Vec2Sent: Probing Sentence Embeddings with Natural Language Generation
We introspect black-box sentence embeddings by conditionally generating from them with the objective to retrieve the underlying discrete sentence. We perceive of this as a new unsupervised probing task and show that it correlates well with downstream task performance. We also illustrate how the language generated from different encoders differs. We apply our approach to generate sentence analogies from sentence embeddings.
Code (1)
Tasks
SentenceSentence EmbeddingsText GenerationSimilar Papers 제목 키워드 기반
How to Probe Sentence Embeddings in Low-Resource Languages: On Structural Design Choices for Probing Task Evaluation
Sentence encoders map sentences to real valued vectors for use in downstream applications. To peek into these representations - e.g., to increase interpretability of their results - probing tasks have been designed which…
SentenceSentence EmbeddingsEmpirical Linguistic Study of Sentence Embeddings
The purpose of the research is to answer the question whether linguistic information is retained in vector representations of sentences. We introduce a method of analysing the content of sentence embeddings based on univ…
SentenceSentence EmbeddingsProbing the Probing Paradigm: Does Probing Accuracy Entail Task Relevance?
Although neural models have achieved impressive results on several NLP benchmarks, little is understood about the mechanisms they use to perform language tasks. Thus, much recent attention has been devoted to analyzing t…
Natural Language InferenceSentenceWord EmbeddingsSentence Embeddings in NLI with Iterative Refinement Encoders
Sentence-level representations are necessary for various NLP tasks. Recurrent neural networks have proven to be very effective in learning distributed representations and can be trained efficiently on natural language in…
Natural Language InferenceSentenceSentence EmbeddingSentence-Embedding+2Universal Text Representation from BERT: An Empirical Study
We present a systematic investigation of layer-wise BERT activations for general-purpose text representations to understand what linguistic information they capture and how transferable they are across different tasks. S…
Learning-To-RankNatural Language InferenceQuestion AnsweringSemantic Similarity+2