Multi-Modal Representations for Improved Bilingual Lexicon Learning
نویسندگان
چکیده
Recent work has revealed the potential of using visual representations for bilingual lexicon learning (BLL). Such image-based BLL methods, however, still fall short of linguistic approaches. In this paper, we propose a simple yet effective multimodal approach that learns bilingual semantic representations that fuse linguistic and visual input. These new bilingual multi-modal embeddings display significant performance gains in the BLL task for three language pairs on two benchmarking test sets, outperforming linguistic-only BLL models using three different types of state-of-the-art bilingual word embeddings, as well as visual-only BLL models.
منابع مشابه
On multiword lexical units and their role in maritime dictionaries
Multi-word lexical units are a typical feature of specialized dictionaries, in particular monolingual and bilingual maritime dictionaries. The paper studies the concept of the multi-word lexical unit and considers the similarities and differences of their selection and presentation in monolingual and bilingual maritime dictionaries. The work analyses such issues as the classification of multi-w...
متن کاملBilingual Distributed Word Representations from Document-Aligned Comparable Data
We propose a new model for learning bilingual word representations from non-parallel document-aligned data. Following the recent advances in word representation learning, our model learns dense real-valued word vectors, that is, bilingual word embeddings (BWEs). Unlike prior work on inducing BWEs which heavily relied on parallel sentence-aligned corpora and/or readily available translation reso...
متن کاملBilingual Lexicon Induction by Learning to Combine Word-Level and Character-Level Representations
We study the problem of bilingual lexicon induction (BLI) in a setting where some translation resources are available, but unknown translations are sought for certain, possibly domain-specific terminology. We frame BLI as a classification problem for which we design a neural network based classification architecture composed of recurrent long short-term memory and deep feed forward networks. Th...
متن کاملBilingual Lexical Representation in a Self-Organizing Neural Network Model
In this paper we present a self-organizing neural network model of bilingual lexical development. We focus on how the representational structure of the bilingual lexicon can emerge, develop, and change as a function of the learning history. Our results show that (1) distinct representations for the two lexicons can develop in our network during simultaneous acquisition, (2) the representational...
متن کاملLimitations of Cross-Lingual Learning from Image Search
Cross-lingual representation learning is an important step in making NLP scale to all the world’s languages. Recent work on bilingual lexicon induction suggests that it is possible to learn cross-lingual representations of words based on similarities between images associated with these words. However, that work focused on the translation of selected nouns only. In our work, we investigate whet...
متن کامل