot examples can help Language Models (LMs) explanations can improve performance even without tuning, they find .
Outcome: The proposed explanations outperform hand-tuned explanations on small validation sets.
Higher-order Comparisons of Sentence Encoder Representations (D19-1)

Copied to clipboard

Challenge: a technique developed by neuroscientists compares activity patterns of different measurement modalities . a recent study examined the correspondence between popular pretrained language encoders and human processing difficulty .
Approach: They employ a technique to compare activity patterns of different measurement modalities . they establish a correspondence between widely-employed pretrained language encoders and human processing difficulty .
Outcome: The proposed technique can be used to compare representational geometries of neural models . it does not require large training samples and is not prone to overfitting, authors say .
Know your audience: specializing grounded language models with listener subtraction (2023.eacl-main)

Copied to clipboard

Challenge: Effective communication requires adapting to the idiosyncrasies of each communicative context.
Approach: They propose a method for specializing grounded language models without supervision . they fine-tune an attention-based adapter between a CLIP vision encoder and a large language model .
Outcome: The proposed method allows a speaker to adapt to the idiosyncracies of the listeners without supervision.
Dialogue Structure Annotation for Multi-Floor Interaction (L18-1)

Copied to clipboard

Challenge: Existing annotation schemes do not address dialogue structure.
Approach: They propose an annotation scheme for meso-level dialogue structure that clusters utterances from multiple participants and floors into units according to realization of an initiator's intent.
Outcome: The proposed annotation scheme is used to annotate a corpus of human-robot interaction dialogues.
SCOUT: A Situated and Multi-Modal Human-Robot Dialogue Corpus (2024.lrec-main)

Copied to clipboard

Challenge: The corpus contains 89,056 utterances and 310,095 words from 278 dialogues averaging 320 utterrances per dialogue.
Approach: They present the Situated Corpus Of Understanding Transactions, a multi-modal collection of human-robot dialogue in the task domain of collaborative exploration.
Outcome: The Situated Corpus Of Understanding Transactions (SCOUT) contains 89,056 utterances and 310,095 words from 278 dialogues averaging 320 utterrances per dialogue.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations