Dominican Republic

Recent progress in generative language models has enabled machines to generate astonishingly realistic texts. While there are many legitimate applications of such models, there is also a rising need to distinguish machine-generated texts from human-written ones (e.g., fake news detection). However, to our best knowledge, there is currently no benchmark environment with datasets and tasks to systematically study the so-called &quot;Turing Test&quot; problem for neural text generation methods. In this work, we present the TuringBench benchmark environment, which is comprised of (1) a dataset with 200K human- or machine-generated samples across 20 labels {Human, GPT-1, GPT-2_small, GPT-2_medium, GPT-2_large, GPT-2_xl, GPT-2_PyTorch, GPT-3, GROVER_base, GROVER_large, GROVER_mega, CTRL, XLM, XLNET_base, XLNET_large, FAIR_wmt19, FAIR_wmt20, TRANSFORMER_XL, PPLM_distil, PPLM_gpt2}, (2) two benchmark tasks -- i.e., Turing Test (TT) and Authorship Attribution (AA), and (3) a website with leaderboards. Our preliminary experimental results using TuringBench show that FAIR_wmt20 and GPT-3 are the current winners, among all language models tested, in generating the most human-like indistinguishable texts with the lowest F1 score by five state-of-the-art TT detection models. The TuringBench is available at: https://turingbench.ist.psu.edu/

EMNLP 2021

TuringBench: A Benchmark Environment for Turing Test in the Age of Neural Text Generation

EMNLP 2021 is planned to be a hybrid event in Punta Cana, Dominican Republic, with both on-site and fully virtual participation possible. The experience for on-site participants would closely approximate a normal pre-COVID *ACL conference, with 5-6 thematically organized parallel sessions and live Q/A and interactive discussion immediately after the talks. Presentations by virtual participants will be equitably interleaved with those of on-site participants, projected on the auditorium screens as if on-site, and also followed immediately by live Q/A and interactive discussion at a time during reasonable waking hours for the virtual presenter. For all participants, on-site and virtual, who are unable to attend a session due to either time-zone issues or because they are participating in another session live, talk recordings and slides will be available online at a minimum after the live presentation (and in many cases before as well), and questions may be submitted in advance on session-specific discussion boards and answered live in session with the usual visual aids if desired.

<iframe style="width:700px;height:400px" src="https://online.fliphtml5.com/ebtyf/ceby/"  seamless="seamless" scrolling="no" frameborder="0" allowtransparency="true" allowfullscreen="true" ></iframe>

Please Note: The EMNLP registration system is not currently connected to the underline site as we are still in the process of building out EMNLP 2021. You will receive access instructions from underline the week of November 1st. 

Access is given only to EMNLP upon registration, if you have not registered please do so [here](https://2021.emnlp.org/registration).

Registered attendees will receive access the week of November 1st.

EMNLP 2021 is planned to be a hybrid event in Punta Cana, Dominican Republic, with both on-site and fully virtual participation possible.

Recent progress in generative language models has enabled machines to generate astonishingly realistic texts. While there are many legitimate applications of such models, there is also a rising need to distinguish machine-generated texts from human-written ones (e.g., fake news detection). However, to our best knowledge, there is currently no benchmark environment with datasets and tasks to systematically study the so-called "Turing Test" problem for neural text generation methods. In this work, we present the TuringBench benchmark environment, which is comprised of (1) a dataset with 200K human- or machine-generated samples across 20 labels {Human, GPT-1, GPT-2_small, GPT-2_medium, GPT-2_large, GPT-2_xl, GPT-2_PyTorch, GPT-3, GROVER_base, GROVER_large, GROVER_mega, CTRL, XLM, XLNET_base, XLNET_large, FAIR_wmt19, FAIR_wmt20, TRANSFORMER_XL, PPLM_distil, PPLM_gpt2}, (2) two benchmark tasks -- i.e., Turing Test (TT) and Authorship Attribution (AA), and (3) a website with leaderboards. Our preliminary experimental results using TuringBench show that FAIR_wmt20 and GPT-3 are the current winners, among all language models tested, in generating the most human-like indistinguishable texts with the lowest F1 score by five state-of-the-art TT detection models. The TuringBench is available at: https://turingbench.ist.psu.edu/

workshop paper

Current research on quality estimation of machine translation focuses on the sentence-level quality of the translations. By using explainability methods, we can use these quality estimations for word-level error identification. In this work, we compare different explainability techniques and investigate gradient-based and perturbation-based methods by measuring their performance and required computational efforts. Throughout our experiments, we observed that using absolute word scores boosts the performance of gradient-based explainers significantly. Further, we combine explainability methods to ensembles to exploit the strengths of individual explainers to get better explanations. We propose the usage of absolute gradient-based methods. These work comparably well to popular perturbation-based ones while being more time-efficient.

