paper-with-me

Papers

Evaluating Compositionality in Sentence Embeddings

2018-02-12 · Ishita Dasgupta, Demi Guo, Andreas Stuhlmüller, Samuel J. Gershman, Noah D. Goodman

An important challenge for human-like AI is compositional semantics. Recent research has attempted to address this by using deep neural networks to learn vector space embeddings of sentences, which then serve as input to other tasks. We present a new dataset for one such task, `natural language inference' (NLI), that cannot be solved using only word-level knowledge and requires some compositionality. We find that the performance of state of the art sentence embeddings (InferSent; Conneau et al., 2017) on our new dataset is poor. We analyze the decision rules learned by InferSent and find that they are consistent with simple heuristics that are ecologically valid in its training dataset. Further, we find that augmenting training with our dataset improves test performance on our dataset without loss of performance on the original training dataset. This highlights the importance of structured datasets in better understanding and improving AI systems.

📄 PDF Abstract BibTeX arXiv:1802.04302

Code (1)

ishita-dg/ScrambleTests 공식 구현 pytorch

Tasks

Natural Language InferenceSentenceSentence Embeddingsvalid

Similar Papers 제목 키워드 기반

Evaluating Compositionality of Sentence Representation Models

2020-07-01 · WS 2020 7 · Hanoz Bhathena, Angelica Willis, Nathan Dass

We evaluate the compositionality of general-purpose sentence encoders by proposing two different metrics to quantify compositional understanding capability of sentence encoders. We introduce a novel metric, Polarity Sens…

SensitivitySentence

Quantifying Compositionality of Classic and State-of-the-Art Embeddings

2025-09-14 · Zhijin Guo, Chenhao Xue, Zhaozhen Xu, Hongbo Bo 외 arxiv

For language models to generalize correctly to novel expressions, it is critical that they exploit access compositional meanings when this is justified. Even if we don't know what a "pelp" is, we can use our knowledge of…

Knowledge Graphs

Comparing word2vec and GloVe for Automatic Measurement of MWE Compositionality

2020-12-01 · COLING (MWE) 2020 12 · Thomas Pickard

This paper explores the use of word2vec and GloVe embeddings for unsupervised measurement of the semantic compositionality of MWE candidates. Through comparison with several human-annotated reference sets, we find word2v…

Syntax-guided Neural Module Distillation to Probe Compositionality in Sentence Embeddings

2023-01-21 · Rohan Pandey

Past work probing compositionality in sentence embedding models faces issues determining the causal impact of implicit syntax representations. Given a sentence, we construct a neural module net based on its syntax parse …

Semantic CompositionSentenceSentence EmbeddingSentence-Embedding+1

Measuring Compositionality in Representation Learning

2019-02-19 · ICLR 2019 5 · Jacob Andreas

Many machine learning algorithms represent input data with vector embeddings or discrete codes. When inputs exhibit compositional structure (e.g. objects built from parts or procedures from subroutines), it is natural to…

BIG-bench Machine LearningRepresentation Learning