Papers by Kristina Gulordava
Towards Incremental Learning of Word Embeddings Using Context Informativeness (P19-2)
Copied to clipboard
| Challenge: | In this paper, we investigate the task of learning word embeddings from very sparse data in an incremental, cognitively-plausible way. |
| Approach: | They propose a model that incorporates informativeness into a proposed model of nonce learning, using it for context selection and learning rate modulation. |
| Outcome: | The proposed model is based on a proposed model of nonce learning, and it performs well on the task of learning new words from definitions and potentially uninformative contexts. |
Probing for Referential Information in Language Models (2020.acl-main)
Copied to clipboard
| Challenge: | Neural network-based language models (LMs) have been shown to learn relevant properties of language without being explicitly trained for them. |
| Approach: | They extend their previous work to analyze whether language models capture anaphoric relations and pronoun-antecedent relations in English. |
| Outcome: | The Transformer outperforms the LSTM in all analyses. |
Putting Words in Context: LSTM Language Models and Lexical Ambiguity (P19-1)
Copied to clipboard
| Challenge: | In language, a word can contribute a very different meaning depending on the context . lexical ambiguity involves both morphosyntactic and semantic aspects . |
| Approach: | They propose a method to probe hidden representations for lexical and contextual information about words. |
| Outcome: | The proposed method shows that both types of information are represented to a large extent, but there is room for improvement for contextual information. |
Colorless Green Recurrent Networks Dream Hierarchically (N18-1)
Copied to clipboard
| Challenge: | Recurrent neural networks (RNNs) can induce non-trivial properties of language. |
| Approach: | They investigate whether RNNs can track hierarchical syntactic structure . they include nonsensical sentences where RNN cannot rely on semantic cues . |
| Outcome: | The proposed models can predict long-distance agreement in nonsensical sentences in Italian and English. |
How to represent a word and predict it, too: Improving tied architectures for language modelling (D18-1)
Copied to clipboard
| Challenge: | Recent state-of-the-art models use word embeddings as input and output mappings instead of tied models. |
| Approach: | They propose to decouple hidden state from word embedding prediction . they extend their proposed modification to word2vec models . |
| Outcome: | The proposed architectures achieve comparable or better results compared to previous models without tying . the proposed architecture reduces parameters, enabling more compact models and faster learning. |