About

Lexical Entailment is concerned with identifying the semantic relation, if any, holding between two words, as in (pigeon, hyponym, animal).

Source: Integrating Multiplicative Features into Supervised Distributional Methods for Lexical Entailment

Benchmarks

TREND DATASET BEST METHOD PAPER TITLE PAPER CODE COMPARE

Datasets

Greatest papers with code

TextAttack: A Framework for Adversarial Attacks, Data Augmentation, and Adversarial Training in NLP

29 Apr 2020QData/TextAttack

TextAttack also includes data augmentation and adversarial training modules for using components of adversarial attacks to improve model accuracy and robustness.

ADVERSARIAL ATTACK ADVERSARIAL TEXT DATA AUGMENTATION LEXICAL ENTAILMENT MACHINE TRANSLATION TEXT CLASSIFICATION

A Consolidated Open Knowledge Representation for Multiple Texts

WS 2017 vered1986/OKR

We propose to move from Open Information Extraction (OIE) ahead to Open Knowledge Representation (OKR), aiming to represent information conveyed jointly in a set of texts in an open text-based manner.

LEXICAL ENTAILMENT OPEN INFORMATION EXTRACTION

Hierarchical Density Order Embeddings

ICLR 2018 benathi/density-order-emb

By representing words with probability densities rather than point vectors, probabilistic word embeddings can capture rich and interpretable semantic information and uncertainty.

LEXICAL ENTAILMENT WORD EMBEDDINGS

Discriminative Topic Mining via Category-Name Guided Text Embedding

20 Aug 2019yumeng5/CatE

We propose a new task, discriminative topic mining, which leverages a set of user-provided category names to mine discriminative topics from text corpora.

CLASSIFICATION DOCUMENT CLASSIFICATION LEXICAL ENTAILMENT TOPIC MODELS WEAKLY SUPERVISED CLASSIFICATION

Specialising Word Vectors for Lexical Entailment

NAACL 2018 nmrksic/lear

We present LEAR (Lexical Entailment Attract-Repel), a novel post-processing method that transforms any input word vector space to emphasise the asymmetric relation of lexical entailment (LE), also known as the IS-A or hyponymy-hypernymy relation.

DIALOGUE STATE TRACKING LEXICAL ENTAILMENT MACHINE TRANSLATION NATURAL LANGUAGE INFERENCE SEMANTIC SIMILARITY SEMANTIC TEXTUAL SIMILARITY TEXT GENERATION WORD EMBEDDINGS

Specialising Word Vectors for Lexical Entailment

17 Oct 2017nmrksic/lear

We present LEAR (Lexical Entailment Attract-Repel), a novel post-processing method that transforms any input word vector space to emphasise the asymmetric relation of lexical entailment (LE), also known as the IS-A or hyponymy-hypernymy relation.

LEXICAL ENTAILMENT SEMANTIC SIMILARITY SEMANTIC TEXTUAL SIMILARITY

Representing Meaning with a Combination of Logical and Distributional Models

CL 2016 ibeltagy/rrr

In this paper, we focus on the three components of a practical system integrating logical and distributional models: 1) Parsing and task representation is the logic-based part where input problems are represented in probabilistic logic.

LEXICAL ENTAILMENT NATURAL LANGUAGE INFERENCE

Mining Knowledge for Natural Language Inference from Wikipedia Categories

3 Oct 2020ZeweiChu/WikiNLI

Accurate lexical entailment (LE) and natural language inference (NLI) often require large quantities of costly annotations.

LEXICAL ENTAILMENT NATURAL LANGUAGE INFERENCE

Experiments with Three Approaches to Recognizing Lexical Entailment

31 Jan 2014context-mover/HypEval

Two general strategies for RLE have been proposed: One strategy is to manually construct an asymmetric similarity measure for context vectors (directional similarity) and another is to treat RLE as a problem of learning to recognize semantic relations using supervised machine learning techniques (relation classification).

CLASSIFICATION LEXICAL ENTAILMENT RELATION CLASSIFICATION

SherLIiC: A Typed Event-Focused Lexical Inference Benchmark for Evaluating Natural Language Inference

ACL 2019 mnschmit/SherLIiC

We present SherLIiC, a testbed for lexical inference in context (LIiC), consisting of 3985 manually annotated inference rule candidates (InfCands), accompanied by (i) ~960k unlabeled InfCands, and (ii) ~190k typed textual relations between Freebase entities extracted from the large entity-linked corpus ClueWeb09.

LEXICAL ENTAILMENT NATURAL LANGUAGE INFERENCE