Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

"Sentiment": models, code, and papers

Reinforcement Learning Based Text Style Transfer without Parallel Training Corpus

Apr 08, 2019
Hongyu Gong, Suma Bhat, Lingfei Wu, Jinjun Xiong, Wen-mei Hwu

Text style transfer rephrases a text from a source style (e.g., informal) to a target style (e.g., formal) while keeping its original meaning. Despite the success existing works have achieved using a parallel corpus for the two styles, transferring text style has proven significantly more challenging when there is no parallel training corpus. In this paper, we address this challenge by using a reinforcement-learning-based generator-evaluator architecture. Our generator employs an attention-based encoder-decoder to transfer a sentence from the source style to the target style. Our evaluator is an adversarially trained style discriminator with semantic and syntactic constraints that score the generated sentence for style, meaning preservation, and fluency. Experimental results on two different style transfer tasks (sentiment transfer and formality transfer) show that our model outperforms state-of-the-art approaches. Furthermore, we perform a manual evaluation that demonstrates the effectiveness of the proposed method using subjective metrics of generated text quality.

  Access Paper or Ask Questions

Anxious Depression Prediction in Real-time Social Data

Mar 25, 2019
Akshi Kumar, Aditi Sharma, Anshika Arora

Mental well-being and social media have been closely related domains of study. In this research a novel model, AD prediction model, for anxious depression prediction in real-time tweets is proposed. This mixed anxiety-depressive disorder is a predominantly associated with erratic thought process, restlessness and sleeplessness. Based on the linguistic cues and user posting patterns, the feature set is defined using a 5-tuple vector . An anxiety-related lexicon is built to detect the presence of anxiety indicators. Time and frequency of tweet is analyzed for irregularities and opinion polarity analytics is done to find inconsistencies in posting behaviour. The model is trained using three classifiers (multinomial na\"ive bayes, gradient boosting, and random forest) and majority voting using an ensemble voting classifier is done. Preliminary results are evaluated for tweets of sampled 100 users and the proposed model achieves a classification accuracy of 85.09%.

  Access Paper or Ask Questions

Quantum-inspired Complex Word Embedding

May 29, 2018
Qiuchi Li, Sagar Uprety, Benyou Wang, Dawei Song

A challenging task for word embeddings is to capture the emergent meaning or polarity of a combination of individual words. For example, existing approaches in word embeddings will assign high probabilities to the words "Penguin" and "Fly" if they frequently co-occur, but it fails to capture the fact that they occur in an opposite sense - Penguins do not fly. We hypothesize that humans do not associate a single polarity or sentiment to each word. The word contributes to the overall polarity of a combination of words depending upon which other words it is combined with. This is analogous to the behavior of microscopic particles which exist in all possible states at the same time and interfere with each other to give rise to new states depending upon their relative phases. We make use of the Hilbert Space representation of such particles in Quantum Mechanics where we subscribe a relative phase to each word, which is a complex number, and investigate two such quantum inspired models to derive the meaning of a combination of words. The proposed models achieve better performances than state-of-the-art non-quantum models on the binary sentence classification task.

* This paper has been accepted by the 3rd Workshop on Representation Learning for NLP (RepL4NLP) 

  Access Paper or Ask Questions

APR: Architectural Pattern Recommender

Mar 23, 2018
Shipra Sharma, Balwinder Sodhi

This paper proposes Architectural Pattern Recommender (APR) system which helps in such architecture selection process. Main contribution of this work is in replacing the manual effort required to identify and analyse relevant architectural patterns in context of a particular set of software requirements. Key input to APR is a set of architecturally significant use cases concerning the application being developed. Central idea of APR's design is two folds: a) transform the unstructured information about software architecture design into a structured form which is suitable for recognizing textual entailment between a requirement scenario and a potential architectural pattern. b) leverage the rich experiential knowledge embedded in discussions on professional developer support forums such as Stackoverflow to check the sentiment about a design decision. APR makes use of both the above elements to identify a suitable architectural pattern and assess its suitability for a given set of requirements. Efficacy of APR has been evaluated by comparing its recommendations for "ground truth" scenarios (comprising of applications whose architecture is well known).

* Sharma, S., & Sodhi, B. (2017, April). APR: architectural pattern recommender. In Proceedings of the Symposium on Applied Computing (pp. 1225-1230). ACM 
* 6 Pages, 1 Figure. Published in SAC 2017 in Software Engineering Track 

  Access Paper or Ask Questions

Identity-sensitive Word Embedding through Heterogeneous Networks

Nov 29, 2016
Jian Tang, Meng Qu, Qiaozhu Mei

Most existing word embedding approaches do not distinguish the same words in different contexts, therefore ignoring their contextual meanings. As a result, the learned embeddings of these words are usually a mixture of multiple meanings. In this paper, we acknowledge multiple identities of the same word in different contexts and learn the \textbf{identity-sensitive} word embeddings. Based on an identity-labeled text corpora, a heterogeneous network of words and word identities is constructed to model different-levels of word co-occurrences. The heterogeneous network is further embedded into a low-dimensional space through a principled network embedding approach, through which we are able to obtain the embeddings of words and the embeddings of word identities. We study three different types of word identities including topics, sentiments and categories. Experimental results on real-world data sets show that the identity-sensitive word embeddings learned by our approach indeed capture different meanings of words and outperforms competitive methods on tasks including text classification and word similarity computation.

