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

Chrome logo Add to Chrome

Firefox logo Add to Firefox

"Text": models, code, and papers

Human Judgement as a Compass to Navigate Automatic Metrics for Formality Transfer

Apr 15, 2022
Huiyuan Lai, Jiali Mao, Antonio Toral, Malvina Nissim

Although text style transfer has witnessed rapid development in recent years, there is as yet no established standard for evaluation, which is performed using several automatic metrics, lacking the possibility of always resorting to human judgement. We focus on the task of formality transfer, and on the three aspects that are usually evaluated: style strength, content preservation, and fluency. To cast light on how such aspects are assessed by common and new metrics, we run a human-based evaluation and perform a rich correlation analysis. We are then able to offer some recommendations on the use of such metrics in formality transfer, also with an eye to their generalisability (or not) to related tasks.

* Accepted to HumEval 2022 

  Access Paper or Ask Questions

MMER: Multimodal Multi-task learning for Emotion Recognition in Spoken Utterances

Apr 01, 2022
Harshvardhan Srivastava, Sreyan Ghosh, S. Umesh

Emotion Recognition (ER) aims to classify human utterances into different emotion categories. Based on early-fusion and self-attention-based multimodal interaction between text and acoustic modalities, in this paper, we propose a multimodal multitask learning approach for ER from individual utterances in isolation. Experiments on the IEMOCAP benchmark show that our proposed model performs better than our re-implementation of state-of-the-art and achieves better performance than all other unimodal and multimodal approaches in literature. In addition, strong baselines and ablation studies prove the effectiveness of our proposed approach. We make all our codes publicly available on GitHub.

* Submitted to Interspeech 2022 

  Access Paper or Ask Questions

Top-Down Influence? Predicting CEO Personality and Risk Impact from Speech Transcripts

Jan 19, 2022
Kilian Theil, Dirk Hovy, Heiner Stuckenschmidt

How much does a CEO's personality impact the performance of their company? Management theory posits a great influence, but it is difficult to show empirically -- there is a lack of publicly available self-reported personality data of top managers. Instead, we propose a text-based personality regressor using crowd-sourced Myers--Briggs Type Indicator (MBTI) assessments. The ratings have a high internal and external validity and can be predicted with moderate to strong correlations for three out of four dimensions. Providing evidence for the upper echelons theory, we demonstrate that the predicted CEO personalities have explanatory power of financial risk.

  Access Paper or Ask Questions

Improve Sentence Alignment by Divide-and-conquer

Jan 18, 2022
Wu Zhang

In this paper, we introduce a divide-and-conquer algorithm to improve sentence alignment speed. We utilize external bilingual sentence embeddings to find accurate hard delimiters for the parallel texts to be aligned. We use Monte Carlo simulation to show experimentally that using this divide-and-conquer algorithm, we can turn any quadratic time complexity sentence alignment algorithm into an algorithm with average time complexity of O(NlogN). On a standard OCR-generated dataset, our method improves the Bleualign baseline by 3 F1 points. Besides, when computational resources are restricted, our algorithm is faster than Vecalign in practice.

  Access Paper or Ask Questions

Inter-Sense: An Investigation of Sensory Blending in Fiction

Oct 19, 2021
Roxana Girju, Charlotte Lambert

This study reports on the semantic organization of English sensory descriptors of the five basic senses of sight, hearing, touch, taste, and smell in a large corpus of over 8,000 fiction books. We introduce a large-scale text data-driven approach based on distributional-semantic word embeddings to identify and extract these descriptors as well as analyze their mixing interconnections in the resulting conceptual and sensory space. The findings are relevant for research on concept acquisition and representation, as well as for applications that can benefit from a better understanding of perceptual spaces of sensory experiences, in fiction, in particular, and in language in general.

* 2021 
* 18 pages 

  Access Paper or Ask Questions

Are you doing what I say? On modalities alignment in ALFRED

Oct 12, 2021
Ting-Rui Chiang, Yi-Ting Yeh, Ta-Chung Chi, Yau-Shian Wang

ALFRED is a recently proposed benchmark that requires a model to complete tasks in simulated house environments specified by instructions in natural language. We hypothesize that key to success is accurately aligning the text modality with visual inputs. Motivated by this, we inspect how well existing models can align these modalities using our proposed intrinsic metric, boundary adherence score (BAS). The results show the previous models are indeed failing to perform proper alignment. To address this issue, we introduce approaches aimed at improving model alignment and demonstrate how improved alignment, improves end task performance.

* Accepted by Novel Ideas in Learning-to-Learn through Interaction at EMNLP 2021 

  Access Paper or Ask Questions

On Bi-gram Graph Attributes

Jul 05, 2021
Thomas Konstantinovsky, Matan Mizrachi

We propose a new approach to text semantic analysis and general corpus analysis using, as termed in this article, a "bi-gram graph" representation of a corpus. The different attributes derived from graph theory are measured and analyzed as unique insights or against other corpus graphs. We observe a vast domain of tools and algorithms that can be developed on top of the graph representation; creating such a graph proves to be computationally cheap, and much of the heavy lifting is achieved via basic graph calculations. Furthermore, we showcase the different use-cases for the bi-gram graphs and how scalable it proves to be when dealing with large datasets.

* 7 pages,8 figures 

  Access Paper or Ask Questions

UoT-UWF-PartAI at SemEval-2021 Task 5: Self Attention Based Bi-GRU with Multi-Embedding Representation for Toxicity Highlighter

Apr 27, 2021
Hamed Babaei Giglou, Taher Rahgooy, Mostafa Rahgouy, Jafar Razmara

Toxic Spans Detection(TSD) task is defined as highlighting spans that make a text toxic. Many works have been done to classify a given comment or document as toxic or non-toxic. However, none of those proposed models work at the token level. In this paper, we propose a self-attention-based bidirectional gated recurrent unit(BiGRU) with a multi-embedding representation of the tokens. Our proposed model enriches the representation by a combination of GPT-2, GloVe, and RoBERTa embeddings, which led to promising results. Experimental results show that our proposed approach is very effective in detecting span tokens.

* Accepted at SemEval-2021 Task 5: Toxic Spans Detection, ACL-IJCNLP 2021 

  Access Paper or Ask Questions

Automatic Post-Editing for Translating Chinese Novels to Vietnamese

Apr 25, 2021
Thanh Vu, Dai Quoc Nguyen

Automatic post-editing (APE) is an important remedy for reducing errors of raw translated texts that are produced by machine translation (MT) systems or software-aided translation. In this paper, we present the first attempt to tackle the APE task for Vietnamese. Specifically, we construct the first large-scale dataset of 5M Vietnamese translated and corrected sentence pairs. We then apply strong neural MT models to handle the APE task, using our constructed dataset. Experimental results from both automatic and human evaluations show the effectiveness of the neural MT models in handling the Vietnamese APE task.

  Access Paper or Ask Questions

Frustratingly Easy Edit-based Linguistic Steganography with a Masked Language Model

Apr 20, 2021
Honai Ueoka, Yugo Murawaki, Sadao Kurohashi

With advances in neural language models, the focus of linguistic steganography has shifted from edit-based approaches to generation-based ones. While the latter's payload capacity is impressive, generating genuine-looking texts remains challenging. In this paper, we revisit edit-based linguistic steganography, with the idea that a masked language model offers an off-the-shelf solution. The proposed method eliminates painstaking rule construction and has a high payload capacity for an edit-based model. It is also shown to be more secure against automatic detection than a generation-based method while offering better control of the security/payload capacity trade-off.

* 7 pages, 4 firgures 

  Access Paper or Ask Questions