Explaining Errors in Machine Translation with Absolute Gradient Ensembles

Quality Estimation (QE) for Machine Translation has been shown to reach 
relatively high accuracy in predicting sentence-level scores, relying on 
pretrained contextual embeddings and human-produced quality scores. 
However, the lack of explanations along with decisions made by end-to-
end neural models makes the results difficult to interpret. Furthermore, 
word-level annotated datasets are rare due to the prohibitive effort 
required to perform this task, while they could provide interpretable 
signals in addition to sentence-level QE outputs. In this paper, we 
propose a novel QE architecture which tackles both the word-level data 
scarcity and the interpretability limitations of recent approaches. 
Sentence-level and word-level components are jointly pretrained through 
an attention mechanism based on synthetic data and a set of MT metrics 
embedded in a common space. Our approach is evaluated on the Eval4NLP 
2021 shared task and our submissions reach the first position in all 
language pairs. The extraction of metric-to-input attention weights show 
that different metrics focus on different parts of the source and target 
text, providing strong rationales in the decision-making process of the 
QE model.

Error Identification for Machine Translation with Metric Embedding and Attention

Anticipating the rise in Artificial Intelligence’s ability to produce original works of literature, this study suggests that literariness, or that which constitutes a text as literary, is understudied in relation to text generation. From a computational perspective, literature is particularly challenging because it typically employs figurative and ambiguous language. Literary expertise would be beneficial to understanding how meaning and emotion are conveyed in this art form but is often overlooked. We propose placing experts from two dissimilar disciplines – machine learning and literary studies – in conversation to improve the quality of AI writing. Concentrating on evaluation as a vital stage in the text generation process, the study demonstrates that benefit could be derived from literary theoretical perspectives. This knowledge would improve algorithm design and enable a deeper understanding of how AI learns and generates.

This presentation is based on the following article: 
Imke van Heerden and Anil Bas, AI as Author – Bridging the Gap Between Machine Learning and Literary Theory, Journal of Artificial Intelligence Research, 71, pp. 175–189, 2021.

AI as Author – Bridging the Gap Between Machine Learning and Literary Theory

Estimating the expected output quality of generation systems is central to NLG. This paper qualifies the notion that automatic metrics are not as good as humans in estimating system-level quality. Statistically, humans are unbiased, high variance estimators, while metrics are biased, low variance estimators. We compare these estimators by their error in pairwise prediction (which generation system is better?) using the bootstrap. Measuring this error is complicated: predictions are evaluated against noisy, human predicted labels instead of the ground truth, and metric predictions fluctuate based on the test sets they were calculated on. By applying a bias-variance-noise decomposition, we adjust this error to a noise-free, infinite test set setting. Our analysis compares the adjusted error of metrics to humans and a derived, perfect segment-level annotator, both of which are unbiased estimators dependent on the number of judgments collected. In MT, we identify two settings where metrics outperform humans due to a statistical advantage in variance: when the number of human judgments used is small, and when the quality difference between compared systems is small.

The statistical advantage of automatic NLG metrics at the system level

Standard accuracy metrics have shown that Math Word Problem (MWP) solvers have achieved high performance on benchmark datasets. However, the extent to which existing MWP solvers truly understand language and its relation with numbers is still unclear. In this paper, we generate adversarial attacks to evaluate the robustness of state-of-the-art MWP solvers. We propose two methods Question Reordering and Sentence Paraphrasing to generate adversarial attacks. We conduct experiments across three neural MWP solvers over two benchmark datasets. On average, our attack method is able to reduce the accuracy of MWP solvers by over 40 percentage points on these datasets. Our results demonstrate that existing MWP solvers are sensitive to linguistic variations in the problem text. We verify the validity and quality of generated adversarial examples through human evaluation.