  Access Paper or Ask Questions

A Generative Word Embedding Model and its Low Rank Positive Semidefinite Solution

Aug 16, 2015
Shaohua Li, Jun Zhu, Chunyan Miao

Most existing word embedding methods can be categorized into Neural Embedding Models and Matrix Factorization (MF)-based methods. However some models are opaque to probabilistic interpretation, and MF-based methods, typically solved using Singular Value Decomposition (SVD), may incur loss of corpus information. In addition, it is desirable to incorporate global latent factors, such as topics, sentiments or writing styles, into the word embedding model. Since generative models provide a principled way to incorporate latent factors, we propose a generative word embedding model, which is easy to interpret, and can serve as a basis of more sophisticated latent factor models. The model inference reduces to a low rank weighted positive semidefinite approximation problem. Its optimization is approached by eigendecomposition on a submatrix, followed by online blockwise regression, which is scalable and avoids the information loss in SVD. In experiments on 7 common benchmark datasets, our vectors are competitive to word2vec, and better than other MF-based methods.

* Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP) 2015 2015, 11 pages, 2 figures 

  Access Paper or Ask Questions

Multiple Source Adaptation and the Renyi Divergence

May 09, 2012
Yishay Mansour, Mehryar Mohri, Afshin Rostamizadeh

This paper presents a novel theoretical study of the general problem of multiple source adaptation using the notion of Renyi divergence. Our results build on our previous work [12], but significantly broaden the scope of that work in several directions. We extend previous multiple source loss guarantees based on distribution weighted combinations to arbitrary target distributions P, not necessarily mixtures of the source distributions, analyze both known and unknown target distribution cases, and prove a lower bound. We further extend our bounds to deal with the case where the learner receives an approximate distribution for each source instead of the exact one, and show that similar loss guarantees can be achieved depending on the divergence between the approximate and true distributions. We also analyze the case where the labeling functions of the source domains are somewhat different. Finally, we report the results of experiments with both an artificial data set and a sentiment analysis task, showing the performance benefits of the distribution weighted combinations and the quality of our bounds based on the Renyi divergence.

* Appears in Proceedings of the Twenty-Fifth Conference on Uncertainty in Artificial Intelligence (UAI2009) 

  Access Paper or Ask Questions

Are Shortest Rationales the Best Explanations for Human Understanding?

Mar 16, 2022
Hua Shen, Tongshuang Wu, Wenbo Guo, Ting-Hao 'Kenneth' Huang

Existing self-explaining models typically favor extracting the shortest possible rationales - snippets of an input text "responsible for" corresponding output - to explain the model prediction, with the assumption that shorter rationales are more intuitive to humans. However, this assumption has yet to be validated. Is the shortest rationale indeed the most human-understandable? To answer this question, we design a self-explaining model, LimitedInk, which allows users to extract rationales at any target length. Compared to existing baselines, LimitedInk achieves compatible end-task performance and human-annotated rationale agreement, making it a suitable representation of the recent class of self-explaining models. We use LimitedInk to conduct a user study on the impact of rationale length, where we ask human judges to predict the sentiment label of documents based only on LimitedInk-generated rationales with different lengths. We show rationales that are too short do not help humans predict labels better than randomly masked text, suggesting the need for more careful design of the best human rationales.

* To appear in ACL 2022 main conference 

  Access Paper or Ask Questions

Academic Support Network Reflects Doctoral Experience and Productivity

Mar 07, 2022
Ozgur Can Seckin, Onur Varol

Current practices of quantifying performance by productivity leads serious concerns for psychological well-being of doctoral students and influence of research environment is often neglected in research evaluations. Acknowledgements in dissertations reflect the student experience and provide an opportunity to thank the people who support them. We conduct textual analysis of acknowledgments to build the "academic support network," uncovering five distinct communities: Academic, Administration, Family, Friends & Colleagues, and Spiritual; each of which is acknowledged differently by genders and disciplines. Female students mention fewer people from each community except for their families and total number of people mentioned in acknowledgements allows disciplines to be categorized as either individual science or team science. We also show that number of people mentioned from academic community is positively correlated with productivity and institutional rankings are found to be correlated with productivity and size of academic support networks but show no effect on students' sentiment on acknowledgements. Our results indicate the importance of academic support networks by explaining how they differ and how they influence productivity.

* 31 pages, 4 figures, 1 table 

  Access Paper or Ask Questions

DoCoGen: Domain Counterfactual Generation for Low Resource Domain Adaptation

Mar 05, 2022
Nitay Calderon, Eyal Ben-David, Amir Feder, Roi Reichart

Natural language processing (NLP) algorithms have become very successful, but they still struggle when applied to out-of-distribution examples. In this paper we propose a controllable generation approach in order to deal with this domain adaptation (DA) challenge. Given an input text example, our DoCoGen algorithm generates a domain-counterfactual textual example (D-con) - that is similar to the original in all aspects, including the task label, but its domain is changed to a desired one. Importantly, DoCoGen is trained using only unlabeled examples from multiple domains - no NLP task labels or parallel pairs of textual examples and their domain-counterfactuals are required. We show that DoCoGen can generate coherent counterfactuals consisting of multiple sentences. We use the D-cons generated by DoCoGen to augment a sentiment classifier and a multi-label intent classifier in 20 and 78 DA setups, respectively, where source-domain labeled data is scarce. Our model outperforms strong baselines and improves the accuracy of a state-of-the-art unsupervised DA algorithm.

* Our code and data are available at 

  Access Paper or Ask Questions