Search Results for author:
Found 8 papers, 4 papers with code
Challenges in including extra-linguistic context in pre-trained language models
To successfully account for language, computational models need to take into account both the linguistic context (the content of the utterances) and the extra-linguistic context (for instance, the participants in a dialogue).
Performance-Efficiency Trade-Offs in Adapting Language Models to Text Classification Tasks
Interestingly, we find that prompting combined with KD can reduce compute and data cost at the same time.
Does referent predictability affect the choice of referential form? A computational approach using masked coreference resolution
It is often posited that more predictable parts of a speaker's meaning tend to be made less explicit, for instance using shorter, less informative words.
The Language Model Understood the Prompt was Ambiguous: Probing Syntactic Uncertainty Through Generation
Temporary syntactic ambiguities arise when the beginning of a sentence is compatible with multiple syntactic analyses.
Putting words in context: LSTM language models and lexical ambiguity
In neural network models of language, words are commonly represented using context-invariant representations (word embeddings) which are then put in context in the hidden layers.
What do Entity-Centric Models Learn? Insights from Entity Linking in Multi-Party Dialogue
In this paper we analyze the behavior of two recently proposed entity-centric models in a referential task, Entity Linking in Multi-party Dialogue (SemEval 2018 Task 4).
How to represent a word and predict it, too: Improving tied architectures for language modelling
Recent state-of-the-art neural language models share the representations of words given by the input and output mappings.
AMORE-UPF at SemEval-2018 Task 4: BiLSTM with Entity Library
This paper describes our winning contribution to SemEval 2018 Task 4: Character Identification on Multiparty Dialogues.