Adversarial Examples for Evaluating Math Word Problem Solvers

While powerful pre-trained language models have improved the fluency of text generation models, it remains difficult to ensure that the generated texts are semantically faithful to the input. In this paper, we introduce a novel automatic evaluation metric, Entity-Based Semantic Adequacy, which can be used to assess to what extent generation models that verbalise RDF (Resource Description Framework) graphs produce text that contains mentions of the entities occurring in the RDF input. This is important as RDF subject and object entities make up 2/3 of the input. We use our metric to compare 25 models from the WebNLG Shared Tasks and we examine correlation with results from human evaluations of semantic adequacy.
We show that while our metric correlates with human evaluation scores,
this correlation varies with the specifics of the human evaluation setup. This suggests that in order to measure the entity-based adequacy of generated texts, an automatic metric such as the one proposed here might be more reliable, as less subjective and more focused on correct verbalisation of the input, than human evaluation measures.

Entity-Based Semantic Adequacy for Data-to-Text Generation

There is an increasing interest in continuous learning (CL), as data privacy is becoming a priority for real-world machine learning applications. Meanwhile, there is still a lack of academic NLP benchmarks that are applicable for realistic CL settings, which is a major challenge for the advancement of the field. In
this paper we discuss some of the unrealistic data characteristics of public datasets, study the challenges of realistic single-task continuous learning as well as the effectiveness of data rehearsal as a way to mitigate accuracy loss. We construct a CL NER dataset from an existing publicly available dataset and release it along with the code to the research community.

Towards Realistic Single-Task Continuous Learning Research for NER

In the last few years, several methods have been proposed to build meta-embeddings. The general aim was to obtain new representations integrating complementary knowledge from different source pre-trained embeddings thereby improving their overall quality. However, previous meta-embeddings have been evaluated using a variety of methods and datasets, which makes it difficult to draw meaningful conclusions regarding the merits of each approach. In this paper we propose a unified common framework, including both intrinsic and extrinsic tasks, for a fair and objective meta-embeddings evaluation. Furthermore, we present a new method to generate meta-embeddings, outperforming previous work on a large number of intrinsic evaluation benchmarks. Our evaluation framework also allows us to conclude that previous extrinsic evaluations of meta-embeddings have been overestimated.

Benchmarking Meta-embeddings: What Works and What Does Not

Learning sentence embeddings often requires a large amount of labeled data. However, for most tasks and domains, labeled data is seldom available and creating it is expensive. In this work, we present a new state-of-the-art unsupervised method based on pre-trained Transformers and Sequential Denoising Auto-Encoder (TSDAE) which outperforms previous approaches by up to 6.4 points. It can achieve up to 93.1% of the performance of in-domain supervised approaches. Further, we show that TSDAE is a strong domain adaptation and pre-training method for sentence embeddings, significantly outperforming other approaches like Masked Language Model.
A crucial shortcoming of previous studies is the narrow evaluation: Most work mainly evaluates on the single task of Semantic Textual Similarity (STS), which does not require any domain knowledge. It is unclear if these proposed methods generalize to other domains and tasks. We fill this gap and evaluate TSDAE and other recent approaches on four different datasets from heterogeneous domains.

TSDAE: Using Transformer-based Sequential Denoising Auto-Encoder for Unsupervised Sentence Embedding Learning

Coreference Resolution is an important NLP task and most state-of-the-art methods rely on word embeddings for word representation. However, one issue that has been largely overlooked in literature is that of comparing the performance of different embeddings across and within families in this task. 
Therefore, we frame our study in the context of Event and Entity Coreference Resolution (EvCR \& EnCR), and address two questions : 
1) Is there a trade-off between performance (predictive \& run-time) and embedding size? 
2) How do the embeddings' performance compare within and across families?
Our experiments reveal several interesting findings. 
First, we observe diminishing returns in performance with respect to embedding size. 
E.g. a model using solely a character embedding achieves 86\% of the performance of the largest model (Elmo, GloVe, Character) while being 1.2\% of its size. 
Second, the larger model using multiple embeddings learns faster overall despite being slower per epoch. 
However, it is still slower at test time.
Finally, Elmo performs best on both EvCR and EnCR, while GloVe and FastText perform best in EvCR and EnCR respectively.

Downloads

Next from EMNLP 2021

Explaining Errors in Machine Translation with Absolute Gradient Ensembles

Similar lecture

TURINGBENCH: A Benchmark Environment for Turing Test in the Age of Neural Text Generation

.css-70qvj9{display:-webkit-box;display:-webkit-flex;display:-ms-flexbox;display:flex;-webkit-align-items:center;-webkit-box-align:center;-ms-flex-align:center;align-items:center;}Downloads

Next from EMNLP 2021

Explaining Errors in Machine Translation with Absolute Gradient Ensembles

Similar lecture

TURINGBENCH: A Benchmark Environment for Turing Test in the Age of Neural Text Generation

Downloads