Deriving Word Vectors from Contextualized Language Models using Topic-Aware Mention Selection

Abstract

One of the long-standing challenges in lexical semantics consists in learning representations of words which reflect their semantic properties. The remarkable success of word embeddings for this purpose suggests that highquality representations can be obtained by summarizing the sentence contexts of word mentions. In this paper, we propose a method for learning word representations that follows this basic strategy, but differs from standard word embeddings in two important ways. First, we take advantage of contextualized language models (CLMs) rather than bags of word vectors to encode contexts. Second, rather than learning a word vector directly, we use a topic model to partition the contexts in which words appear, and then learn different topic-specific vectors for each word. Finally, we use a taskspecific supervision signal to make a soft selection of the resulting vectors. We show that this simple strategy leads to high-quality word vectors, which are more predictive of semantic properties than word embeddings and existing CLM-based strategies.

Topics in Contextualised Attention Embeddings

“…They have used BERT-base final layer's [CLS] token embedding as the corresponding embedding of an input document. Wang et al, [55] have argued that BERT contextual embedding can be improved by adding topical information to it. In their study, BERT embedding was derived from topics in the corpus.…”