Challenge: a lack of understanding of the properties of sentence embeddings is limiting the use of the techniques.
Approach: They propose 10 probing tasks designed to capture simple linguistic features of sentences . they use three different encoders to train embeddings in eight different ways .
Outcome: The proposed tasks capture key linguistic features of sentences, but they are difficult to infer from them.

Similar Papers

Empirical Linguistic Study of Sentence Embeddings (P19-1)

Copied to clipboard

Challenge: a new method of analysing sentence embeddings shows that linguistic information is retained in the vector representations of sentences.
Approach: They propose a method of analysing the content of sentence embeddings based on probing tasks and contrasting languages.
Outcome: The proposed method is based on probing tasks and classification datasets for two contrasting languages.
Probing the Probing Paradigm: Does Probing Accuracy Entail Task Relevance? (2021.eacl-main)

Copied to clipboard

Challenge: Neural models have established state-of-the-art performance on several NLP benchmarks, but little is understood about the mechanisms by which they operate.
Approach: They examine the probing paradigm through a set of controlled synthetic tasks and show that pretrained word embeddings play a considerable role in encoding these properties rather than the training task itself.
Outcome: The proposed model can encode linguistic properties above chance-level even when distributed in the data as random noise, reversing the interpretation of absolute claims on probing tasks.
Learning Visually Grounded Sentence Representations (N18-1)

Copied to clipboard

Challenge: Unsupervised sentence representation models suffer from the grounding problem because of lack of association between symbols and external information.
Approach: They train a sentence encoder to predict image features of a caption and use them as sentence representations.
Outcome: The proposed model improves on word embeddings and word representations on standard benchmarks.
Exploring Semantic Properties of Sentence Embeddings (P18-2)

Copied to clipboard

Challenge: Neural vector representations are ubiquitous throughout all subfields of natural language processing.
Approach: They propose a framework that generates triplets of sentences to explore how changes in the syntactic structure or semantics of a given sentence affect their similarity.
Outcome: The proposed framework generates triplets of sentences to explore how changes in the syntactic structure or semantics of a given sentence affect the similarities obtained between their embeddings.
Probing Multimodal Embeddings for Linguistic Properties: the Visual-Semantic Case (2020.coling-main)

Copied to clipboard

Challenge: Semantic embeddings have advanced the state of the art for natural language processing tasks . but their inner workings are poorly understood and there is a shortage of analysis tools .
Approach: They propose to extend visual-semantic embeddings to multimodal domains by defining probing tasks for embeddable image-caption pairs and testing them with classifiers.
Outcome: The proposed probing tasks show up to 16% more accurate on visual-semantic embeddings compared to unimodal embedders . the proposed extensions to multimodal domains have been lauded as promising in natural language processing .
Probing Linguistic Features of Sentence-Level Representations in Neural Relation Extraction (2020.acl-main)

Copied to clipboard

Challenge: Neural relation extraction models capture linguistic and semantic properties of the input, a recent study shows.
Approach: They introduce 14 probing tasks targeting linguistic properties relevant to RE . they add contextualized word representations to enhance probing performance .
Outcome: The proposed models achieve state-of-the-art on two datasets, TACRED and SemEval 2010 Task 8 . they show that the models capture linguistic and semantic properties relevant to the downstream task .
Are the Best Multilingual Document Embeddings simply Based on Sentence Embeddings? (2023.findings-eacl)

Copied to clipboard

Challenge: obtaining document embeddings at document level is challenging due to computational requirements and lack of appropriate data.
Approach: They compare methods to produce document-level representations from sentences based on LASER, LaBSE, and Sentence BERT pre-trained multilingual models.
Outcome: The proposed methods produce document-level representations from sentences in 8 languages . the results show that a clever combination of sentence embeddings is usually better than encoding the full document as a single unit.
Classifier Probes May Just Learn from Linear Context Features (2020.coling-main)

Copied to clipboard

Challenge: Current probing methods can help to better estimate the complexity of learning, but not build a foundation for speculations about the nature of the linguistic structure encoded in the learned representations.
Approach: They propose to use token embeddings to test whether probing tasks contain linguistic structure . they argue that current probing methods do not provide enough information to support this hypothesis .
Outcome: The proposed method can be scrutinized and proves that representations encode linguistic structure even without additional linguistic structures.
Semantic Geometry of Sentence Embeddings (2025.findings-emnlp)

Copied to clipboard

Challenge: Sentence embeddings are central to natural language processing, but their internal features are not interpretable and users lack fine-grained control for downstream tasks.
Approach: They propose a formal framework to characterize the organization of features in sentence embeddings . they show how they can be composed to capture richer semantic structures .
Outcome: The proposed method can be used to capture richer semantic structures.
PWESuite: Phonetic Word Embeddings and Tasks They Facilitate (2024.lrec-main)

Copied to clipboard

Challenge: Existing word embedding methods overlook phonetic information that is crucial for many tasks.
Approach: They propose three methods that use articulatory features to build phonetically informed word embeddings.
Outcome: The proposed methods improve word retrieval and correlation with sound similarity and on rhyme and cognate detection tasks.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations