• Publications
  • Influence
Combining Language and Vision with a Multimodal Skip-gram Model
TLDR
Since they propagate visual information to all words, the MMSKIP-GRAM models discover intriguing visual properties of abstract words, paving the way to realistic implementations of embodied theories of meaning. Expand
Jointly optimizing word representations for lexical and sentential tasks with the C-PHRASE model
TLDR
C-PHRASE, a distributional semantic model that learns word representations by optimizing context prediction for phrases at all levels in a syntactic tree, outperforms the state-of-theart C-BOW model on a variety of lexical tasks. Expand
DISSECT - DIStributional SEmantics Composition Toolkit
TLDR
DISSECT can be useful to researchers and practitioners who need models of word meaning (without composition) as well, as it supports various methods to construct distributional semantic spaces, assessing similarity and even evaluating against benchmarks, that are independent of the composition infrastructure. Expand
A practical and linguistically-motivated approach to compositional distributional semantics
TLDR
A new model that closely mimics the standard Montagovian semantic treatment of composition in distributional terms is presented, showing that it consistently outperforms a set of competitive rivals. Expand
General estimation and evaluation of compositional distributional semantic models
TLDR
An evaluation of alternative cDSMs under truly comparable conditions is presented, and the linguistically motivated functional model of Baroni and Zamparelli and Coecke et al. (2010) emerges as the winner in all the authors' tests. Expand
Intensionality was only alleged: On adjective-noun composition in distributional semantics
TLDR
This work acknowledges the support of Spanish MICINN grant FFI2010-09464-E (Mcnally, Boleda), the ICREA Foundation (McNally), Catalan AGAUR grant 2010BP-A00070 (Baroni, Pham). Expand
A Multitask Objective to Inject Lexical Contrast into Distributional Semantics
TLDR
The multitask Lexical Contrast Model (mLCM), an extension of the effective Skip-gram method that optimizes semantic vectors on the joint tasks of predicting corpus contexts and making the representations of WordNet synonyms closer than that of matching WordNet antonyms, is introduced. Expand
Sentence paraphrase detection: When determiners and word order make the difference
TLDR
An evaluation task is presented that highlights some differences among the CDSMs currently available by challenging them in detecting semantic differences caused by word order switch and by determiner replacements. Expand
Towards Multi-Agent Communication-Based Language Learning
TLDR
An interactive multimodal framework for language learning where learners engage in cooperative referential games starting from a tabula rasa setup, and thus develop their own language from the need to communicate in order to succeed at the game. Expand
A Large-Scale Multi-Document Summarization Dataset from the Wikipedia Current Events Portal
TLDR
This work presents a new dataset for MDS that is large both in the total number of document clusters and in the size of individual clusters, and provides a quantitative analysis of the dataset and empirical results for several state-of-the-art MDS techniques. Expand
...
1
2
...