Distributional Inclusion Hypothesis for Tensor-based Composition
According to the distributional inclusion hypothesis, entailment between words can be measured via the feature inclusions of their distributional vectors. In recent work, we showed how this hypothesis can be extended from words to phrases and sentences in the setting of compositional distributional semantics. This paper focuses on inclusion properties of tensors; its main contribution is a theoretical and experimental analysis of how feature inclusion works in different concrete models of verb tensors. We present results for relational, Frobenius, projective, and holistic methods and compare them to the simple vector addition, multiplication, min, and max models. The degrees of entailment thus obtained are evaluated via a variety of existing word-based measures, such as Weed's and Clarke's, KL-divergence, APinc, balAPinc, and two of our previously proposed metrics at the phrase/sentence level. We perform experiments on three entailment datasets, investigating which version of tensor-based composition achieves the highest performance when combined with the sentence-level measures.
Code (0)
등록된 구현이 없습니다.
Tasks
SentenceSimilar Papers 제목 키워드 기반
Resolving Lexical Ambiguity in Tensor Regression Models of Meaning
This paper provides a method for improving tensor-based compositional distributional models of meaning by the addition of an explicit disambiguation step prior to composition. In contrast with previous research where thi…
regressionDistributional Inclusion Hypothesis and Quantifications: Probing for Hypernymy in Functional Distributional Semantics
Functional Distributional Semantics (FDS) models the meaning of words by truth-conditional functions. This provides a natural representation for hypernymy but no guarantee that it can be learnt when FDS models are traine…
Towards a Formal Distributional Semantics: Simulating Logical Calculi with Tensors
The development of compositional distributional models of semantics reconciling the empirical aspects of distributional semantics with the compositional aspects of formal semantics is a popular topic in the contemporary …
RelationLow-Rank Tensors for Verbs in Compositional Distributional Semantics
DisCoCLIP: A Distributional Compositional Tensor Network Encoder for Vision-Language Understanding
Recent vision-language models excel at large-scale image-text alignment but often neglect the compositional structure of language, leading to failures on tasks that hinge on word order and predicate-argument structure. W…