How to make words with vectors: Phrase generation in distributional semantics

We introduce the problem of generation in distributional semantics: Given a distributional vector representing some meaning, how can we generate the phrase that best expresses that meaning? We motivate this novel challenge on theoretical and practical grounds and propose a simple data-driven approach to the estimation of generation functions. We test this in a monolingual scenario (paraphrase generation) as well as in a cross-lingual setting (translation by synthesizing adjectivenoun phrase vectors in English and generating the equivalent expressions in Italian).

• Publication year

  2014

• Venue

  Annual Meeting of the Association for Computational Linguistics

• Publication date

  2014-06-01

• Fields of study

  Linguistics, Computer Science

• Identifiers
  DOI 10.3115/v1/P14-1059
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Don’t count, predict! A systematic comparison of context-counting vs. context-predicting semantic vectors

  2014cited by this paper
• Grounded Compositional Semantics for Finding and Describing Images with Sentences

  2014cited by this paper
• Composition in Distributional Semantics

  2013cited by this paper
• DeViSE: A Deep Visual-Semantic Embedding Model

  2013cited by this paper
• Exploiting Similarities among Languages for Machine Translation

  2013influential reference
• Zero-Shot Learning Through Cross-Modal Transfer

  2013cited by this paper
• Efficient Estimation of Word Representations in Vector Space

  2013influential reference
• General estimation and evaluation of compositional distributional semantic models

  2013cited by this paper
• A Generative Model of Vector Space Semantics

  2013cited by this paper
• Recurrent Continuous Translation Models

  2013cited by this paper
• Domain and Function: A Dual-Space Model of Semantic Relations and Compositions

  2012cited by this paper
• Distributional Semantics in Technicolor

  2012influential reference
• Toward Statistical Machine Translation without Parallel Corpora

  2012cited by this paper
• Selecting Corpus-Semantic Models for Neurolinguistic Decoding

  2012cited by this paper
• A Comparison of Vector-based Representations for Semantic Composition

  2012cited by this paper
• Semi-supervised learning for automatic conceptual property extraction

  2012cited by this paper
• Parallel Data, Tools and Interfaces in OPUS

  2012cited by this paper
• Vector Space Models of Word Meaning and Phrase Meaning: A Survey

  2012cited by this paper
• A continuous semantic space describes the representation of thousands of object and action categories across the human brain.

  2012cited by this paper
• Dynamic Pooling and Unfolding Recursive Autoencoders for Paraphrase Detection

  2011cited by this paper
• From Frequency to Meaning: Vector Space Models of Semantics

  2010cited by this paper
• A Regression Model of Adjective-Noun Compositionality in Distributional Semantics

  2010cited by this paper
• Estimating Linear Models for Compositional Distributional Semantics

  2010cited by this paper
• Composition in Distributional Models of Semantics

  2010cited by this paper
• Nouns are Vectors, Adjectives are Matrices: Representing Adjective-Noun Constructions in Semantic Space

  2010cited by this paper
• Predicting Human Brain Activity Associated with the Meanings of Nouns

  2008cited by this paper
• Learning Bilingual Lexicons from Monolingual Corpora

  2008cited by this paper
• Vector-based Models of Semantic Composition

  2008cited by this paper
• Near-Optimal Hashing Algorithms for Approximate Nearest Neighbor in High Dimensions

  2006cited by this paper
• Learning a Translation Lexicon from Monolingual Corpora

  2002cited by this paper
• Distributed and Overlapping Representations of Faces and Objects in Ventral Temporal Cortex

  2001cited by this paper
• Automatic Identification of Word Translations from Unrelated English and German Corpora

  1999cited by this paper

• Montague semantics and modifier consistency measurement in neural language models

  2022cites this paper
• Aligning Word Vectors on Low-Resource Languages with Wiktionary

  2022cites this paper
• Discovering Bilingual Lexicons in Polyglot Word Embeddings

  2020cites this paper
• What Meaning-Form Correlation Has to Compose With: A Study of MFC on Artificial and Natural Language

  2020cites this paper
• Learning to detect visual relations

  2019cites this paper
• Can word vectors help corpus linguists?

  2019cites this paper
• A Survey of Zero-Shot Learning

  2019cites this paper
• An Unsupervised Query Rewriting Approach Using N-gram Co-occurrence Statistics to Find Similar Phrases in Large Text Corpora

  2019cites this paper
• How Much Competence Is There in Performance? Assessing the Distributional Hypothesis in Word Bigrams

  2019cites this paper
• Should All Cross-Lingual Embeddings Speak English?

  2019cites this paper
• Inspecting and Directing Neural Language Models

  2018cites this paper
• Optimal Low Rank Tensor Factorization for Deep Learning

  2018cites this paper
• NLG Challenge : Neural Models vs . Templates

  2018cites this paper
• Testing word embeddings for Polish

  2017cites this paper
• Domain Transfer for Deep Natural Language Generation from Abstract Meaning Representations

  2017cites this paper
• Modelling Sentence Generation from Sum of Word Embedding Vectors as a Mixed Integer Programming Problem

  2016influential citation
• Definition Modeling: Learning to Define Word Embeddings in Natural Language

  2016cites this paper
• Data-driven natural language generation using statistical machine translation and discriminative learning. (L'approche discriminante à la génération de la parole)

  2016influential citation
• Translation of Word Vectors by Exploiting Translatable Context Pairs

  2016cites this paper
• Constraining Word Embeddings by Prior Knowledge - Application to Medical Information Retrieval

  2016cites this paper
• Generating Bags of Words from the Sums of Their Word Embeddings

  2016cites this paper
• From Visual Attributes to Adjectives through Decompositional Distributional Semantics

  2015cites this paper
• Ridge Regression, Hubness, and Zero-Shot Learning

  2015influential citation
• How Deep is Your Bag of Words?

  2015cites this paper
• Learning Composition Models for Phrase Embeddings

  2015cites this paper
• Distributional Semantic Features as Semantic Primitives - Or Not

  2015cites this paper
• Formal versus Distributional Semantics of Natural Language : a Survey

  2015cites this paper
• Representing Meaning with a Combination of Logical and Distributional Models

  2015cites this paper
• Texts in, meaning out: neural language models in semantic similarity task for Russian

  2015influential citation
• Hubness and Pollution: Delving into Cross-Space Mapping for Zero-Shot Learning

  2015cites this paper
• Accurate Cross-lingual Projection between Count-based Word Vectors by Exploiting Translatable Context Pairs

  2015cites this paper
• Representing Meaning with a Combination of Logical Form and Vectors

  2015cites this paper
• New Directions in Vector Space Models of Meaning

  2014cites this paper
• Generating Sentences from Semantic Vector Space Representations

  2014cites this paper
• Semantic Composition and Decomposition: From Recognition to Generation

  2014cites this paper
• Improving zero-shot learning by mitigating the hubness problem

  2014cites this paper
• Factor-based Compositional Embedding Models

  2014cites this paper