paper-with-me

홈 › Papers

Specialising Word Vectors for Lexical Entailment

2018-06-01 · NAACL 2018 6 · Ivan Vuli{\'c}, Nikola Mrk{\v{s}}i{\'c}

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. By injecting external linguistic constraints (e.g., WordNet links) into the initial vector space, the LE specialisation procedure brings true hyponymy-hypernymy pairs closer together in the transformed Euclidean space. The proposed asymmetric distance measure adjusts the norms of word vectors to reflect the actual WordNet-style hierarchy of concepts. Simultaneously, a joint objective enforces semantic similarity using the symmetric cosine distance, yielding a vector space specialised for both lexical relations at once. LEAR specialisation achieves state-of-the-art performance in the tasks of hypernymy directionality, hypernymy detection, and graded lexical entailment, demonstrating the effectiveness and robustness of the proposed asymmetric specialisation model.

📄 PDF Abstract BibTeX

Code (1)

nmrksic/lear 공식 구현 tf

Tasks

Dialogue State TrackingLexical EntailmentMachine TranslationNatural Language InferenceRelationRepresentation LearningSemantic SimilaritySemantic Textual SimilarityText GenerationWord Embeddings

Similar Papers 제목 키워드 기반

Specialising Word Vectors for Lexical Entailment

2017-10-17 · Ivan Vulić, Nikola Mrkšić

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 hy…

Lexical EntailmentRelationSemantic SimilaritySemantic Textual Similarity

Embedding WordNet Knowledge for Textual Entailment

2018-08-01 · COLING 2018 8 · Yunshi Lan, Jing Jiang

In this paper, we study how we can improve a deep learning approach to textual entailment by incorporating lexical entailment relations from WordNet. Our idea is to embed the lexical entailment knowledge contained in Wor…

Feature EngineeringLexical EntailmentNatural Language Inference

Generalized Tuning of Distributional Word Vectors for Monolingual and Cross-Lingual Lexical Entailment

2019-07-01 · ACL 2019 7 · Goran Glava{\v{s}}, Ivan Vuli{\'c}

Lexical entailment (LE; also known as hyponymy-hypernymy or is-a relation) is a core asymmetric lexical relation that supports tasks like taxonomy induction and text generation. In this work, we propose a simple and effe…

Lexical EntailmentRelationText Generation

Post-Specialisation: Retrofitting Vectors of Words Unseen in Lexical Resources

2018-05-08 · NAACL 2018 6 · Ivan Vulić, Goran Glavaš, Nikola Mrkšić, Anna Korhonen

Word vector specialisation (also known as retrofitting) is a portable, light-weight approach to fine-tuning arbitrary distributional word vector spaces by injecting external knowledge from rich lexical resources such as …

Dialogue State TrackingText SimplificationWord Similarity

Learning Word Embeddings for Hyponymy with Entailment-Based Distributional Semantics

2017-10-06 · James Henderson

Lexical entailment, such as hyponymy, is a fundamental issue in the semantics of natural language. This paper proposes distributional semantic models which efficiently learn word embeddings for entailment, using a recent…

Learning Word EmbeddingsLexical EntailmentWord Embeddings