paper-with-me

홈 › Papers

Vec2Sent: Probing Sentence Embeddings with Natural Language Generation

2020-11-01 · COLING 2020 8 · Martin Kerscher, Steffen Eger

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.

📄 PDF Abstract BibTeX arXiv:2011.00592

Code (1)

maruker/vec2sent 공식 구현 pytorch

Tasks

SentenceSentence EmbeddingsText Generation

Similar Papers 제목 키워드 기반

How to Probe Sentence Embeddings in Low-Resource Languages: On Structural Design Choices for Probing Task Evaluation

2020-06-16 · CONLL 2020 · Steffen Eger, Johannes Daxenberger, Iryna Gurevych

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 Embeddings

Empirical Linguistic Study of Sentence Embeddings

2019-07-01 · ACL 2019 7 · Katarzyna Krasnowska-Kiera{\'s}, Alina Wr{\'o}blewska

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 Embeddings

Probing the Probing Paradigm: Does Probing Accuracy Entail Task Relevance?

2020-05-02 · EACL 2021 2 · Abhilasha Ravichander, Yonatan Belinkov, Eduard Hovy

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 Embeddings

Sentence Embeddings in NLI with Iterative Refinement Encoders

2018-08-27 · Aarne Talman, Anssi Yli-Jyrä, Jörg Tiedemann

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+2

Universal Text Representation from BERT: An Empirical Study

2019-10-17 · Xiaofei Ma, Zhiguo Wang, Patrick Ng, Ramesh Nallapati 외

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