paper-with-me

Papers

Compositional Semantics and Inference System for Temporal Order based on Japanese CCG

2022-04-20 · ACL 2022 5 · Tomoki Sugimoto, Hitomi Yanaka

Natural Language Inference (NLI) is the task of determining whether a premise entails a hypothesis. NLI with temporal order is a challenging task because tense and aspect are complex linguistic phenomena involving interactions with temporal adverbs and temporal connectives. To tackle this, temporal and aspectual inference has been analyzed in various ways in the field of formal semantics. However, a Japanese NLI system for temporal order based on the analysis of formal semantics has not been sufficiently developed. We present a logic-based NLI system that considers temporal order in Japanese based on compositional semantics via Combinatory Categorial Grammar (CCG) syntactic analysis. Our system performs inference involving temporal order by using axioms for temporal relations and automated theorem provers. We evaluate our system by experimenting with Japanese NLI datasets that involve temporal order. We show that our system outperforms previous logic-based systems as well as current deep learning-based models.

📄 PDF Abstract BibTeX arXiv:2204.09245

Code (1)

ynklab/ccgtemp 공식 구현

Tasks

Natural Language Inference

Similar Papers 제목 키워드 기반

Building compositional semantics and higher-order inference system for a wide-coverage Japanese CCG parser

2016-11-01 · EMNLP 2016 11 · Koji Mineshima, Ribeka Tanaka, Pascual Mart{\'\i}nez-G{\'o}mez, Yusuke Miyao 외
Dependency ParsingNatural Language InferenceQuestion AnsweringSemantic Parsing

Higher-order logical inference with compositional semantics

2015-09-01 · EMNLP 2015 9 · Koji Mineshima, Pascual Mart{\'\i}nez-G{\'o}mez, Yusuke Miyao, Daisuke Bekki
Semantic Composition

Variational Cross-Graph Reasoning and Adaptive Structured Semantics Learning for Compositional Temporal Grounding

2023-01-22 · Juncheng Li, Siliang Tang, Linchao Zhu, Wenqiao Zhang 외

Temporal grounding is the task of locating a specific segment from an untrimmed video according to a query sentence. This task has achieved significant momentum in the computer vision community as it enables activity gro…

DiversitySemantic correspondenceSentence

Compositional Active Inference II: Polynomial Dynamics. Approximate Inference Doctrines

2022-08-25 · Toby St. Clere Smithe

We develop the compositional theory of active inference by introducing activity, functorially relating statistical games to the dynamical systems which play them, using the new notion of approximate inference doctrine. I…

A CCG-based Compositional Semantics and Inference System for Comparatives

2019-10-02 · Izumi Haruta, Koji Mineshima, Daisuke Bekki

Comparative constructions play an important role in natural language inference. However, attempts to study semantic representations and logical inferences for comparatives from the computational perspective are not well …

Natural Language Inference