Learning Bilingual Sentiment-Specific Word Embeddings without Cross-lingual Supervision

Feng, Yanlin; Wan, Xiaojun

doi:10.18653/v1/n19-1040

Cited by 10 publications

(8 citation statements)

References 20 publications

(31 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The fitness function for sentiment analysis was based on a state-of-theart sentiment analysis model (Feng and Wan 2019). However, based on our evaluation, it failed miserably.…”

Section: Exposing the Internals For Evaluationmentioning

confidence: 99%

Computational Understanding, Generation and Evaluation of Creative Expressions

Alnajjar¹

2021

Preprint

View full text Add to dashboard Cite

Computational creativity has received a good amount of research interest in generating creative artefacts programmatically. At the same time, research has been conducted in computational aesthetics, which essentially tries to analyse creativity exhibited in art. This thesis aims to unite these two distinct lines of research in the context of natural language generation by building, from models for interpretation and generation, a cohesive whole that can assess its own generations. I present a novel method for interpreting one of the most difficult rhetoric devices in the figurative use of language: metaphors. The method does not rely on hand-annotated data and it is purely data-driven. It obtains the state of the art results and is comparable to the interpretations given by humans. We show how a metaphor interpretation model can be used in generating metaphors and metaphorical expressions. Furthermore, as a creative natural language generation task, we demonstrate assigning creative names to colours using an algorithmic approach that leverages a knowledge base of stereotypical associations for colours. Colour names produced by the approach were favoured by human judges to names given by humans 70% of the time. A genetic algorithm-based method is elaborated for slogan generation. The use of a genetic algorithm makes it possible to model the generation of text while optimising multiple fitness functions, as part of the evolutionary process, to assess the aesthetic quality of the output. Our evaluation indicates that having multiple balanced aesthetics outperforms a single maximised aesthetic. From an interplay of neural networks and the traditional AI approach of genetic algorithms, we present a symbiotic framework. This is called the master-apprentice framework. This makes it possible for the system to produce more diverse output as the neural network can learn from both the genetic algorithm and real people. The master-apprentice framework emphasises a strong theoretical foundation for the creative problem one seeks to solve. From this theoretical foundation, a reasoned evaluation method can be derived. This thesis presents two different evaluation practices based on two different theories on computational creativity. This research is conducted in two distinct practical tasks: pun generation in English and poetry generation in Finnish.

show abstract

“…The fitness function for sentiment analysis was based on a state-of-theart sentiment analysis model (Feng and Wan 2019). However, based on our evaluation, it failed miserably.…”

Section: Exposing the Internals For Evaluationmentioning

confidence: 99%

Computational Understanding, Generation and Evaluation of Creative Expressions

Alnajjar¹

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…UBiSE [5] presents a projection approach based on bilingual sentiment-specific word embeddings without any cross-lingual supervision, thus reducing resource requirements to a minimum: Only relying on a labeled sentiment corpus in the source language, as well as monolingual embeddings for both languages, their method outperforms Bilingual Sentiment Embeddings (BLSE) [1] on online customer reviews. In light of our results presented in this paper, it remains to be evaluated as to whether UBiSE can be scaled to technical domains as well.…”

Section: Cross-lingual Transfer Learningmentioning

confidence: 99%

Leveraging Linguistic Linked Data for Cross-Lingual Model Transfer in the Pharmaceutical Domain

Gracia

Fäth

Hartung³

et al. 2020

Lecture Notes in Computer Science

View full text Add to dashboard Cite

We describe the use of linguistic linked data to support a cross-lingual transfer framework for sentiment analysis in the pharmaceutical domain. The proposed system dynamically gathers translations from the Linked Open Data (LOD) cloud, particularly from Apertium RDF, in order to project a deep learning-based sentiment classifier from one language to another, thus enabling scalability and avoiding the need of model re-training when transferred across languages. We describe the whole pipeline traversed by the multilingual data, from their conversion into RDF based on a new dynamic and flexible transformation framework, through their linking and publication as linked data, and finally their exploitation in the particular use case. Based on experiments on projecting a sentiment classifier from English to Spanish, we demonstrate how linked data techniques are able to enhance the multilingual capabilities of a deep learning-based approach in a dynamic and scalable way, in a real application scenario from the pharmaceutical domain.

show abstract

“…To capture sentiment in poetry, we use an already existing recent state of the art approach (Feng & Wan, 2019) as one of the fitness functions. The approach made it possible to train a sentiment analyzer for Finnish without annotated data in Finnish.…”

Section: Aster As a G Enetic A Lgorithmmentioning

confidence: 99%

Generating Creative Language - Theories, Practice and Evaluation

Hämäläinen

2020

Preprint

View full text Add to dashboard Cite

This thesis presents approaches to computationally creative natural language generation focusing on theoretical foundations, practical solutions and evaluation. I defend that a theoretical definition is crucial for computational creativity and that the practical solution must closely follow the theoretical definition. Finally, evaluation must be based on the underlying theory and what was actually modelled in the practical solution. A theoretical void in the existing theoretical work on computational creativity is identified. The existing theories do not explicitly take into account the communicative nature of natural language. Therefore, a new theoretical framework is elaborated that identifies how computational creativity can take place in a setting that has a clear communicative goal. This introduces a communicative-creative trade off that sets limits to creativity in such a communicative context. My framework divides creativity in three categories: message creativity, contextual creativity and communicative creativity. Any computationally creative NLG approach not taking communicativity into account is called mere surface generation.I propose a novel master-apprentice approach for creative language generation. The approach consists of a genetic algorithm, the fitness functions of which correspond to different parameters defined as important for the creative task in question from a theoretical perspective. The output of the genetic algorithm together with possible human authored data are used to train the apprentice, which is a sequence-to-sequence neural network model. The role of the apprentice in the system is to approximate creative autonomy.Evaluation is approached from three different perspectives in this work: ad-hoc and abstract, theory-based and abstract, and theory-based and concrete. The first perspective is the most common one in the current literature and its shortcomings are demonstrated and discussed. This starts a gradual shift towards more meaningful evaluation by first using proper theories to define the task being modelled and finally reducing the room for subjective interpretation by suggesting the use of concrete evaluation questions.

show abstract

Learning Bilingual Sentiment-Specific Word Embeddings without Cross-lingual Supervision

Cited by 10 publications

References 20 publications

Computational Understanding, Generation and Evaluation of Creative Expressions

Computational Understanding, Generation and Evaluation of Creative Expressions

Leveraging Linguistic Linked Data for Cross-Lingual Model Transfer in the Pharmaceutical Domain

Generating Creative Language - Theories, Practice and Evaluation

Contact Info

Product

Resources

About